xfs: repair summary countersrepair-hard-problems_2019-10-09

Use the same summary counter calculation infrastructure to generate new
values for the in-core summary counters.   The difference between the
scrubber and the repairer is that the repairer will freeze the fs during
setup, which means that the values should match exactly.

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

6 files changed, 103 insertions, 6 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 3cff8b68637c..74073ff034ec 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -166,6 +166,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   bitmap.o \
 				   blob.o \
 				   bmap_repair.o \
+				   fscounters_repair.o \
 				   ialloc_repair.o \
 				   inode_repair.o \
 				   refcount_repair.o \
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index 98f82d7c8b40..e536ab6fdad0 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -40,6 +40,10 @@
  * structures as quickly as it can.  We snapshot the percpu counters before and
  * after this operation and use the difference in counter values to guess at
  * our tolerance for mismatch between expected and actual counter values.
+ *
+ * NOTE: If the calling application has permitted us to repair the counters,
+ * we /must/ prevent all other filesystem activity by freezing it.  Since we've
+ * frozen the filesystem, we can require an exact match.
  */
 
 /*
@@ -141,8 +145,19 @@ xchk_setup_fscounters(
 	 * Pause background reclaim while we're scrubbing to reduce the
 	 * likelihood of background perturbations to the counters throwing off
 	 * our calculations.
+	 *
+	 * If we're repairing, we need to prevent any other thread from
+	 * changing the global fs summary counters while we're repairing them.
+	 * This requires the fs to be frozen, which will disable background
+	 * reclaim and purge all inactive inodes.
 	 */
-	xchk_stop_reaping(sc);
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+		error = xchk_fs_freeze(sc);
+		if (error)
+			return error;
+	} else {
+		xchk_stop_reaping(sc);
+	}
 
 	return xchk_trans_alloc(sc, 0);
 }
@@ -251,6 +266,8 @@ retry:
  * Otherwise, we /might/ have a problem.  If the change in the summations is
  * more than we want to tolerate, the filesystem is probably busy and we should
  * just send back INCOMPLETE and see if userspace will try again.
+ *
+ * If we're repairing then we require an exact match.
  */
 static inline bool
 xchk_fscount_within_range(
@@ -273,6 +290,10 @@ xchk_fscount_within_range(
 	if (curr_value == expected)
 		return true;
 
+	/* We require exact matches when repair is running. */
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+		return false;
+
 	min_value = min(old_value, curr_value);
 	max_value = max(old_value, curr_value);
 
diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c
new file mode 100644
index 000000000000..c3d2214133ff
--- /dev/null
+++ b/fs/xfs/scrub/fscounters_repair.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Copyright (C) 2019 Oracle.  All Rights Reserved.
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_btree.h"
+#include "xfs_bit.h"
+#include "xfs_log_format.h"
+#include "xfs_trans.h"
+#include "xfs_sb.h"
+#include "xfs_inode.h"
+#include "xfs_alloc.h"
+#include "xfs_ialloc.h"
+#include "xfs_rmap.h"
+#include "xfs_health.h"
+#include "scrub/xfs_scrub.h"
+#include "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/trace.h"
+#include "scrub/repair.h"
+
+/*
+ * FS Summary Counters
+ * ===================
+ *
+ * We correct errors in the filesystem summary counters by setting them to the
+ * values computed during the obligatory scrub phase.  However, we must be
+ * careful not to allow any other thread to change the counters while we're
+ * computing and setting new values.  To achieve this, we freeze the
+ * filesystem for the whole operation if the REPAIR flag is set.  The checking
+ * function is stricter when we've frozen the fs.
+ */
+
+/*
+ * Reset the superblock counters.  Caller is responsible for freezing the
+ * filesystem during the calculation and reset phases.
+ */
+int
+xrep_fscounters(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_mount	*mp = sc->mp;
+	struct xchk_fscounters	*fsc = sc->buf;
+
+	/*
+	 * Reinitialize the in-core counters from what we computed.  We froze
+	 * the filesystem, so there shouldn't be anyone else trying to modify
+	 * these counters.
+	 */
+	ASSERT(sc->flags & XCHK_FS_FROZEN);
+	percpu_counter_set(&mp->m_icount, fsc->icount);
+	percpu_counter_set(&mp->m_ifree, fsc->ifree);
+	percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks);
+
+	return 0;
+}
diff --git a/fs/xfs/scrub/repair.h b/fs/xfs/scrub/repair.h
index 057dc51c490f..edf36afe9000 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -85,6 +85,7 @@ int xrep_quota(struct xfs_scrub *sc);
 #else
 # define xrep_quota			xrep_notsupported
 #endif /* CONFIG_XFS_QUOTA */
+int xrep_fscounters(struct xfs_scrub *sc);
 
 struct xrep_newbt_resv {
 	/* Link to list of extents that we've reserved. */
@@ -203,6 +204,7 @@ xrep_rmapbt_setup(
 #define xrep_symlink			xrep_notsupported
 #define xrep_xattr			xrep_notsupported
 #define xrep_quota			xrep_notsupported
+#define xrep_fscounters			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 10adf5475fc0..1085db9a2a24 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -347,7 +347,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.type	= ST_FS,
 		.setup	= xchk_setup_fscounters,
 		.scrub	= xchk_fscounters,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_fscounters,
 	},
 	[XFS_SCRUB_TYPE_HEALTHY] = {	/* fs healthy; clean all reminders */
 		.type	= ST_FS,
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index bc01b56e8bd1..ebf06e247411 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -949,16 +949,26 @@ TRACE_EVENT(xrep_calc_ag_resblks_btsize,
 		  __entry->refcbt_sz)
 )
 TRACE_EVENT(xrep_reset_counters,
-	TP_PROTO(struct xfs_mount *mp),
-	TP_ARGS(mp),
+	TP_PROTO(struct xfs_mount *mp, int64_t icount_adj, int64_t ifree_adj,
+		 int64_t fdblocks_adj),
+	TP_ARGS(mp, icount_adj, ifree_adj, fdblocks_adj),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
+		__field(int64_t, icount_adj)
+		__field(int64_t, ifree_adj)
+		__field(int64_t, fdblocks_adj)
 	),
 	TP_fast_assign(
 		__entry->dev = mp->m_super->s_dev;
+		__entry->icount_adj = icount_adj;
+		__entry->ifree_adj = ifree_adj;
+		__entry->fdblocks_adj = fdblocks_adj;
 	),
-	TP_printk("dev %d:%d",
-		  MAJOR(__entry->dev), MINOR(__entry->dev))
+	TP_printk("dev %d:%d icount %lld ifree %lld fdblocks %lld",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->icount_adj,
+		  __entry->ifree_adj,
+		  __entry->fdblocks_adj)
 )
 
 DECLARE_EVENT_CLASS(xrep_newbt_extent_class,