xfs: report btree block corruption errors to the health system

Whenever we encounter corrupt btree blocks, we should report that to the
health monitoring system for later reporting.

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

10 files changed, 81 insertions, 7 deletions

diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 578794c93782..fd78088a1ce8 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -261,6 +261,7 @@ out_bad_rec:
 		cur->bc_btnum == XFS_BTNUM_BNO ? "Block" : "Size", agno);
 	xfs_warn(mp,
 		"start block 0x%x block count 0x%x", *bno, *len);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 01572821408a..723b271c41d2 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -367,6 +367,8 @@ xfs_bmap_check_leaf_extents(
 			error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
 						XFS_BMAP_BTREE_REF,
 						&xfs_bmbt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(cur);
 			if (error)
 				goto error_norelse;
 		}
@@ -453,6 +455,8 @@ xfs_bmap_check_leaf_extents(
 			error = xfs_btree_read_bufl(mp, NULL, bno, &bp,
 						XFS_BMAP_BTREE_REF,
 						&xfs_bmbt_buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(cur);
 			if (error)
 				goto error_norelse;
 		}
@@ -617,6 +621,8 @@ xfs_bmap_btree_to_extents(
 #endif
 	error = xfs_btree_read_bufl(mp, tp, cbno, &cbp, XFS_BMAP_BTREE_REF,
 				&xfs_bmbt_buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
 	if (error)
 		return error;
 	cblock = XFS_BUF_TO_BLOCK(cbp);
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 2d25bab68764..97a27eee4568 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -21,6 +21,7 @@
 #include "xfs_alloc.h"
 #include "xfs_log.h"
 #include "xfs_btree_staging.h"
+#include "xfs_health.h"
 
 /*
  * Cursor allocation zone.
@@ -110,6 +111,7 @@ xfs_btree_check_lblock(
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_LBLOCK)) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -173,6 +175,7 @@ xfs_btree_check_sblock(
 	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BTREE_CHECK_SBLOCK)) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
 	}
 	return 0;
@@ -248,6 +251,7 @@ xfs_btree_check_ptr(
 				level, index);
 	}
 
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -429,6 +433,8 @@ xfs_btree_dup_cursor(
 						   XFS_BUF_ADDR(bp), mp->m_bsize,
 						   0, &bp,
 						   cur->bc_ops->buf_ops);
+			if (xfs_metadata_is_sick(error))
+				xfs_btree_mark_sick(new);
 			if (error) {
 				xfs_btree_del_cursor(new, error);
 				*ncur = NULL;
@@ -1282,6 +1288,8 @@ xfs_btree_read_buf_block(
 	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
 				   mp->m_bsize, flags, bpp,
 				   cur->bc_ops->buf_ops);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
 	if (error)
 		return error;
 
@@ -1592,6 +1600,7 @@ xfs_btree_increment(
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			goto out0;
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1685,6 +1694,7 @@ xfs_btree_decrement(
 		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
 			goto out0;
 		ASSERT(0);
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto error0;
 	}
@@ -1777,6 +1787,7 @@ out_bad:
 	*blkp = NULL;
 	xfs_buf_mark_corrupt(bp);
 	xfs_trans_brelse(cur->bc_tp, bp);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1823,8 +1834,10 @@ xfs_btree_lookup(
 	XFS_BTREE_STATS_INC(cur, lookup);
 
 	/* No such thing as a zero-level tree. */
-	if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0))
+	if (XFS_IS_CORRUPT(cur->bc_mp, cur->bc_nlevels == 0)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	block = NULL;
 	keyno = 0;
@@ -1867,6 +1880,7 @@ xfs_btree_lookup(
 							XFS_ERRLEVEL_LOW,
 							cur->bc_mp, block,
 							sizeof(*block));
+					xfs_btree_mark_sick(cur);
 					return -EFSCORRUPTED;
 				}
 
diff --git a/fs/xfs/libxfs/xfs_health.h b/fs/xfs/libxfs/xfs_health.h
index e0ad4eb03446..8e3247a192c1 100644
--- a/fs/xfs/libxfs/xfs_health.h
+++ b/fs/xfs/libxfs/xfs_health.h
@@ -37,6 +37,7 @@ struct xfs_mount;
 struct xfs_perag;
 struct xfs_inode;
 struct xfs_fsop_geom;
+struct xfs_btree_cur;
 
