xfs: repair refcount btrees

Reconstruct the refcount data from the rmap btree.

Link: https://docs.kernel.org/filesystems/xfs-online-fsck-design.html#case-study-rebuilding-the-space-reference-counts
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

fs/xfs/Makefile

@@ -186,6 +186,7 @@ xfs-y				+= $(addprefix scrub/, \
 				   ialloc_repair.o \
 				   newbt.o \
 				   reap.o \
+				   refcount_repair.o \
 				   repair.o \
 				   )
 endif

fs/xfs/libxfs/xfs_ag.h

@@ -87,6 +87,7 @@ struct xfs_perag {
 	 * verifiers while rebuilding the AG btrees.
 	 */
 	uint8_t		pagf_repair_levels[XFS_BTNUM_AGF];
+	uint8_t		pagf_repair_refcount_level;
 #endif
 
 	spinlock_t	pag_state_lock;

fs/xfs/libxfs/xfs_btree.c

@@ -5212,3 +5212,29 @@ xfs_btree_destroy_cur_caches(void)
 	xfs_rmapbt_destroy_cur_cache();
 	xfs_refcountbt_destroy_cur_cache();
 }
+
+/* Move the btree cursor before the first record. */
+int
+xfs_btree_goto_left_edge(
+	struct xfs_btree_cur	*cur)
+{
+	int			stat = 0;
+	int			error;
+
+	memset(&cur->bc_rec, 0, sizeof(cur->bc_rec));
+	error = xfs_btree_lookup(cur, XFS_LOOKUP_LE, &stat);
+	if (error)
+		return error;
+	if (!stat)
+		return 0;
+
+	error = xfs_btree_decrement(cur, 0, &stat);
+	if (error)
+		return error;
+	if (stat != 0) {
+		ASSERT(0);
+		return -EFSCORRUPTED;
+	}
+
+	return 0;
+}

fs/xfs/libxfs/xfs_btree.h

@@ -738,4 +738,6 @@ xfs_btree_alloc_cursor(
 int __init xfs_btree_init_cur_caches(void);
 void xfs_btree_destroy_cur_caches(void);
 
+int xfs_btree_goto_left_edge(struct xfs_btree_cur *cur);
+
 #endif	/* __XFS_BTREE_H__ */

fs/xfs/libxfs/xfs_refcount.c

@@ -123,11 +123,9 @@ xfs_refcount_btrec_to_irec(
 /* Simple checks for refcount records. */
 xfs_failaddr_t
 xfs_refcount_check_irec(
-	struct xfs_btree_cur		*cur,
+	struct xfs_perag		*pag,
 	const struct xfs_refcount_irec	*irec)
 {
-	struct xfs_perag		*pag = cur->bc_ag.pag;
-
 	if (irec->rc_blockcount == 0 || irec->rc_blockcount > MAXREFCEXTLEN)
 		return __this_address;
 
@@ -179,7 +177,7 @@ xfs_refcount_get_rec(
 		return error;
 
 	xfs_refcount_btrec_to_irec(rec, irec);
-	fa = xfs_refcount_check_irec(cur, irec);
+	fa = xfs_refcount_check_irec(cur->bc_ag.pag, irec);
 	if (fa)
 		return xfs_refcount_complain_bad_rec(cur, fa, irec);
 
@@ -1899,7 +1897,7 @@ xfs_refcount_recover_extent(
 	INIT_LIST_HEAD(&rr->rr_list);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
 
-	if (xfs_refcount_check_irec(cur, &rr->rr_rrec) != NULL ||
+	if (xfs_refcount_check_irec(cur->bc_ag.pag, &rr->rr_rrec) != NULL ||
 	    XFS_IS_CORRUPT(cur->bc_mp,
 			   rr->rr_rrec.rc_domain != XFS_REFC_DOMAIN_COW)) {
 		kfree(rr);

fs/xfs/libxfs/xfs_refcount.h

@@ -117,7 +117,7 @@ extern int xfs_refcount_has_records(struct xfs_btree_cur *cur,
 union xfs_btree_rec;
 extern void xfs_refcount_btrec_to_irec(const union xfs_btree_rec *rec,
 		struct xfs_refcount_irec *irec);
-xfs_failaddr_t xfs_refcount_check_irec(struct xfs_btree_cur *cur,
+xfs_failaddr_t xfs_refcount_check_irec(struct xfs_perag *pag,
 		const struct xfs_refcount_irec *irec);
 extern int xfs_refcount_insert(struct xfs_btree_cur *cur,
 		struct xfs_refcount_irec *irec, int *stat);

