diff mbox

[05/25] xfs: create helpers to scrub a metadata btree

Message ID 150706328091.19351.8950704471769189971.stgit@magnolia (mailing list archive)
State Accepted
Headers show

Commit Message

Darrick J. Wong Oct. 3, 2017, 8:41 p.m. UTC
From: Darrick J. Wong <darrick.wong@oracle.com>

Create helper functions and tracepoints to deal with errors while
scrubbing a metadata btree.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
 fs/xfs/Makefile      |    1 
 fs/xfs/scrub/btree.c |  112 +++++++++++++++++++++++++++++++++++
 fs/xfs/scrub/btree.h |   57 ++++++++++++++++++
 fs/xfs/scrub/trace.c |   15 +++++
 fs/xfs/scrub/trace.h |  162 ++++++++++++++++++++++++++++++++++++++++++++++++++
 5 files changed, 347 insertions(+)
 create mode 100644 fs/xfs/scrub/btree.c
 create mode 100644 fs/xfs/scrub/btree.h



--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Comments

Dave Chinner Oct. 3, 2017, 11:49 p.m. UTC | #1
On Tue, Oct 03, 2017 at 01:41:20PM -0700, Darrick J. Wong wrote:
> +/* btree scrubbing */
> +
> +/*
> + * Check for btree operation errors.  See the section about handling
> + * operational errors in common.c.
> + */
> +bool
> +xfs_scrub_btree_op_ok(
> +	struct xfs_scrub_context	*sc,
> +	struct xfs_btree_cur		*cur,
> +	int				level,
> +	int				*error)
> +{
......
> +
> +/*
> + * Visit all nodes and leaves of a btree.  Check that all pointers and
> + * records are in order, that the keys reflect the records, and use a callback
> + * so that the caller can verify individual records.  The callback is the same
> + * as the one for xfs_btree_query_range, so therefore this function also
> + * returns XFS_BTREE_QUERY_RANGE_ABORT, zero, or a negative error code.
> + */
> +int
> +xfs_scrub_btree(
> +	struct xfs_scrub_context	*sc,
> +	struct xfs_btree_cur		*cur,
> +	xfs_scrub_btree_rec_fn		scrub_fn,
> +	struct xfs_owner_info		*oinfo,
> +	void				*private)
> +{
> +	xfs_scrub_btree_op_ok(sc, cur, 0, false);

Looks like this patch won't compile - it's passing a bool to an int
*. I know it's just a stub and probably gets fixed later, but
better not to leave a bisect landmine...

-Dave
Darrick J. Wong Oct. 4, 2017, 12:13 a.m. UTC | #2
On Wed, Oct 04, 2017 at 10:49:13AM +1100, Dave Chinner wrote:
> On Tue, Oct 03, 2017 at 01:41:20PM -0700, Darrick J. Wong wrote:
> > +/* btree scrubbing */
> > +
> > +/*
> > + * Check for btree operation errors.  See the section about handling
> > + * operational errors in common.c.
> > + */
> > +bool
> > +xfs_scrub_btree_op_ok(
> > +	struct xfs_scrub_context	*sc,
> > +	struct xfs_btree_cur		*cur,
> > +	int				level,
> > +	int				*error)
> > +{
> ......
> > +
> > +/*
> > + * Visit all nodes and leaves of a btree.  Check that all pointers and
> > + * records are in order, that the keys reflect the records, and use a callback
> > + * so that the caller can verify individual records.  The callback is the same
> > + * as the one for xfs_btree_query_range, so therefore this function also
> > + * returns XFS_BTREE_QUERY_RANGE_ABORT, zero, or a negative error code.
> > + */
> > +int
> > +xfs_scrub_btree(
> > +	struct xfs_scrub_context	*sc,
> > +	struct xfs_btree_cur		*cur,
> > +	xfs_scrub_btree_rec_fn		scrub_fn,
> > +	struct xfs_owner_info		*oinfo,
> > +	void				*private)
> > +{
> > +	xfs_scrub_btree_op_ok(sc, cur, 0, false);
> 
> Looks like this patch won't compile - it's passing a bool to an int
> *. I know it's just a stub and probably gets fixed later, but
> better not to leave a bisect landmine...

