Re: [PATCH RESEND v2 09/10] xfs: Implement ->corrupted_range() for XFS
On 2021/2/2 上午10:41, Darrick J. Wong wrote:
On Fri, Jan 29, 2021 at 02:27:56PM +0800, Shiyang Ruan wrote:
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)
I would suggest:
"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."
Yes, this is better.
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
---
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
#include
@@ -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;
The xfs_force_shutdown() call should go here, since SHUTDOWN_CORRUPT_META
is specific to this case.
OK.
I guess one could also dig through the buffer cache and delwri_submit
those buffers or something.
+ } 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, );
+ 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
What could we do to fix the data? If we're not in S_DAX mode and
there's actually pagecache mapped in, does that imply that we could
mark it dirty and kick off dirty pagecache writeback?
But in this case, the dax page is already broken, it seems that page
cache should not be written back to the origin dax page. I think
another dax
Re: [PATCH RESEND v2 09/10] xfs: Implement ->corrupted_range() for XFS
On Fri, Jan 29, 2021 at 02:27:56PM +0800, Shiyang Ruan wrote:
> 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)
I would suggest:
"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 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
> ---
> 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_ERROR0x0002 /* write attempt to the log
> failed */
> #define SHUTDOWN_FORCE_UMOUNT0x0004 /* shutdown from a forced
> unmount */
> #define SHUTDOWN_CORRUPT_INCORE 0x0008 /* corrupt in-memory data
> structures */
> +#define SHUTDOWN_CORRUPT_META0x0010 /* 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
> #include
> @@ -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;
The xfs_force_shutdown() call should go here, since SHUTDOWN_CORRUPT_META
is specific to this case.
I guess one could also dig through the buffer cache and delwri_submit
those buffers or something.
> + } 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, );
> + 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
What could we do to fix the data? If we're not in S_DAX mode and
there's actually pagecache mapped in, does that imply that we could
mark it dirty and kick off dirty pagecache writeback?
> +out:
> + xfs_irele(ip);
> + }
> +
> + return rc;
> +}
> +
> +static int
>
[PATCH RESEND 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
---
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_INCORE0x0008 /* 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
#include
@@ -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, );
+ 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_irecrmap_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