 /* Observable health issues for metadata spanning the entire filesystem. */
 #define XFS_SICK_FS_COUNTERS	(1 << 0)  /* summary counters */
@@ -139,6 +140,7 @@ void xfs_inode_measure_sickness(struct xfs_inode *ip, unsigned int *sick,
 
 void xfs_health_unmount(struct xfs_mount *mp);
 void xfs_bmap_mark_sick(struct xfs_inode *ip, int whichfork);
+void xfs_btree_mark_sick(struct xfs_btree_cur *cur);
 
 /* Now some helpers. */
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 5e79389b81c8..f2f2ef96f4ab 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -151,6 +151,7 @@ out_bad_rec:
 "start inode 0x%x, count 0x%x, free 0x%x freemask 0x%llx, holemask 0x%x",
 		irec->ir_startino, irec->ir_count, irec->ir_freecount,
 		irec->ir_free, irec->ir_holemask);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 2076627243b0..74aa1c032219 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -22,6 +22,7 @@
 #include "xfs_bit.h"
 #include "xfs_refcount.h"
 #include "xfs_rmap.h"
+#include "xfs_health.h"
 
 /* Allowable refcount adjustment amounts. */
 enum xfs_refc_adjust_op {
@@ -153,6 +154,7 @@ out_bad_rec:
 	xfs_warn(mp,
 		"Start block 0x%x, block count 0x%x, references 0x%x",
 		irec->rc_startblock, irec->rc_blockcount, irec->rc_refcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1667,8 +1669,10 @@ xfs_refcount_recover_extent(
 	struct xfs_refcount_recovery	*rr;
 
 	if (XFS_IS_CORRUPT(cur->bc_mp,
-			   be32_to_cpu(rec->refc.rc_refcount) != 1))
+			   be32_to_cpu(rec->refc.rc_refcount) != 1)) {
+		xfs_btree_mark_sick(cur);
 		return -EFSCORRUPTED;
+	}
 
 	rr = kmem_alloc(sizeof(struct xfs_refcount_recovery), 0);
 	xfs_refcount_btrec_to_irec(rec, &rr->rr_rrec);
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 27c39268c31f..85bf792b76cd 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -21,6 +21,7 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_inode.h"
+#include "xfs_health.h"
 
 /*
  * Lookup the first record less than or equal to [bno, len, owner, offset]
@@ -177,14 +178,20 @@ done:
 /* Convert an internal btree record to an rmap record. */
 int
 xfs_rmap_btrec_to_irec(
+	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*rec,
 	struct xfs_rmap_irec	*irec)
 {
+	int			error;
+
 	irec->rm_startblock = be32_to_cpu(rec->rmap.rm_startblock);
 	irec->rm_blockcount = be32_to_cpu(rec->rmap.rm_blockcount);
 	irec->rm_owner = be64_to_cpu(rec->rmap.rm_owner);
-	return xfs_rmap_irec_offset_unpack(be64_to_cpu(rec->rmap.rm_offset),
+	error = xfs_rmap_irec_offset_unpack(be64_to_cpu(rec->rmap.rm_offset),
 			irec);
+	if (xfs_metadata_is_sick(error))
+		xfs_btree_mark_sick(cur);
+	return error;
 }
 
 /*
@@ -205,7 +212,7 @@ xfs_rmap_get_rec(
 	if (error || !*stat)
 		return error;
 