Frighteningly it /does/ compile because the 'false' apparently gets
converted to NULL and therefore there's no type error.  Fortunately
there are no callers so it'll never blow up... but hey, I'll fix it
anyway.  Good catch!

--D

> 
> -Dave
> -- 
> Dave Chinner
> david@fromorbit.com
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
diff mbox

Patch

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index ca14595..5888b9f 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -146,6 +146,7 @@  ifeq ($(CONFIG_XFS_ONLINE_SCRUB),y)
 
 xfs-y				+= $(addprefix scrub/, \
 				   trace.o \
+				   btree.o \
 				   common.o \
 				   scrub.o \
 				   )
diff --git a/fs/xfs/scrub/btree.c b/fs/xfs/scrub/btree.c
new file mode 100644
index 0000000..9645f6d
--- /dev/null
+++ b/fs/xfs/scrub/btree.c
@@ -0,0 +1,112 @@ 
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#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 "scrub/scrub.h"
+#include "scrub/common.h"
+#include "scrub/btree.h"
+#include "scrub/trace.h"
+
+/* btree scrubbing */
+
+/*
+ * Check for btree operation errors.  See the section about handling
+ * operational errors in common.c.
+ */
+bool
+xfs_scrub_btree_op_ok(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	int				level,
+	int				*error)
+{
+	if (*error == 0)
+		return true;
+
+	switch (*error) {
+	case -EDEADLOCK:
+		/* Used to restart an op with deadlock avoidance. */
+		trace_xfs_scrub_deadlock_retry(sc->ip, sc->sm, *error);
+		break;
+	case -EFSBADCRC:
+	case -EFSCORRUPTED:
+		/* Note the badness but don't abort. */
+		sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+		*error = 0;
+		/* fall through */
+	default:
+		if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+			trace_xfs_scrub_ifork_btree_op_error(sc, cur, level,
+					*error, __return_address);
+		else
+			trace_xfs_scrub_btree_op_error(sc, cur, level,
+					*error, __return_address);
+		break;
+	}
+	return false;
+}
+
+/* Record btree block corruption. */
+void
+xfs_scrub_btree_set_corrupt(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	int				level)
+{
+	sc->sm->sm_flags |= XFS_SCRUB_OFLAG_CORRUPT;
+
+	if (cur->bc_flags & XFS_BTREE_ROOT_IN_INODE)
+		trace_xfs_scrub_ifork_btree_error(sc, cur, level,
+				__return_address);
+	else
+		trace_xfs_scrub_btree_error(sc, cur, level,
+				__return_address);
+}
+
+/*
+ * Visit all nodes and leaves of a btree.  Check that all pointers and
+ * records are in order, that the keys reflect the records, and use a callback
+ * so that the caller can verify individual records.  The callback is the same
+ * as the one for xfs_btree_query_range, so therefore this function also
+ * returns XFS_BTREE_QUERY_RANGE_ABORT, zero, or a negative error code.
+ */
+int
