subject:"\[PATCH v10.1 8\/9\] xfs\: Implement \->notify

Re: [PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS

2022-02-15 Thread Shiyang Ruan





在 2022/2/15 9:46, Darrick J. Wong 写道:

On Sun, Feb 13, 2022 at 09:02:24PM +0800, Shiyang Ruan wrote:

v10.1 update:
  - Handle the error code returns by dax_register_holder()
  - In v10.1, dax_register_holder() will hold a write lock so XFS
  doesn't need to hold a lock
  - Fix the mistake in failure notification over two AGs
  - Fix the year in copyright message

Introduce xfs_notify_failure.c to handle failure related works, such as
implement ->notify_failure(), register/unregister dax holder in xfs, and
so on.

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.

Signed-off-by: Shiyang Ruan 
---
  fs/xfs/Makefile |   1 +
  fs/xfs/xfs_buf.c|  12 ++
  fs/xfs/xfs_fsops.c  |   3 +
  fs/xfs/xfs_mount.h  |   1 +
  fs/xfs/xfs_notify_failure.c | 225 
  fs/xfs/xfs_notify_failure.h |  10 ++
  6 files changed, 252 insertions(+)
  create mode 100644 fs/xfs/xfs_notify_failure.c
  create mode 100644 fs/xfs/xfs_notify_failure.h

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 04611a1068b4..389970b3e13b 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -84,6 +84,7 @@ xfs-y += xfs_aops.o \
   xfs_message.o \
   xfs_mount.o \
   xfs_mru_cache.o \
+  xfs_notify_failure.o \
   xfs_pwork.o \
   xfs_reflink.o \
   xfs_stats.o \
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index b45e0d50a405..941e8825cee6 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -19,6 +19,7 @@
  #include "xfs_errortag.h"
  #include "xfs_error.h"
  #include "xfs_ag.h"
+#include "xfs_notify_failure.h"
  
  static struct kmem_cache *xfs_buf_cache;
  
@@ -1892,6 +1893,8 @@ xfs_free_buftarg(

list_lru_destroy(&btp->bt_lru);
  
  	blkdev_issue_flush(btp->bt_bdev);

+   if (btp->bt_daxdev)
+   dax_unregister_holder(btp->bt_daxdev);
fs_put_dax(btp->bt_daxdev);
  
  	kmem_free(btp);

@@ -1939,6 +1942,7 @@ xfs_alloc_buftarg(
struct block_device *bdev)
  {
xfs_buftarg_t   *btp;
+   int error;
  
  	btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
  
@@ -1946,6 +1950,14 @@ xfs_alloc_buftarg(

btp->bt_dev =  bdev->bd_dev;
btp->bt_bdev = bdev;
btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
+   if (btp->bt_daxdev) {
+   error = dax_register_holder(btp->bt_daxdev, mp,
+   &xfs_dax_holder_operations);
+   if (error) {
+   xfs_err(mp, "DAX device already in use?!");
+   goto error_free;
+   }
+   }
  
  	/*

 * Buffer IO error rate limiting. Limit it to no more than 10 messages
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 33e26690a8c4..d4d36c5bef11 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -542,6 +542,9 @@ xfs_do_force_shutdown(
} else if (flags & SHUTDOWN_CORRUPT_INCORE) {
tag = XFS_PTAG_SHUTDOWN_CORRUPT;
why = "Corruption of in-memory data";
+   } else if (flags & SHUTDOWN_CORRUPT_ONDISK) {
+   tag = XFS_PTAG_SHUTDOWN_CORRUPT;
+   why = "Corruption of on-disk metadata";
} else {
tag = XFS_PTAG_SHUTDOWN_IOERROR;
why = "Metadata I/O Error";
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 00720a02e761..47ff4ac53c4c 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -435,6 +435,7 @@ 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_ONDISK0x0010  /* corrupt metadata on device */
  
  #define XFS_SHUTDOWN_STRINGS \

{ SHUTDOWN_META_IO_ERROR,   "metadata_io" }, \
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
new file mode 100644
index ..aa67662210a1
--- /dev/null
+++ b/fs/xfs/xfs_notify_failure.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Fujitsu.  All Rights Reserved.
+ */
+
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_alloc

