diff mbox series

[v5,6/9] xfs: Implement ->corrupted_range() for XFS

Message ID 20210628000218.387833-7-ruansy.fnst@fujitsu.com (mailing list archive)
State New
Headers show
Series fsdax: introduce fs query to support reflink | expand

Commit Message

Shiyang Ruan June 28, 2021, 12:02 a.m. UTC
This function is used to handle errors which may cause data lost in
filesystem.  Such as memory failure in fsdax mode.

If the rmap feature of XFS enabled, we can query it to find files and
metadata which are associated with the corrupt data.  For now all we do
is kill processes with that file mapped into their address spaces, but
future patches could actually do something about corrupt metadata.

After that, the memory failure 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 | 140 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 146 insertions(+)

--
2.32.0

Comments

kernel test robot June 28, 2021, 2:02 a.m. UTC | #1
Hi Shiyang,

Thank you for the patch! Perhaps something to improve:

[auto build test WARNING on linus/master]
[also build test WARNING on v5.13]
[cannot apply to hnaz-linux-mm/master xfs-linux/for-next dm/for-next next-20210625]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Shiyang-Ruan/fsdax-introduce-fs-query-to-support-reflink/20210628-080346
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 62fb9874f5da54fdb243003b386128037319b219
config: x86_64-randconfig-a002-20210628 (attached as .config)
compiler: clang version 13.0.0 (https://github.com/llvm/llvm-project 4c92e31dd0f1bd152eda883af20ff7fbcaa14945)
reproduce (this is a W=1 build):
        wget https://raw.githubusercontent.com/intel/lkp-tests/master/sbin/make.cross -O ~/bin/make.cross
        chmod +x ~/bin/make.cross
        # install x86_64 cross compiling tool for clang build
        # apt-get install binutils-x86-64-linux-gnu
        # https://github.com/0day-ci/linux/commit/6833b9441ae13413e20968838cd8de34b8c69ed4
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Shiyang-Ruan/fsdax-introduce-fs-query-to-support-reflink/20210628-080346
        git checkout 6833b9441ae13413e20968838cd8de34b8c69ed4
        # save the attached .config to linux build tree
        COMPILER_INSTALL_PATH=$HOME/0day COMPILER=clang make.cross ARCH=x86_64 

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All warnings (new ones prefixed by >>):

   fs/xfs/xfs_super.c:1103:10: warning: unused variable 'flags' [-Wunused-variable]
           int                             *flags = data;
                                            ^
>> fs/xfs/xfs_super.c:1101:25: warning: variable 'mapping' set but not used [-Wunused-but-set-variable]
           struct address_space            *mapping;
                                            ^
   2 warnings generated.


vim +/mapping +1101 fs/xfs/xfs_super.c

  1093	
  1094	static int
  1095	xfs_corrupt_helper(
  1096		struct xfs_btree_cur		*cur,
  1097		struct xfs_rmap_irec		*rec,
  1098		void				*data)
  1099	{
  1100		struct xfs_inode		*ip;
> 1101		struct address_space		*mapping;
  1102		int				error = 0;
  1103		int				*flags = data;
  1104	
  1105		if (XFS_RMAP_NON_INODE_OWNER(rec->rm_owner) ||
  1106		    (rec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))) {
  1107			// TODO check and try to fix metadata
  1108			xfs_force_shutdown(cur->bc_mp, SHUTDOWN_CORRUPT_META);
  1109			return -EFSCORRUPTED;
  1110		}
  1111	
  1112		/*
  1113		 * Get files that incore, filter out others that are not in use.
  1114		 */
  1115		error = xfs_iget(cur->bc_mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE,
  1116				0, &ip);
  1117		if (error)
  1118			return error;
  1119	
  1120		mapping = VFS_I(ip)->i_mapping;
  1121	

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
kernel test robot June 28, 2021, 3:05 a.m. UTC | #2
Hi Shiyang,

