All of lore.kernel.org
 help / color / mirror / Atom feed
From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
	<linux-nvdimm@lists.01.org>, <linux-mm@kvack.org>
Cc: linux-fsdevel@vger.kernel.org, linux-raid@vger.kernel.org,
	darrick.wong@oracle.com, david@fromorbit.com, hch@lst.de,
	song@kernel.org, rgoldwyn@suse.de, qi.fuli@fujitsu.com,
	y-goto@fujitsu.com
Subject: [RFC PATCH v3 9/9] xfs: Implement ->corrupted_range() for XFS
Date: Tue, 15 Dec 2020 20:14:14 +0800	[thread overview]
Message-ID: <20201215121414.253660-10-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20201215121414.253660-1-ruansy.fnst@cn.fujitsu.com>

This function is used to handle errors which may cause data lost in
filesystem.  Such as memory failure in fsdax mode.

In XFS, it requires "rmapbt" feature in order to query for files or
metadata which associated to the corrupted data.  Then we could call fs
recover functions to try to repair the corrupted data.(did not
implemented in this patchset)

After that, the memory failure also needs to notify the processes who
are using those files.

Only support data device.  Realtime device is not supported for now.

Signed-off-by: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
---
 fs/xfs/xfs_fsops.c | 10 +++++
 fs/xfs/xfs_mount.h |  2 +
 fs/xfs/xfs_super.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)

diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index ef1d5bb88b93..0ec1b44bfe88 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -501,6 +501,16 @@ xfs_do_force_shutdown(
 "Corruption of in-memory data detected.  Shutting down filesystem");
 		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
 			xfs_stack_trace();
+	} else if (flags & SHUTDOWN_CORRUPT_META) {
+		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+"Corruption of on-disk metadata detected.  Shutting down filesystem");
+		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
+			xfs_stack_trace();
+	} else if (flags & SHUTDOWN_CORRUPT_DATA) {
+		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+"Corruption of on-disk file data detected.  Shutting down filesystem");
+		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
+			xfs_stack_trace();
 	} else if (logerror) {
 		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
 			"Log I/O Error Detected. Shutting down filesystem");
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index dfa429b77ee2..e36c07553486 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -274,6 +274,8 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define SHUTDOWN_LOG_IO_ERROR	0x0002	/* write attempt to the log failed */
 #define SHUTDOWN_FORCE_UMOUNT	0x0004	/* shutdown from a forced unmount */
 #define SHUTDOWN_CORRUPT_INCORE	0x0008	/* corrupt in-memory data structures */
+#define SHUTDOWN_CORRUPT_META	0x0010  /* corrupt metadata on device */
+#define SHUTDOWN_CORRUPT_DATA	0x0020  /* corrupt file data on device */
 
 /*
  * Flags for xfs_mountfs
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e3e229e52512..30202de7e89d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -35,6 +35,11 @@
 #include "xfs_refcount_item.h"
 #include "xfs_bmap_item.h"
 #include "xfs_reflink.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_rtalloc.h"
+#include "xfs_bit.h"
 
 #include <linux/magic.h>
 #include <linux/fs_context.h>
@@ -1103,6 +1108,93 @@ xfs_fs_free_cached_objects(
 	return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
 }
 