fs/xfs/libxfs/xfs_refcount_btree.c

@@ -226,7 +226,18 @@ xfs_refcountbt_verify(
 
 	level = be16_to_cpu(block->bb_level);
 	if (pag && xfs_perag_initialised_agf(pag)) {
-		if (level >= pag->pagf_refcount_level)
+		unsigned int	maxlevel = pag->pagf_refcount_level;
+
+#ifdef CONFIG_XFS_ONLINE_REPAIR
+		/*
+		 * Online repair could be rewriting the refcount btree, so
+		 * we'll validate against the larger of either tree while this
+		 * is going on.
+		 */
+		maxlevel = max_t(unsigned int, maxlevel,
+				pag->pagf_repair_refcount_level);
+#endif
+		if (level >= maxlevel)
 			return __this_address;
 	} else if (level >= mp->m_refc_maxlevels)
 		return __this_address;

fs/xfs/scrub/refcount.c

@@ -441,7 +441,7 @@ xchk_refcountbt_rec(
 	struct xchk_refcbt_records *rrc = bs->private;
 
 	xfs_refcount_btrec_to_irec(rec, &irec);
-	if (xfs_refcount_check_irec(bs->cur, &irec) != NULL) {
+	if (xfs_refcount_check_irec(bs->cur->bc_ag.pag, &irec) != NULL) {
 		xchk_btree_set_corrupt(bs->sc, bs->cur, 0);
 		return 0;
 	}

fs/xfs/scrub/repair.h

@@ -80,6 +80,7 @@ int xrep_agfl(struct xfs_scrub *sc);
 int xrep_agi(struct xfs_scrub *sc);
 int xrep_allocbt(struct xfs_scrub *sc);
 int xrep_iallocbt(struct xfs_scrub *sc);
+int xrep_refcountbt(struct xfs_scrub *sc);
 
 int xrep_reinit_pagf(struct xfs_scrub *sc);
 int xrep_reinit_pagi(struct xfs_scrub *sc);
@@ -133,6 +134,7 @@ xrep_setup_nothing(
 #define xrep_agi			xrep_notsupported
 #define xrep_allocbt			xrep_notsupported
 #define xrep_iallocbt			xrep_notsupported
+#define xrep_refcountbt			xrep_notsupported
 
 #endif /* CONFIG_XFS_ONLINE_REPAIR */
 

fs/xfs/scrub/scrub.c

@@ -276,7 +276,7 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 		.setup	= xchk_setup_ag_refcountbt,
 		.scrub	= xchk_refcountbt,
 		.has	= xfs_has_reflink,
-		.repair	= xrep_notsupported,
+		.repair	= xrep_refcountbt,
 	},
 	[XFS_SCRUB_TYPE_INODE] = {	/* inode record */
 		.type	= ST_INODE,

fs/xfs/scrub/trace.h

@@ -1232,27 +1232,29 @@ TRACE_EVENT(xrep_ibt_found,
 		  __entry->freemask)
 )
 
-TRACE_EVENT(xrep_refcount_extent_fn,
-	TP_PROTO(struct xfs_mount *mp, xfs_agnumber_t agno,
-		 struct xfs_refcount_irec *irec),
-	TP_ARGS(mp, agno, irec),
+TRACE_EVENT(xrep_refc_found,
+	TP_PROTO(struct xfs_perag *pag, const struct xfs_refcount_irec *rec),
+	TP_ARGS(pag, rec),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(xfs_agnumber_t, agno)
+		__field(enum xfs_refc_domain, domain)
 		__field(xfs_agblock_t, startblock)
 		__field(xfs_extlen_t, blockcount)
 		__field(xfs_nlink_t, refcount)
 	),
 	TP_fast_assign(
-		__entry->dev = mp->m_super->s_dev;
-		__entry->agno = agno;
-		__entry->startblock = irec->rc_startblock;
-		__entry->blockcount = irec->rc_blockcount;
-		__entry->refcount = irec->rc_refcount;
+		__entry->dev = pag->pag_mount->m_super->s_dev;
+		__entry->agno = pag->pag_agno;
+		__entry->domain = rec->rc_domain;
+		__entry->startblock = rec->rc_startblock;
+		__entry->blockcount = rec->rc_blockcount;
+		__entry->refcount = rec->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x refcount %u",
+	TP_printk("dev %d:%d agno 0x%x dom %s agbno 0x%x fsbcount 0x%x refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
+		  __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS),
 		  __entry->startblock,
 		  __entry->blockcount,
 		  __entry->refcount)