Thank you for the patch! Yet something to improve:

[auto build test ERROR on linus/master]
[also build test ERROR on v5.13]
[cannot apply to hnaz-linux-mm/master xfs-linux/for-next dm/for-next next-20210625]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch]

url:    https://github.com/0day-ci/linux/commits/Shiyang-Ruan/fsdax-introduce-fs-query-to-support-reflink/20210628-080346
base:   https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git 62fb9874f5da54fdb243003b386128037319b219
config: i386-randconfig-a012-20210628 (attached as .config)
compiler: gcc-9 (Debian 9.3.0-22) 9.3.0
reproduce (this is a W=1 build):
        # https://github.com/0day-ci/linux/commit/6833b9441ae13413e20968838cd8de34b8c69ed4
        git remote add linux-review https://github.com/0day-ci/linux
        git fetch --no-tags linux-review Shiyang-Ruan/fsdax-introduce-fs-query-to-support-reflink/20210628-080346
        git checkout 6833b9441ae13413e20968838cd8de34b8c69ed4
        # save the attached .config to linux build tree
        mkdir build_dir
        make W=1 O=build_dir ARCH=i386 SHELL=/bin/bash

If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>

All errors (new ones prefixed by >>):

   ld: fs/xfs/xfs_super.o: in function `xfs_dax_notify_failure':
>> xfs_super.c:(.text+0xc35): undefined reference to `dax_get_holder'
   ld: fs/xfs/xfs_super.o: in function `xfs_open_devices':
>> xfs_super.c:(.text+0xd57): undefined reference to `dax_set_holder'
>> ld: xfs_super.c:(.text+0xdb8): undefined reference to `dax_set_holder'
   ld: fs/xfs/xfs_super.o: in function `xfs_close_devices':
   xfs_super.c:(.text+0xf0a): undefined reference to `dax_set_holder'
   ld: xfs_super.c:(.text+0xf3d): undefined reference to `dax_set_holder'
   ld: xfs_super.c:(.text+0xf59): undefined reference to `dax_set_holder'

---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
diff mbox series

Patch

diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index be9cf88d2ad7..e89ada33d8fc 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -551,6 +551,11 @@  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 bb67274ee23f..c62ccf3e07d0 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -276,6 +276,7 @@  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 a2dab05332ac..a986ddf3b248 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -36,11 +36,18 @@ 
 #include "xfs_bmap_item.h"
 #include "xfs_reflink.h"
 #include "xfs_pwork.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>
 #include <linux/fs_parser.h>
+#include <linux/mm.h>

+static const struct dax_holder_operations xfs_dax_holder_operations;
 static const struct super_operations xfs_super_operations;

 static struct kset *xfs_kset;		/* top-level xfs sysfs dir */
@@ -358,6 +365,7 @@  xfs_close_devices(

 		xfs_free_buftarg(mp->m_logdev_targp);
 		xfs_blkdev_put(logdev);
+		dax_set_holder(dax_logdev, NULL, NULL);
 		fs_put_dax(dax_logdev);
 	}
 	if (mp->m_rtdev_targp) {
@@ -366,9 +374,11 @@  xfs_close_devices(

 		xfs_free_buftarg(mp->m_rtdev_targp);
 		xfs_blkdev_put(rtdev);
+		dax_set_holder(dax_rtdev, NULL, NULL);
 		fs_put_dax(dax_rtdev);
 	}
 	xfs_free_buftarg(mp->m_ddev_targp);
+	dax_set_holder(dax_ddev, NULL, NULL);
 	fs_put_dax(dax_ddev);
 }

@@ -392,6 +402,7 @@  xfs_open_devices(
 	struct block_device	*logdev = NULL, *rtdev = NULL;
 	int			error;