+static int
+xfs_corrupt_helper(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*data)
+{
+	struct xfs_inode		*ip;
+	int				rc = 0;
+	int				*flags = data;
+
+	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner)) {
+		// TODO check and try to fix metadata
+		rc = -EFSCORRUPTED;
+	} else {
+		/*
+		 * Get files that incore, filter out others that are not in use.
+		 */
+		rc = xfs_iget(cur->bc_mp, cur->bc_tp, rec->rm_owner,
+			      XFS_IGET_INCORE, 0, &ip);
+		if (rc || !ip)
+			return rc;
+		if (!VFS_I(ip)->i_mapping)
+			goto out;
+
+		if (IS_DAX(VFS_I(ip)))
+			rc = mf_dax_mapping_kill_procs(VFS_I(ip)->i_mapping,
+						       rec->rm_offset, *flags);
+
+		// TODO try to fix data
+out:
+		xfs_irele(ip);
+	}
+
+	return rc;
+}
+
+static int
+xfs_fs_corrupted_range(
+	struct super_block	*sb,
+	struct block_device	*bdev,
+	loff_t			offset,
+	size_t			len,
+	void			*data)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	struct xfs_trans	*tp = NULL;
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_rmap_irec	rmap_low, rmap_high;
+	struct xfs_buf		*agf_bp = NULL;
+	xfs_fsblock_t		fsbno = XFS_B_TO_FSB(mp, offset);
+	xfs_filblks_t		bc = XFS_B_TO_FSB(mp, len);
+	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
+	xfs_agblock_t		agbno = XFS_FSB_TO_AGBNO(mp, fsbno);
+	int			rc = 0;
+
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev == bdev) {
+		xfs_warn(mp, "storage lost support not available for realtime device!");
+		return 0;
+	}
+
+	rc = xfs_trans_alloc_empty(mp, &tp);
+	if (rc)
+		return rc;
+
+	rc = xfs_alloc_read_agf(mp, tp, agno, 0, &agf_bp);
+	if (rc)
+		return rc;
+
+	cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, agno);
+
+	/* Construct a range for rmap query */
+	memset(&rmap_low, 0, sizeof(rmap_low));
+	memset(&rmap_high, 0xFF, sizeof(rmap_high));
+	rmap_low.rm_startblock = rmap_high.rm_startblock = agbno;
+	rmap_low.rm_blockcount = rmap_high.rm_blockcount = bc;
+
+	rc = xfs_rmap_query_range(cur, &rmap_low, &rmap_high, xfs_corrupt_helper, data);
+	if (rc == -ECANCELED)
+		rc = 0;
+	if (rc == -EFSCORRUPTED)
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_META);
+
+	xfs_btree_del_cursor(cur, rc);
+	xfs_trans_brelse(tp, agf_bp);
+	return rc;
+}
+
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
@@ -1116,6 +1208,7 @@ static const struct super_operations xfs_super_operations = {
 	.show_options		= xfs_fs_show_options,
 	.nr_cached_objects	= xfs_fs_nr_cached_objects,
 	.free_cached_objects	= xfs_fs_free_cached_objects,
+	.corrupted_range	= xfs_fs_corrupted_range,
 };
 
 static int
-- 
2.29.2


_______________________________________________
Linux-nvdimm mailing list -- linux-nvdimm@lists.01.org
To unsubscribe send an email to linux-nvdimm-leave@lists.01.org

WARNING: multiple messages have this Message-ID (diff)
From: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
To: <linux-kernel@vger.kernel.org>, <linux-xfs@vger.kernel.org>,
	<linux-nvdimm@lists.01.org>, <linux-mm@kvack.org>
Cc: <linux-fsdevel@vger.kernel.org>, <linux-raid@vger.kernel.org>,
	<darrick.wong@oracle.com>, <dan.j.williams@intel.com>,
	<david@fromorbit.com>, <hch@lst.de>, <song@kernel.org>,
	<rgoldwyn@suse.de>, <qi.fuli@fujitsu.com>, <y-goto@fujitsu.com>
Subject: [RFC PATCH v3 9/9] xfs: Implement ->corrupted_range() for XFS
Date: Tue, 15 Dec 2020 20:14:14 +0800	[thread overview]
Message-ID: <20201215121414.253660-10-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20201215121414.253660-1-ruansy.fnst@cn.fujitsu.com>

This function is used to handle errors which may cause data lost in
filesystem.  Such as memory failure in fsdax mode.

In XFS, it requires "rmapbt" feature in order to query for files or
metadata which associated to the corrupted data.  Then we could call fs
recover functions to try to repair the corrupted data.(did not
implemented in this patchset)

After that, the memory failure also needs to notify the processes who
are using those files.

Only support data device.  Realtime device is not supported for now.

Signed-off-by: Shiyang Ruan <ruansy.fnst@cn.fujitsu.com>
---
 fs/xfs/xfs_fsops.c | 10 +++++
 fs/xfs/xfs_mount.h |  2 +
 fs/xfs/xfs_super.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 105 insertions(+)

diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index ef1d5bb88b93..0ec1b44bfe88 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -501,6 +501,16 @@ xfs_do_force_shutdown(
 "Corruption of in-memory data detected.  Shutting down filesystem");
 		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
 			xfs_stack_trace();
+	} else if (flags & SHUTDOWN_CORRUPT_META) {
+		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+"Corruption of on-disk metadata detected.  Shutting down filesystem");
+		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
+			xfs_stack_trace();
+	} else if (flags & SHUTDOWN_CORRUPT_DATA) {
+		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_CORRUPT,
+"Corruption of on-disk file data detected.  Shutting down filesystem");
+		if (XFS_ERRLEVEL_HIGH <= xfs_error_level)
+			xfs_stack_trace();
 	} else if (logerror) {
 		xfs_alert_tag(mp, XFS_PTAG_SHUTDOWN_LOGERROR,
 			"Log I/O Error Detected. Shutting down filesystem");
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index dfa429b77ee2..e36c07553486 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -274,6 +274,8 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 #define SHUTDOWN_LOG_IO_ERROR	0x0002	/* write attempt to the log failed */
 #define SHUTDOWN_FORCE_UMOUNT	0x0004	/* shutdown from a forced unmount */
 #define SHUTDOWN_CORRUPT_INCORE	0x0008	/* corrupt in-memory data structures */
+#define SHUTDOWN_CORRUPT_META	0x0010  /* corrupt metadata on device */
+#define SHUTDOWN_CORRUPT_DATA	0x0020  /* corrupt file data on device */
 
 /*
  * Flags for xfs_mountfs
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index e3e229e52512..30202de7e89d 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -35,6 +35,11 @@
 #include "xfs_refcount_item.h"
 #include "xfs_bmap_item.h"
 #include "xfs_reflink.h"
+#include "xfs_alloc.h"
+#include "xfs_rmap.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_rtalloc.h"
+#include "xfs_bit.h"
 
 #include <linux/magic.h>
 #include <linux/fs_context.h>
@@ -1103,6 +1108,93 @@ xfs_fs_free_cached_objects(
 	return xfs_reclaim_inodes_nr(XFS_M(sb), sc->nr_to_scan);
 }
 
+static int
+xfs_corrupt_helper(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*data)
+{
+	struct xfs_inode		*ip;
+	int				rc = 0;
+	int				*flags = data;
+
+	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner)) {
+		// TODO check and try to fix metadata
+		rc = -EFSCORRUPTED;
+	} else {
+		/*
+		 * Get files that incore, filter out others that are not in use.
+		 */
+		rc = xfs_iget(cur->bc_mp, cur->bc_tp, rec->rm_owner,
+			      XFS_IGET_INCORE, 0, &ip);
+		if (rc || !ip)
+			return rc;
+		if (!VFS_I(ip)->i_mapping)
+			goto out;
+
+		if (IS_DAX(VFS_I(ip)))
+			rc = mf_dax_mapping_kill_procs(VFS_I(ip)->i_mapping,
+						       rec->rm_offset, *flags);
+
+		// TODO try to fix data
+out:
+		xfs_irele(ip);
+	}
+
+	return rc;
+}
+
+static int
+xfs_fs_corrupted_range(
+	struct super_block	*sb,
+	struct block_device	*bdev,
+	loff_t			offset,
+	size_t			len,
+	void			*data)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	struct xfs_trans	*tp = NULL;
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_rmap_irec	rmap_low, rmap_high;
+	struct xfs_buf		*agf_bp = NULL;
+	xfs_fsblock_t		fsbno = XFS_B_TO_FSB(mp, offset);
+	xfs_filblks_t		bc = XFS_B_TO_FSB(mp, len);
+	xfs_agnumber_t		agno = XFS_FSB_TO_AGNO(mp, fsbno);
+	xfs_agblock_t		agbno = XFS_FSB_TO_AGBNO(mp, fsbno);
+	int			rc = 0;
+
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev == bdev) {
+		xfs_warn(mp, "storage lost support not available for realtime device!");
+		return 0;
+	}
+
+	rc = xfs_trans_alloc_empty(mp, &tp);
+	if (rc)
+		return rc;
+
+	rc = xfs_alloc_read_agf(mp, tp, agno, 0, &agf_bp);
+	if (rc)
+		return rc;
+
+	cur = xfs_rmapbt_init_cursor(mp, tp, agf_bp, agno);
+
+	/* Construct a range for rmap query */
+	memset(&rmap_low, 0, sizeof(rmap_low));
+	memset(&rmap_high, 0xFF, sizeof(rmap_high));
+	rmap_low.rm_startblock = rmap_high.rm_startblock = agbno;
+	rmap_low.rm_blockcount = rmap_high.rm_blockcount = bc;
+
+	rc = xfs_rmap_query_range(cur, &rmap_low, &rmap_high, xfs_corrupt_helper, data);
+	if (rc == -ECANCELED)
+		rc = 0;
+	if (rc == -EFSCORRUPTED)
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_META);
+
+	xfs_btree_del_cursor(cur, rc);
+	xfs_trans_brelse(tp, agf_bp);
+	return rc;
+}
+
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
@@ -1116,6 +1208,7 @@ static const struct super_operations xfs_super_operations = {
 	.show_options		= xfs_fs_show_options,
 	.nr_cached_objects	= xfs_fs_nr_cached_objects,
 	.free_cached_objects	= xfs_fs_free_cached_objects,
+	.corrupted_range	= xfs_fs_corrupted_range,
 };
 