+xfs_scrub_btree(
+	struct xfs_scrub_context	*sc,
+	struct xfs_btree_cur		*cur,
+	xfs_scrub_btree_rec_fn		scrub_fn,
+	struct xfs_owner_info		*oinfo,
+	void				*private)
+{
+	xfs_scrub_btree_op_ok(sc, cur, 0, false);
+	return -EOPNOTSUPP;
+}
diff --git a/fs/xfs/scrub/btree.h b/fs/xfs/scrub/btree.h
new file mode 100644
index 0000000..38ca0e8
--- /dev/null
+++ b/fs/xfs/scrub/btree.h
@@ -0,0 +1,57 @@ 
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#ifndef __XFS_SCRUB_BTREE_H__
+#define __XFS_SCRUB_BTREE_H__
+
+/* btree scrub */
+
+/* Check for btree operation errors. */
+bool xfs_scrub_btree_op_ok(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur *cur, int level, int *error);
+
+/* Check for btree corruption. */
+void xfs_scrub_btree_set_corrupt(struct xfs_scrub_context *sc,
+		struct xfs_btree_cur *cur, int level);
+
+struct xfs_scrub_btree;
+typedef int (*xfs_scrub_btree_rec_fn)(
+	struct xfs_scrub_btree	*bs,
+	union xfs_btree_rec	*rec);
+
+struct xfs_scrub_btree {
+	/* caller-provided scrub state */
+	struct xfs_scrub_context	*sc;
+	struct xfs_btree_cur		*cur;
+	xfs_scrub_btree_rec_fn		scrub_rec;
+	struct xfs_owner_info		*oinfo;
+	void				*private;
+
+	/* internal scrub state */
+	union xfs_btree_rec		lastrec;
+	bool				firstrec;
+	union xfs_btree_key		lastkey[XFS_BTREE_MAXLEVELS];
+	bool				firstkey[XFS_BTREE_MAXLEVELS];
+	struct list_head		to_check;
+};
+int xfs_scrub_btree(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+		    xfs_scrub_btree_rec_fn scrub_fn,
+		    struct xfs_owner_info *oinfo, void *private);
+
+#endif /* __XFS_SCRUB_BTREE_H__ */
diff --git a/fs/xfs/scrub/trace.c b/fs/xfs/scrub/trace.c
index 88b5ccb..a1abf04 100644
--- a/fs/xfs/scrub/trace.c
+++ b/fs/xfs/scrub/trace.c
@@ -30,10 +30,25 @@ 
 #include "xfs_inode.h"
 #include "xfs_btree.h"
 #include "xfs_trans.h"
+#include "xfs_bit.h"
 #include "scrub/xfs_scrub.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 
+/* Figure out which block the btree cursor was pointing to. */
+static inline xfs_fsblock_t
+xfs_scrub_btree_cur_fsbno(
+	struct xfs_btree_cur		*cur,
+	int				level)
+{
+	if (level < cur->bc_nlevels && cur->bc_bufs[level])
+		return XFS_DADDR_TO_FSB(cur->bc_mp, cur->bc_bufs[level]->b_bn);
+	else if (level == cur->bc_nlevels - 1 &&
+		 cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		return XFS_INO_TO_FSB(cur->bc_mp, cur->bc_private.b.ip->i_ino);
+	return NULLFSBLOCK;
+}
+
 /*
  * We include this last to have the helpers above available for the trace
  * event implementations.
diff --git a/fs/xfs/scrub/trace.h b/fs/xfs/scrub/trace.h
index 8d67a85..78f96b0 100644
--- a/fs/xfs/scrub/trace.h
+++ b/fs/xfs/scrub/trace.h
@@ -261,6 +261,168 @@  TRACE_EVENT(xfs_scrub_incomplete,
 		  __entry->ret_ip)
 );
 