Re: [PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS

2022-02-14 Thread Darrick J. Wong

On Sun, Feb 13, 2022 at 09:02:24PM +0800, Shiyang Ruan wrote:
> v10.1 update:
>  - Handle the error code returns by dax_register_holder()
>  - In v10.1, dax_register_holder() will hold a write lock so XFS
>  doesn't need to hold a lock
>  - Fix the mistake in failure notification over two AGs
>  - Fix the year in copyright message
> 
> Introduce xfs_notify_failure.c to handle failure related works, such as
> implement ->notify_failure(), register/unregister dax holder in xfs, and
> so on.
> 
> 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.
> 
> Signed-off-by: Shiyang Ruan 
> ---
>  fs/xfs/Makefile |   1 +
>  fs/xfs/xfs_buf.c|  12 ++
>  fs/xfs/xfs_fsops.c  |   3 +
>  fs/xfs/xfs_mount.h  |   1 +
>  fs/xfs/xfs_notify_failure.c | 225 
>  fs/xfs/xfs_notify_failure.h |  10 ++
>  6 files changed, 252 insertions(+)
>  create mode 100644 fs/xfs/xfs_notify_failure.c
>  create mode 100644 fs/xfs/xfs_notify_failure.h
> 
> diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
> index 04611a1068b4..389970b3e13b 100644
> --- a/fs/xfs/Makefile
> +++ b/fs/xfs/Makefile
> @@ -84,6 +84,7 @@ xfs-y   += xfs_aops.o \
>  xfs_message.o \
>  xfs_mount.o \
>  xfs_mru_cache.o \
> +xfs_notify_failure.o \
>  xfs_pwork.o \
>  xfs_reflink.o \
>  xfs_stats.o \
> diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
> index b45e0d50a405..941e8825cee6 100644
> --- a/fs/xfs/xfs_buf.c
> +++ b/fs/xfs/xfs_buf.c
> @@ -19,6 +19,7 @@
>  #include "xfs_errortag.h"
>  #include "xfs_error.h"
>  #include "xfs_ag.h"
> +#include "xfs_notify_failure.h"
>  
>  static struct kmem_cache *xfs_buf_cache;
>  
> @@ -1892,6 +1893,8 @@ xfs_free_buftarg(
>   list_lru_destroy(&btp->bt_lru);
>  
>   blkdev_issue_flush(btp->bt_bdev);
> + if (btp->bt_daxdev)
> + dax_unregister_holder(btp->bt_daxdev);
>   fs_put_dax(btp->bt_daxdev);
>  
>   kmem_free(btp);
> @@ -1939,6 +1942,7 @@ xfs_alloc_buftarg(
>   struct block_device *bdev)
>  {
>   xfs_buftarg_t   *btp;
> + int error;
>  
>   btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
>  
> @@ -1946,6 +1950,14 @@ xfs_alloc_buftarg(
>   btp->bt_dev =  bdev->bd_dev;
>   btp->bt_bdev = bdev;
>   btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
> + if (btp->bt_daxdev) {
> + error = dax_register_holder(btp->bt_daxdev, mp,
> + &xfs_dax_holder_operations);
> + if (error) {
> + xfs_err(mp, "DAX device already in use?!");
> + goto error_free;
> + }
> + }
>  
>   /*
>* Buffer IO error rate limiting. Limit it to no more than 10 messages
> diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
> index 33e26690a8c4..d4d36c5bef11 100644
> --- a/fs/xfs/xfs_fsops.c
> +++ b/fs/xfs/xfs_fsops.c
> @@ -542,6 +542,9 @@ xfs_do_force_shutdown(
>   } else if (flags & SHUTDOWN_CORRUPT_INCORE) {
>   tag = XFS_PTAG_SHUTDOWN_CORRUPT;
>   why = "Corruption of in-memory data";
> + } else if (flags & SHUTDOWN_CORRUPT_ONDISK) {
> + tag = XFS_PTAG_SHUTDOWN_CORRUPT;
> + why = "Corruption of on-disk metadata";
>   } else {
>   tag = XFS_PTAG_SHUTDOWN_IOERROR;
>   why = "Metadata I/O Error";
> diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
> index 00720a02e761..47ff4ac53c4c 100644
> --- a/fs/xfs/xfs_mount.h
> +++ b/fs/xfs/xfs_mount.h
> @@ -435,6 +435,7 @@ 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_ONDISK  0x0010  /* corrupt metadata on device */
>  
>  #define XFS_SHUTDOWN_STRINGS \
>   { SHUTDOWN_META_IO_ERROR,   "metadata_io" }, \
> diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
> new file mode 100644
> index ..aa67662210a1
> --- /dev/null
> +++ b/fs/xfs/xfs_notify_failure.c
> @@ -0,0 +1,225 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/*
> + * Copyright (c) 2022 Fujitsu.  All Rights Reserved.
> + */
> +
> +#include "xfs.h"
> +#include "xfs

[PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS

2022-02-13 Thread Shiyang Ruan

v10.1 update:
 - Handle the error code returns by dax_register_holder()
 - In v10.1, dax_register_holder() will hold a write lock so XFS
 doesn't need to hold a lock
 - Fix the mistake in failure notification over two AGs
 - Fix the year in copyright message

Introduce xfs_notify_failure.c to handle failure related works, such as
implement ->notify_failure(), register/unregister dax holder in xfs, and
so on.