 static int
-- 
2.29.2




  parent reply	other threads:[~2020-12-15 12:15 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-15 12:14 [RFC PATCH v3 0/9] fsdax: introduce fs query to support reflink Shiyang Ruan
2020-12-15 12:14 ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 1/9] pagemap: Introduce ->memory_failure() Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 2/9] blk: Introduce ->corrupted_range() for block device Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 3/9] fs: Introduce ->corrupted_range() for superblock Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 4/9] mm, fsdax: Refactor memory-failure handler for dax mapping Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-16 21:26   ` Dave Chinner
2020-12-16 21:26     ` Dave Chinner
2020-12-18  1:48     ` Ruan Shiyang
2020-12-18  1:48       ` Ruan Shiyang
2020-12-15 12:14 ` [RFC PATCH v3 5/9] mm, pmem: Implement ->memory_failure() in pmem driver Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 6/9] pmem: Implement ->corrupted_range() for " Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 7/9] dm: Introduce ->rmap() to find bdev offset Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 12:14 ` [RFC PATCH v3 8/9] md: Implement ->corrupted_range() Shiyang Ruan
2020-12-15 12:14   ` Shiyang Ruan
2020-12-15 20:51   ` Darrick J. Wong
2020-12-15 20:51     ` Darrick J. Wong
2020-12-15 23:28     ` Dave Chinner
2020-12-15 23:28       ` Dave Chinner
2020-12-18  2:11     ` Ruan Shiyang
2020-12-18  2:11       ` Ruan Shiyang
2021-01-04 23:34       ` Darrick J. Wong
2021-01-04 23:34         ` Darrick J. Wong
2021-01-08  9:52         ` Ruan Shiyang
2021-01-08  9:52           ` Ruan Shiyang
2021-01-08 19:05           ` Darrick J. Wong
2021-01-08 19:05             ` Darrick J. Wong
2020-12-16  5:43   ` Jane Chu
2020-12-16  5:43     ` Jane Chu
2020-12-18  1:50     ` Ruan Shiyang
2020-12-18  1:50       ` Ruan Shiyang
2020-12-15 12:14 ` Shiyang Ruan [this message]
2020-12-15 12:14   ` [RFC PATCH v3 9/9] xfs: Implement ->corrupted_range() for XFS Shiyang Ruan
2020-12-15 20:40   ` Darrick J. Wong
2020-12-15 20:40     ` Darrick J. Wong
2020-12-18  2:31     ` Ruan Shiyang
2020-12-18  2:31       ` Ruan Shiyang
2020-12-16 20:55 ` [RFC PATCH v3 0/9] fsdax: introduce fs query to support reflink Jane Chu
2020-12-16 20:55   ` Jane Chu
2020-12-18  2:44   ` Ruan Shiyang
2020-12-18  2:44     ` Ruan Shiyang
2020-12-18  3:49     ` Darrick J. Wong
2020-12-18  3:49       ` Darrick J. Wong
2020-12-18  9:13       ` Ruan Shiyang
2020-12-18  9:13         ` Ruan Shiyang
2021-01-08 18:14         ` Jane Chu
2021-01-08 18:14           ` Jane Chu

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=20201215121414.253660-10-ruansy.fnst@cn.fujitsu.com \
    --to=ruansy.fnst@cn.fujitsu.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@lst.de \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nvdimm@lists.01.org \
    --cc=linux-raid@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=qi.fuli@fujitsu.com \
    --cc=rgoldwyn@suse.de \
    --cc=song@kernel.org \
    --cc=y-goto@fujitsu.com \
    /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.