All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Darrick J. Wong" <darrick.wong@oracle.com>
To: darrick.wong@oracle.com
Cc: linux-xfs@vger.kernel.org
Subject: [PATCH 04/10] xfs: report btree block corruption errors to the health system
Date: Thu, 07 Nov 2019 23:05:52 -0800	[thread overview]
Message-ID: <157319675218.834783.7098410445833520635.stgit@magnolia> (raw)
In-Reply-To: <157319672612.834783.1318671695966912922.stgit@magnolia>

From: Darrick J. Wong <darrick.wong@oracle.com>

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>
---
 fs/xfs/libxfs/xfs_alloc.c    |    1 +
 fs/xfs/libxfs/xfs_bmap.c     |    7 +++++++
 fs/xfs/libxfs/xfs_btree.c    |   16 +++++++++++++++-
 fs/xfs/libxfs/xfs_health.h   |    2 ++
 fs/xfs/libxfs/xfs_ialloc.c   |    1 +
 fs/xfs/libxfs/xfs_refcount.c |    5 ++++-
 fs/xfs/libxfs/xfs_rmap.c     |   13 ++++++++++---
 fs/xfs/libxfs/xfs_rmap.h     |    2 +-
 fs/xfs/scrub/rmap.c          |    2 +-
 fs/xfs/xfs_health.c          |   39 +++++++++++++++++++++++++++++++++++++++
 10 files changed, 81 insertions(+), 7 deletions(-)


diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 0d95aab033cd..389f84d118c5 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -261,6 +261,7 @@ xfs_alloc_get_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 b309b7c4d92f..63ee98dd479d 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -369,6 +369,8 @@ 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;
 		}
@@ -455,6 +457,8 @@ 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;
 		}
@@ -619,6 +623,8 @@ 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);
@@ -5993,6 +5999,7 @@ xfs_bmap_insert_extents(
 
 	if (XFS_IS_CORRUPT(mp,
 	    stop_fsb >= got.br_startoff + got.br_blockcount)) {
+		xfs_btree_mark_sick(cur);
 		error = -EFSCORRUPTED;
 		goto del_cursor;
 	}
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 962020574a2d..4d43c1d03782 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -20,6 +20,7 @@
 #include "xfs_trace.h"
 #include "xfs_alloc.h"
 #include "xfs_log.h"
+#include "xfs_health.h"
 
 /*
  * Cursor allocation zone.
@@ -109,6 +110,7 @@ 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;
@@ -172,6 +174,7 @@ 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;
@@ -247,6 +250,7 @@ xfs_btree_check_ptr(
 				level, index);
 	}
 
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -426,6 +430,8 @@ 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;
@@ -1330,6 +1336,8 @@ 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;
 
@@ -1640,6 +1648,7 @@ 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;
 	}
@@ -1733,6 +1742,7 @@ 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;
 	}
@@ -1825,6 +1835,7 @@ xfs_btree_lookup_get_block(
 	*blkp = NULL;
 	xfs_buf_corruption_error(bp);
 	xfs_trans_brelse(cur->bc_tp, bp);
+	xfs_btree_mark_sick(cur);
 	return -EFSCORRUPTED;
 }
 
@@ -1871,8 +1882,10 @@ 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;
@@ -1915,6 +1928,7 @@ 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 25b61180b562..2049419e9555 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 cc552ac6721e..312a625a8330 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -143,6 +143,7 @@ xfs_inobt_get_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 988cedd2107e..49606f3257ce 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -154,6 +154,7 @@ xfs_refcount_get_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;
 }
 
@@ -1672,8 +1673,10 @@ 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 eb163c7927ce..6f0575dfbd26 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -178,14 +178,20 @@ xfs_rmap_delete(
 /* 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;
 }
 
 /*
@@ -206,7 +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)
@@ -242,6 +248,7 @@ xfs_rmap_get_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;
 }
 
@@ -2279,7 +2286,7 @@ 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 8d4cefd761c1..eb92ccb67a98 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..1f09027c55ad 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 +479,41 @@ 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_private.b.ip,
+				   cur->bc_private.b.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_private.a.agno, mask);
+}


  parent reply	other threads:[~2019-11-08  7:07 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-11-08  7:05 [PATCH v3 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2019-11-08  7:05 ` [PATCH 01/10] xfs: separate the marking of sick and checked metadata Darrick J. Wong
2019-11-08  7:05 ` [PATCH 02/10] xfs: report ag header corruption errors to the health tracking system Darrick J. Wong
2019-11-08  7:05 ` [PATCH 03/10] xfs: report block map " Darrick J. Wong
2019-11-08  7:05 ` Darrick J. Wong [this message]
2019-11-08  7:05 ` [PATCH 05/10] xfs: report dir/attr block corruption errors to the health system Darrick J. Wong
2019-11-08  7:06 ` [PATCH 06/10] xfs: report symlink " Darrick J. Wong
2019-11-08  7:06 ` [PATCH 07/10] xfs: report inode " Darrick J. Wong
2019-11-08  7:06 ` [PATCH 08/10] xfs: report quota block " Darrick J. Wong
2019-11-08  7:06 ` [PATCH 09/10] xfs: report realtime metadata " Darrick J. Wong
2019-11-08  7:06 ` [PATCH 10/10] xfs: report XFS_IS_CORRUPT " Darrick J. Wong
  -- strict thread matches above, loose matches on Subject: below --
2020-01-01  1:04 [PATCH 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2020-01-01  1:05 ` [PATCH 04/10] xfs: report btree block corruption errors to the health system Darrick J. Wong
2019-11-07  3:03 [PATCH 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2019-11-07  3:03 ` [PATCH 04/10] xfs: report btree block corruption errors to the health system Darrick J. Wong
2019-11-03 22:24 [PATCH 00/10] xfs: report corruption to the health trackers Darrick J. Wong
2019-11-03 22:25 ` [PATCH 04/10] xfs: report btree block corruption errors to the health system Darrick J. Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=157319675218.834783.7098410445833520635.stgit@magnolia \
    --to=darrick.wong@oracle.com \
    --cc=linux-xfs@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.