xfs: update health status if we get a clean bill of healthindirect-health-reporting_2019-10-19

If scrub finds that everything is ok with the filesystem, we need a way
to tell the health tracking that it can let go of indirect health flags,
since indirect flags only mean that at some point in the past we lost
some context.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>

1 files changed, 71 insertions, 0 deletions

diff --git a/fs/xfs/scrub/health.c b/fs/xfs/scrub/health.c
index 3f93bb81f06f..ce97581015ce 100644
--- a/fs/xfs/scrub/health.c
+++ b/fs/xfs/scrub/health.c
@@ -7,10 +7,13 @@
 #include "xfs_fs.h"
 #include "xfs_shared.h"
 #include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
 #include "xfs_btree.h"
 #include "xfs_sb.h"
 #include "xfs_health.h"
 #include "scrub/scrub.h"
+#include "scrub/common.h"
 
 /*
  * Scrub and In-Core Filesystem Health Assessments
@@ -113,6 +116,28 @@ xchk_health_mask_for_scrub_type(
 }
 
 /*
+ * Scrub gave the filesystem a clean bill of health, so clear all the indirect
+ * markers of past problems (at least for the fs and ags) so that we can be
+ * healthy again.
+ */
+STATIC void
+xchk_mark_all_healthy(
+	struct xfs_mount	*mp)
+{
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	int			error = 0;
+
+	xfs_fs_mark_healthy(mp, XFS_SICK_FS_INDIRECT);
+	xfs_rt_mark_healthy(mp, XFS_SICK_RT_INDIRECT);
+	for (agno = 0; error == 0 && agno < mp->m_sb.sb_agcount; agno++) {
+		pag = xfs_perag_get(mp, agno);
+		xfs_ag_mark_healthy(pag, XFS_SICK_AG_INDIRECT);
+		xfs_perag_put(pag);
+	}
+}
+
+/*
  * Update filesystem health assessments based on what we found and did.
  *
  * If the scrubber finds errors, we mark sick whatever's mentioned in
@@ -129,6 +154,18 @@ xchk_update_health(
 	struct xfs_perag	*pag;
 	bool			bad;
 
+	/*
+	 * The HEALTHY scrub type is a request from userspace to clear all the
+	 * indirect flags after a clean scan of the entire filesystem.  As such
+	 * there's no sick flag defined for it, so we branch here ahead of the
+	 * mask check.
+	 */
+	if (sc->sm->sm_type == XFS_SCRUB_TYPE_HEALTHY &&
+	    !(sc->sm->sm_flags & XFS_SCRUB_OFLAG_CORRUPT)) {
+		xchk_mark_all_healthy(sc->mp);
+		return;
+	}
+
 	if (!sc->sick_mask)
 		return;
 
@@ -247,3 +284,37 @@ xchk_ag_btree_healthy_enough(
 
 	return true;
 }
+
+/*
+ * Quick scan to double-check that there isn't any evidence of lingering
+ * primary health problems.  If we're still clear, then the health update will
+ * take care of clearing the indirect evidence.
+ */
+int
+xchk_health_record(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xfs_perag	*pag;
+	xfs_agnumber_t		agno;
+	unsigned int		sick;
+	unsigned int		checked;
+
+	xfs_fs_measure_sickness(mp, &sick, &checked);
+	if (sick & XFS_SICK_FS_PRIMARY)
+		xchk_set_corrupt(sc);
+
+	xfs_rt_measure_sickness(mp, &sick, &checked);
+	if (sick & XFS_SICK_RT_PRIMARY)
+		xchk_set_corrupt(sc);
+
+	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+		pag = xfs_perag_get(mp, agno);
+		xfs_ag_measure_sickness(pag, &sick, &checked);
+		if (sick & XFS_SICK_AG_PRIMARY)
+			xchk_set_corrupt(sc);
+		xfs_perag_put(pag);
+	}
+
+	return 0;
+}