-	if (xfs_rmap_btrec_to_irec(rec, irec))
+	if (xfs_rmap_btrec_to_irec(cur, rec, irec))
 		goto out_bad_rec;
 
 	if (irec->rm_blockcount == 0)
@@ -241,6 +248,7 @@ out_bad_rec:
 		"Owner 0x%llx, flags 0x%x, start block 0x%x block count 0x%x",
 		irec->rm_owner, irec->rm_flags, irec->rm_startblock,
 		irec->rm_blockcount);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -2284,7 +2292,7 @@ xfs_rmap_query_range_helper(
 	struct xfs_rmap_irec			irec;
 	int					error;
 
-	error = xfs_rmap_btrec_to_irec(rec, &irec);
+	error = xfs_rmap_btrec_to_irec(cur, rec, &irec);
 	if (error)
 		return error;
 	return query->fn(cur, &irec, query->priv);
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index abe633403fd1..e756989d0da5 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -190,7 +190,7 @@ int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 int xfs_rmap_compare(const struct xfs_rmap_irec *a,
 		const struct xfs_rmap_irec *b);
 union xfs_btree_rec;
-int xfs_rmap_btrec_to_irec(union xfs_btree_rec *rec,
+int xfs_rmap_btrec_to_irec(struct xfs_btree_cur *cur, union xfs_btree_rec *rec,
 		struct xfs_rmap_irec *irec);
 int xfs_rmap_has_record(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, bool *exists);
diff --git a/fs/xfs/scrub/rmap.c b/fs/xfs/scrub/rmap.c
index f4fcb4719f41..71028886562d 100644
--- a/fs/xfs/scrub/rmap.c
+++ b/fs/xfs/scrub/rmap.c
@@ -99,7 +99,7 @@ xchk_rmapbt_rec(
 	bool			is_attr;
 	int			error;
 
-	error = xfs_rmap_btrec_to_irec(rec, &irec);
+	error = xfs_rmap_btrec_to_irec(bs->cur, rec, &irec);
 	if (!xchk_btree_process_error(bs->sc, bs->cur, 0, &error))
 		goto out;
 
diff --git a/fs/xfs/xfs_health.c b/fs/xfs/xfs_health.c
index 5e5de5338476..765188f64f7c 100644
--- a/fs/xfs/xfs_health.c
+++ b/fs/xfs/xfs_health.c
@@ -14,6 +14,7 @@
 #include "xfs_inode.h"
 #include "xfs_trace.h"
 #include "xfs_health.h"
+#include "xfs_btree.h"
 
 /*
  * Warn about metadata corruption that we detected but haven't fixed, and
@@ -478,3 +479,40 @@ xfs_bmap_mark_sick(
 
 	xfs_inode_mark_sick(ip, mask);
 }
+
+/* Record observations of btree corruption with the health tracking system. */
+void
+xfs_btree_mark_sick(
+	struct xfs_btree_cur		*cur)
+{
+	unsigned int			mask;
+
+	switch (cur->bc_btnum) {
+	case XFS_BTNUM_BMAP:
+		xfs_bmap_mark_sick(cur->bc_ino.ip, cur->bc_ino.whichfork);
+		return;
+	case XFS_BTNUM_BNO:
+		mask = XFS_SICK_AG_BNOBT;
+		break;
+	case XFS_BTNUM_CNT:
+		mask = XFS_SICK_AG_CNTBT;
+		break;
+	case XFS_BTNUM_INO:
+		mask = XFS_SICK_AG_INOBT;
+		break;
+	case XFS_BTNUM_FINO:
+		mask = XFS_SICK_AG_FINOBT;
+		break;
+	case XFS_BTNUM_RMAP:
+		mask = XFS_SICK_AG_RMAPBT;
+		break;
+	case XFS_BTNUM_REFC:
+		mask = XFS_SICK_AG_REFCNTBT;
+		break;
+	default:
+		ASSERT(0);
+		return;
+	}
+
+	xfs_agno_mark_sick(cur->bc_mp, cur->bc_ag.agno, mask);
+}