Linux-Raid Archives on lore.kernel.org
 help / color / 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>, <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: [PATCH v2 09/10] xfs: Implement ->corrupted_range() for XFS
Date: Tue, 26 Jan 2021 06:55:25 +0800
Message-ID: <20210125225526.1048877-10-ruansy.fnst@cn.fujitsu.com> (raw)
In-Reply-To: <20210125225526.1048877-1-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 |   5 +++
 fs/xfs/xfs_mount.h |   1 +
 fs/xfs/xfs_super.c | 109 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 115 insertions(+)

diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 959ce91a3755..f03901a5c673 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -498,6 +498,11 @@ 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 (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..8f0df67ffcc1 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -274,6 +274,7 @@ 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 */
 
 /*
  * Flags for xfs_mountfs
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 813be879a5e5..93093fe0ee8a 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>
@@ -1105,6 +1110,109 @@ 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;
+	struct address_space		*mapping;
+	int				rc = 0;
+	int				*flags = data;
+
+	if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
+	    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
+		// 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;
+
+		mapping = VFS_I(ip)->i_mapping;
+		if (IS_DAX(VFS_I(ip)))
+			rc = mf_dax_mapping_kill_procs(mapping, rec->rm_offset,
+						       *flags);
+		else
+			mapping_set_error(mapping, -EIO);
+
+		// 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		bcnt = 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			error = 0;
+
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_bdev == bdev) {
+		xfs_warn(mp, "corrupted_range support not available for realtime device!");
+		return 0;
+	}
+	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_bdev == bdev &&
+	    mp->m_logdev_targp != mp->m_ddev_targp) {
+		xfs_err(mp, "ondisk log corrupt, shutting down fs!");
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_META);
+		return 0;
+	}
+
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+		xfs_warn(mp, "corrupted_range needs rmapbt enabled!");
+		return 0;
+	}
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agf_bp);
+	if (error)
+		goto out_cancel_tp;
+
+	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 = bcnt;
+
+	error = xfs_rmap_query_range(cur, &rmap_low, &rmap_high, xfs_corrupt_helper, data);
+	if (error == -EFSCORRUPTED)
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_META);
+
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, agf_bp);
+out_cancel_tp:
+	xfs_trans_cancel(tp);
+	return error;
+}
+
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
@@ -1118,6 +1226,7 @@ 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
-- 
2.30.0




  parent reply index

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-01-25 22:55 [PATCH v2 00/10] fsdax: introduce fs query to support reflink Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 01/10] pagemap: Introduce ->memory_failure() Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 02/10] blk: Introduce ->corrupted_range() for block device Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 03/10] fs: Introduce ->corrupted_range() for superblock Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 04/10] mm, fsdax: Refactor memory-failure handler for dax mapping Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 05/10] mm, pmem: Implement ->memory_failure() in pmem driver Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 06/10] pmem: Implement ->corrupted_range() for " Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 07/10] dm: Introduce ->rmap() to find bdev offset Shiyang Ruan
2021-01-25 22:55 ` [PATCH v2 08/10] md: Implement ->corrupted_range() Shiyang Ruan
2021-01-26  0:50   ` Guoqing Jiang
2021-01-25 22:55 ` Shiyang Ruan [this message]
2021-01-25 22:55 ` [PATCH v2 10/10] fs/dax: Remove useless functions Shiyang Ruan

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=20210125225526.1048877-10-ruansy.fnst@cn.fujitsu.com \
    --to=ruansy.fnst@cn.fujitsu.com \
    --cc=dan.j.williams@intel.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

Linux-Raid Archives on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-raid/0 linux-raid/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-raid linux-raid/ https://lore.kernel.org/linux-raid \
		linux-raid@vger.kernel.org
	public-inbox-index linux-raid

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-raid


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git