xfs: repair summary countersrepair-part-three_2019-04-15djwong-experimental_2019-04-15

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, 100 insertions, 7 deletions

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index d7412c191575..f344def0f2af 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -167,6 +167,7 @@ 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 add36e824845..e5575bb67418 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -53,6 +53,8 @@ xchk_setup_fscounters(
 	struct xfs_scrub	*sc,
 	struct xfs_inode	*ip)
 {
+	int			error;
+
 	sc->buf = kmem_zalloc(sizeof(struct xchk_fscounters), KM_SLEEP);
 	if (!sc->buf)
 		return -ENOMEM;
@@ -61,8 +63,19 @@ 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_disable_reclaim(sc);
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR) {
+		error = xchk_fs_freeze(sc);
+		if (error)
+			return error;
+	} else {
+		xchk_disable_reclaim(sc);
+	}
 
 	return xchk_trans_alloc(sc, 0);
 }
@@ -153,6 +166,7 @@ xchk_fscounters_calc(
  * Is the @counter within an acceptable range of @expected?
  *
  * Currently that means 1/16th (6%) or @nr_range of the @expected value.
+ * If we're repairing then we require an exact match.
  */
 static inline bool
 xchk_fscounter_within_range(
@@ -164,7 +178,10 @@ xchk_fscounter_within_range(
 	int64_t			value = percpu_counter_sum(counter);
 	uint64_t		range;
 
-	range = max_t(uint64_t, expected >> 4, nr_range);
+	if (sc->sm->sm_flags & XFS_SCRUB_IFLAG_REPAIR)
+		range = 0;
+	else
+		range = max_t(uint64_t, expected >> 4, nr_range);
 	if (value < 0)
 		return false;
 	if (range < expected && value < expected - range)
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 f0f811ca3e51..5fe91fc7a056 100644
--- a/fs/xfs/scrub/repair.h
+++ b/fs/xfs/scrub/repair.h
@@ -82,6 +82,7 @@ int xrep_quota(struct xfs_scrub *sc);
 #else
 # define xrep_quota			xrep_notsupported
 #endif /* CONFIG_XFS_QUOTA */
+int xrep_fscounters(struct xfs_scrub *sc);
 
 #else
 
@@ -141,6 +142,7 @@ 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 c96f5dcc22ea..91c1f650802b 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -374,7 +374,7 @@ 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,
 	},
 };
 
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 1e958836d27a..c4590a46f355 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -848,16 +848,26 @@ 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)
 )
 
 TRACE_EVENT(xrep_ibt_insert,