lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210125225526.1048877-10-ruansy.fnst@cn.fujitsu.com>
Date:   Tue, 26 Jan 2021 06:55:25 +0800
From:   Shiyang Ruan <ruansy.fnst@...fujitsu.com>
To:     <linux-kernel@...r.kernel.org>, <linux-xfs@...r.kernel.org>,
        <linux-nvdimm@...ts.01.org>, <linux-mm@...ck.org>
CC:     <linux-fsdevel@...r.kernel.org>, <linux-raid@...r.kernel.org>,
        <darrick.wong@...cle.com>, <dan.j.williams@...el.com>,
        <david@...morbit.com>, <hch@....de>, <song@...nel.org>,
        <rgoldwyn@...e.de>, <qi.fuli@...itsu.com>, <y-goto@...itsu.com>
Subject: [PATCH v2 09/10] xfs: Implement ->corrupted_range() for XFS

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@...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



Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