+TRACE_EVENT(xfs_scrub_btree_op_error,
+	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+		 int level, int error, void *ret_ip),
+	TP_ARGS(sc, cur, level, error, ret_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, type)
+		__field(xfs_btnum_t, btnum)
+		__field(int, level)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, bno)
+		__field(int, ptr);
+		__field(int, error)
+		__field(void *, ret_ip)
+	),
+	TP_fast_assign(
+		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->type = sc->sm->sm_type;
+		__entry->btnum = cur->bc_btnum;
+		__entry->level = level;
+		__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
+		__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+		__entry->ptr = cur->bc_ptrs[level];
+		__entry->error = error;
+		__entry->ret_ip = ret_ip;
+	),
+	TP_printk("dev %d:%d type %u btnum %d level %d ptr %d agno %u agbno %u error %d ret_ip %pF",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->type,
+		  __entry->btnum,
+		  __entry->level,
+		  __entry->ptr,
+		  __entry->agno,
+		  __entry->bno,
+		  __entry->error,
+		  __entry->ret_ip)
+);
+
+TRACE_EVENT(xfs_scrub_ifork_btree_op_error,
+	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+		 int level, int error, void *ret_ip),
+	TP_ARGS(sc, cur, level, error, ret_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, whichfork)
+		__field(unsigned int, type)
+		__field(xfs_btnum_t, btnum)
+		__field(int, level)
+		__field(int, ptr)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, bno)
+		__field(int, error)
+		__field(void *, ret_ip)
+	),
+	TP_fast_assign(
+		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->ip->i_ino;
+		__entry->whichfork = cur->bc_private.b.whichfork;
+		__entry->type = sc->sm->sm_type;
+		__entry->btnum = cur->bc_btnum;
+		__entry->level = level;
+		__entry->ptr = cur->bc_ptrs[level];
+		__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
+		__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+		__entry->error = error;
+		__entry->ret_ip = ret_ip;
+	),
+	TP_printk("dev %d:%d ino %llu fork %d type %u btnum %d level %d ptr %d agno %u agbno %u error %d ret_ip %pF",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->whichfork,
+		  __entry->type,
+		  __entry->btnum,
+		  __entry->level,
+		  __entry->ptr,
+		  __entry->agno,
+		  __entry->bno,
+		  __entry->error,
+		  __entry->ret_ip)
+);
+
+TRACE_EVENT(xfs_scrub_btree_error,
+	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+		 int level, void *ret_ip),
+	TP_ARGS(sc, cur, level, ret_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(unsigned int, type)
+		__field(xfs_btnum_t, btnum)
+		__field(int, level)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, bno)
+		__field(int, ptr);
+		__field(void *, ret_ip)
+	),
+	TP_fast_assign(
+		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->type = sc->sm->sm_type;
+		__entry->btnum = cur->bc_btnum;
+		__entry->level = level;
+		__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
+		__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+		__entry->ptr = cur->bc_ptrs[level];
+		__entry->ret_ip = ret_ip;
+	),
+	TP_printk("dev %d:%d type %u btnum %d level %d ptr %d agno %u agbno %u ret_ip %pF",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->type,
+		  __entry->btnum,
+		  __entry->level,
+		  __entry->ptr,
+		  __entry->agno,
+		  __entry->bno,
+		  __entry->ret_ip)
+);
+
+TRACE_EVENT(xfs_scrub_ifork_btree_error,
+	TP_PROTO(struct xfs_scrub_context *sc, struct xfs_btree_cur *cur,
+		 int level, void *ret_ip),
+	TP_ARGS(sc, cur, level, ret_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_ino_t, ino)
+		__field(int, whichfork)
+		__field(unsigned int, type)
+		__field(xfs_btnum_t, btnum)
+		__field(int, level)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_agblock_t, bno)
+		__field(int, ptr);
+		__field(void *, ret_ip)
+	),
+	TP_fast_assign(
+		xfs_fsblock_t fsbno = xfs_scrub_btree_cur_fsbno(cur, level);
+		__entry->dev = sc->mp->m_super->s_dev;
+		__entry->ino = sc->ip->i_ino;
+		__entry->whichfork = cur->bc_private.b.whichfork;
+		__entry->type = sc->sm->sm_type;
+		__entry->btnum = cur->bc_btnum;
+		__entry->level = level;
+		__entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsbno);
+		__entry->bno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsbno);
+		__entry->ptr = cur->bc_ptrs[level];
+		__entry->ret_ip = ret_ip;
+	),
+	TP_printk("dev %d:%d ino %llu fork %d type %u btnum %d level %d ptr %d agno %u agbno %u ret_ip %pF",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->ino,
+		  __entry->whichfork,
+		  __entry->type,
+		  __entry->btnum,
+		  __entry->level,
+		  __entry->ptr,
+		  __entry->agno,
+		  __entry->bno,
+		  __entry->ret_ip)
+);
+
 #endif /* _TRACE_XFS_SCRUB_TRACE_H */
 
 #undef TRACE_INCLUDE_PATH