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.

Signed-off-by: Shiyang Ruan 
---
 fs/xfs/Makefile |   1 +
 fs/xfs/xfs_buf.c|  12 ++
 fs/xfs/xfs_fsops.c  |   3 +
 fs/xfs/xfs_mount.h  |   1 +
 fs/xfs/xfs_notify_failure.c | 225 
 fs/xfs/xfs_notify_failure.h |  10 ++
 6 files changed, 252 insertions(+)
 create mode 100644 fs/xfs/xfs_notify_failure.c
 create mode 100644 fs/xfs/xfs_notify_failure.h

diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 04611a1068b4..389970b3e13b 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -84,6 +84,7 @@ xfs-y += xfs_aops.o \
   xfs_message.o \
   xfs_mount.o \
   xfs_mru_cache.o \
+  xfs_notify_failure.o \
   xfs_pwork.o \
   xfs_reflink.o \
   xfs_stats.o \
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index b45e0d50a405..941e8825cee6 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -19,6 +19,7 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_ag.h"
+#include "xfs_notify_failure.h"
 
 static struct kmem_cache *xfs_buf_cache;
 
@@ -1892,6 +1893,8 @@ xfs_free_buftarg(
list_lru_destroy(&btp->bt_lru);
 
blkdev_issue_flush(btp->bt_bdev);
+   if (btp->bt_daxdev)
+   dax_unregister_holder(btp->bt_daxdev);
fs_put_dax(btp->bt_daxdev);
 
kmem_free(btp);
@@ -1939,6 +1942,7 @@ xfs_alloc_buftarg(
struct block_device *bdev)
 {
xfs_buftarg_t   *btp;
+   int error;
 
btp = kmem_zalloc(sizeof(*btp), KM_NOFS);
 
@@ -1946,6 +1950,14 @@ xfs_alloc_buftarg(
btp->bt_dev =  bdev->bd_dev;
btp->bt_bdev = bdev;
btp->bt_daxdev = fs_dax_get_by_bdev(bdev, &btp->bt_dax_part_off);
+   if (btp->bt_daxdev) {
+   error = dax_register_holder(btp->bt_daxdev, mp,
+   &xfs_dax_holder_operations);
+   if (error) {
+   xfs_err(mp, "DAX device already in use?!");
+   goto error_free;
+   }
+   }
 
/*
 * Buffer IO error rate limiting. Limit it to no more than 10 messages
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 33e26690a8c4..d4d36c5bef11 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -542,6 +542,9 @@ xfs_do_force_shutdown(
} else if (flags & SHUTDOWN_CORRUPT_INCORE) {
tag = XFS_PTAG_SHUTDOWN_CORRUPT;
why = "Corruption of in-memory data";
+   } else if (flags & SHUTDOWN_CORRUPT_ONDISK) {
+   tag = XFS_PTAG_SHUTDOWN_CORRUPT;
+   why = "Corruption of on-disk metadata";
} else {
tag = XFS_PTAG_SHUTDOWN_IOERROR;
why = "Metadata I/O Error";
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 00720a02e761..47ff4ac53c4c 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -435,6 +435,7 @@ 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_ONDISK0x0010  /* corrupt metadata on device */
 
 #define XFS_SHUTDOWN_STRINGS \
{ SHUTDOWN_META_IO_ERROR,   "metadata_io" }, \
diff --git a/fs/xfs/xfs_notify_failure.c b/fs/xfs/xfs_notify_failure.c
new file mode 100644
index ..aa67662210a1
--- /dev/null
+++ b/fs/xfs/xfs_notify_failure.c
@@ -0,0 +1,225 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2022 Fujitsu.  All Rights Reserved.
+ */
+
+#include "xfs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_alloc.h"
+#include "xfs_bit.h"
+#include "xfs_btree.h"
+#include "xfs_inode.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h

Re: [PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS

Re: [PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS

[PATCH v10.1 8/9] xfs: Implement ->notify_failure() for XFS

3 matches

Site Navigation

Mail list logo

Footer information