+	dax_set_holder(dax_ddev, mp, &xfs_dax_holder_operations);
 	/*
 	 * Open real time and log devices - order is important.
 	 */
@@ -400,6 +411,9 @@  xfs_open_devices(
 		if (error)
 			goto out;
 		dax_logdev = fs_dax_get_by_bdev(logdev);
+		if (dax_logdev != dax_ddev)
+			dax_set_holder(dax_logdev, mp,
+				       &xfs_dax_holder_operations);
 	}

 	if (mp->m_rtname) {
@@ -414,6 +428,7 @@  xfs_open_devices(
 			goto out_close_rtdev;
 		}
 		dax_rtdev = fs_dax_get_by_bdev(rtdev);
+		dax_set_holder(dax_rtdev, mp, &xfs_dax_holder_operations);
 	}

 	/*
@@ -1076,6 +1091,131 @@  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				error = 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
+		xfs_force_shutdown(cur->bc_mp, SHUTDOWN_CORRUPT_META);
+		return -EFSCORRUPTED;
+	}
+
+	/*
+	 * Get files that incore, filter out others that are not in use.
+	 */
+	error = xfs_iget(cur->bc_mp, cur->bc_tp, rec->rm_owner, XFS_IGET_INCORE,
+			0, &ip);
+	if (error)
+		return error;
+
+	mapping = VFS_I(ip)->i_mapping;
+
+#ifdef CONFIG_MEMORY_FAILURE
+	error = mf_dax_kill_procs(mapping, rec->rm_offset, *flags);
+#endif
+
+	// TODO try to fix data
+	xfs_irele(ip);
+
+	return error;
+}
+
+static loff_t
+xfs_dax_bdev_offset(
+	struct xfs_mount *mp,
+	struct dax_device *dax_dev,
+	loff_t disk_offset)
+{
+	struct block_device *bdev;
+
+	if (mp->m_ddev_targp->bt_daxdev == dax_dev)
+		bdev = mp->m_ddev_targp->bt_bdev;
+	else if (mp->m_logdev_targp->bt_daxdev == dax_dev)
+		bdev = mp->m_logdev_targp->bt_bdev;
+	else
+		bdev = mp->m_rtdev_targp->bt_bdev;
+
+	return disk_offset - (get_start_sect(bdev) << SECTOR_SHIFT);
+}
+
+static int
+xfs_dax_notify_failure(
+	struct dax_device	*dax_dev,
+	loff_t			offset,
+	size_t			len,
+	void			*data)
+{
+	struct xfs_mount	*mp = dax_get_holder(dax_dev);
+	struct xfs_trans	*tp = NULL;
+	struct xfs_btree_cur	*cur = NULL;
+	struct xfs_buf		*agf_bp = NULL;
+	struct xfs_rmap_irec	rmap_low, rmap_high;
+	loff_t 			bdev_offset = xfs_dax_bdev_offset(mp, dax_dev,
+								  offset);
+	xfs_fsblock_t		fsbno = XFS_B_TO_FSB(mp, bdev_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;
+
+	pr_warn("%s bno: %lld\n", __func__, bdev_offset >> SECTOR_SHIFT);
+
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp->bt_daxdev == dax_dev) {
+		xfs_warn(mp, "corrupted_range support not available for realtime device!");
+		return -EOPNOTSUPP;
+	}
+	if (mp->m_logdev_targp && mp->m_logdev_targp->bt_daxdev == dax_dev &&
+	    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 -EFSCORRUPTED;
+	}
+
+	if (!xfs_sb_version_hasrmapbt(&mp->m_sb)) {
+		xfs_warn(mp, "corrupted_range needs rmapbt enabled!");
+		return -EOPNOTSUPP;
+	}
+
+	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);
+
+	xfs_btree_del_cursor(cur, error);
+	xfs_trans_brelse(tp, agf_bp);
+
+out_cancel_tp:
+	xfs_trans_cancel(tp);
+	return error;
+}
+
+static const struct dax_holder_operations xfs_dax_holder_operations = {
+	.notify_failure = xfs_dax_notify_failure,
+};
+
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,