@@ -188,6 +188,7 @@ xfs-y += $(addprefix scrub/, \
alloc_repair.o \
bmap_repair.o \
cow_repair.o \
+ fscounters_repair.o \
ialloc_repair.o \
inode_repair.o \
newbt.o \
@@ -199,8 +199,13 @@ xchk_setup_fscounters(
* Pause all writer activity in the filesystem 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.
*/
- if (sc->flags & XCHK_TRY_HARDER) {
+ if ((sc->flags & XCHK_TRY_HARDER) || xchk_could_repair(sc)) {
error = xchk_fscounters_freeze(sc);
if (error)
return error;
@@ -218,7 +223,9 @@ xchk_setup_fscounters(
* set the INCOMPLETE flag even when a negative errno is returned. This care
* must be taken with certain errno values (i.e. EFSBADCRC, EFSCORRUPTED,
* ECANCELED) that are absorbed into a scrub state flag update by
- * xchk_*_process_error.
+ * xchk_*_process_error. Scrub and repair share the same incore data
+ * structures, so the INCOMPLETE flag is critical to prevent a repair based on
+ * insufficient information.
*/
/* Count free space btree blocks manually for pre-lazysbcount filesystems. */
@@ -446,6 +453,10 @@ 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);
new file mode 100644
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2018-2023 Oracle. All Rights Reserved.
+ * Author: Darrick J. Wong <djwong@kernel.org>
+ */
+#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"
+#include "scrub/fscounters.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.
+ */
+ if (!fsc->frozen) {
+ ASSERT(fsc->frozen);
+ return -EFSCORRUPTED;
+ }
+
+ trace_xrep_reset_counters(mp, fsc);
+
+ percpu_counter_set(&mp->m_icount, fsc->icount);
+ percpu_counter_set(&mp->m_ifree, fsc->ifree);
+ percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks);
+ percpu_counter_set(&mp->m_frextents, fsc->frextents);
+ mp->m_sb.sb_frextents = fsc->frextents;
+
+ return 0;
+}
@@ -109,6 +109,7 @@ int xrep_bmap_data(struct xfs_scrub *sc);
int xrep_bmap_attr(struct xfs_scrub *sc);
int xrep_bmap_cow(struct xfs_scrub *sc);
int xrep_nlinks(struct xfs_scrub *sc);
+int xrep_fscounters(struct xfs_scrub *sc);
#ifdef CONFIG_XFS_RT
int xrep_rtbitmap(struct xfs_scrub *sc);
@@ -194,6 +195,7 @@ static inline int xrep_setup_rtbitmap(struct xfs_scrub *sc, unsigned int *x)
#define xrep_quota xrep_notsupported
#define xrep_quotacheck xrep_notsupported
#define xrep_nlinks xrep_notsupported
+#define xrep_fscounters xrep_notsupported
#endif /* CONFIG_XFS_ONLINE_REPAIR */
@@ -367,7 +367,7 @@ 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_QUOTACHECK] = { /* quota counters */
.type = ST_FS,
@@ -20,6 +20,7 @@
#include "scrub/xfarray.h"
#include "scrub/iscan.h"
#include "scrub/nlinks.h"
+#include "scrub/fscounters.h"
/* Figure out which block the btree cursor was pointing to. */
static inline xfs_fsblock_t
@@ -23,6 +23,7 @@ struct xfarray;
struct xfarray_sortinfo;
struct xchk_iscan;
struct xchk_nlink;
+struct xchk_fscounters;
/*
* ftrace's __print_symbolic requires that all enum values be wrapped in the
@@ -1671,16 +1672,28 @@ 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, struct xchk_fscounters *fsc),
+ TP_ARGS(mp, fsc),
TP_STRUCT__entry(
__field(dev_t, dev)
+ __field(uint64_t, icount)
+ __field(uint64_t, ifree)
+ __field(uint64_t, fdblocks)
+ __field(uint64_t, frextents)
),
TP_fast_assign(
__entry->dev = mp->m_super->s_dev;
+ __entry->icount = fsc->icount;
+ __entry->ifree = fsc->ifree;
+ __entry->fdblocks = fsc->fdblocks;
+ __entry->frextents = fsc->frextents;
),
- TP_printk("dev %d:%d",
- MAJOR(__entry->dev), MINOR(__entry->dev))
+ TP_printk("dev %d:%d icount %llu ifree %llu fdblocks %llu frextents %llu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ __entry->icount,
+ __entry->ifree,
+ __entry->fdblocks,
+ __entry->frextents)
)
DECLARE_EVENT_CLASS(xrep_newbt_extent_class,