Mounting BorderWare UFS File Systems

Mounting BorderWare UFS File Systems

[Thomas Stewart]

Hi,

I recently had to recover some files from an old broken machine that was
running BorderWare Document Gateway. It's basically a drop in web server
for sharing files. From the look of the init process and using strings
on of a few files it seems to be based on FreeBSD 3.3. The process
turned out to be more difficult than I imagined, but to cut a long story
short BorderWare in their wisdom use a nonstandard magic number in their
UFS (ufstype=44bsd) file systems. Thus Linux refuses to mount the file
systems in order to recover the data. After a bit of hunting I was able
to make a quick fix to fs/ufs/super.c in order to detect the new magic
number. I don't think this needs to get into mainline, but hopefully
this will hit the archives to save anyone else the effort. I'm assume
that this number is the same for all installations. It's quite easy to
find out from ufs_fs.h. The superblock sits 8k into the block device and
the magic number its 1372 bytes into the superblock struct.

# dd if=/dev/sda5 skip=$(( 8192 + 1372 )) bs=1 count=4 2> /dev/null | hd
00000000  97 26 24 0f                                       |.&$.|
#

Here is the patch, please cc any questions or comments as I'm off list.

diff -urN linux-2.6.33.1.orig/fs/ufs/super.c linux-2.6.33.1/fs/ufs/super.c
--- linux-2.6.33.1.orig/fs/ufs/super.c  2010-05-11 20:07:08.000000000 +0100
+++ linux-2.6.33.1/fs/ufs/super.c       2010-05-11 21:23:06.000000000 +0100
@@ -918,6 +918,7 @@
        sbi->s_bytesex = BYTESEX_LE;
        switch ((uspi->fs_magic = fs32_to_cpu(sb, usb3->fs_magic))) {
                case UFS_MAGIC:
+               case UFS_MAGIC_BW:
                case UFS2_MAGIC:
                case UFS_MAGIC_LFN:
                case UFS_MAGIC_FEA:
@@ -927,6 +928,7 @@
        sbi->s_bytesex = BYTESEX_BE;
        switch ((uspi->fs_magic = fs32_to_cpu(sb, usb3->fs_magic))) {
                case UFS_MAGIC:
+               case UFS_MAGIC_BW:
                case UFS2_MAGIC:
                case UFS_MAGIC_LFN:
                case UFS_MAGIC_FEA:
diff -urN linux-2.6.33.1.orig/fs/ufs/ufs_fs.h linux-2.6.33.1/fs/ufs/ufs_fs.h
--- linux-2.6.33.1.orig/fs/ufs/ufs_fs.h 2010-03-15 16:09:39.000000000 +0000
+++ linux-2.6.33.1/fs/ufs/ufs_fs.h      2010-05-11 21:20:35.000000000 +0100
@@ -48,6 +48,7 @@
 #define UFS_SECTOR_SIZE 512
 #define UFS_SECTOR_BITS 9
 #define UFS_MAGIC  0x00011954
+#define UFS_MAGIC_BW 0x0f242697
 #define UFS2_MAGIC 0x19540119
 #define UFS_CIGAM  0x54190100 /* byteswapped MAGIC */
 
Regards
--
Tom

Re: Mounting BorderWare UFS File Systems

[Andrew Morton]

On Tue, 11 May 2010 22:53:04 +0100
Thomas Stewart <thomas@stewarts.org.uk> wrote:

> Hi,
> 
> I recently had to recover some files from an old broken machine that was
> running BorderWare Document Gateway. It's basically a drop in web server
> for sharing files. From the look of the init process and using strings
> on of a few files it seems to be based on FreeBSD 3.3. The process
> turned out to be more difficult than I imagined, but to cut a long story
> short BorderWare in their wisdom use a nonstandard magic number in their
> UFS (ufstype=44bsd) file systems. Thus Linux refuses to mount the file
> systems in order to recover the data. After a bit of hunting I was able
> to make a quick fix to fs/ufs/super.c in order to detect the new magic
> number. I don't think this needs to get into mainline, but hopefully
> this will hit the archives to save anyone else the effort.

Oh, I expect we'll merge it - we're crazy like that.  Thanks.

> I'm assume
> that this number is the same for all installations. It's quite easy to
> find out from ufs_fs.h. The superblock sits 8k into the block device and
> the magic number its 1372 bytes into the superblock struct.
> 
> # dd if=/dev/sda5 skip=$(( 8192 + 1372 )) bs=1 count=4 2> /dev/null | hd
> 00000000  97 26 24 0f                                       |.&$.|
> #
> 
> Here is the patch, please cc any questions or comments as I'm off list.

It would be preferred if you could send us your Signed-off-by: for this
change, please.  It's described in Documentation/SubmittingPatches.

> diff -urN linux-2.6.33.1.orig/fs/ufs/super.c linux-2.6.33.1/fs/ufs/super.c
> --- linux-2.6.33.1.orig/fs/ufs/super.c  2010-05-11 20:07:08.000000000 +0100
> +++ linux-2.6.33.1/fs/ufs/super.c       2010-05-11 21:23:06.000000000 +0100
> @@ -918,6 +918,7 @@
>         sbi->s_bytesex = BYTESEX_LE;
>         switch ((uspi->fs_magic = fs32_to_cpu(sb, usb3->fs_magic))) {
>                 case UFS_MAGIC:
> +               case UFS_MAGIC_BW:
>                 case UFS2_MAGIC:
>                 case UFS_MAGIC_LFN:
>                 case UFS_MAGIC_FEA:
> @@ -927,6 +928,7 @@
>         sbi->s_bytesex = BYTESEX_BE;
>         switch ((uspi->fs_magic = fs32_to_cpu(sb, usb3->fs_magic))) {
>                 case UFS_MAGIC:
> +               case UFS_MAGIC_BW:
>                 case UFS2_MAGIC:
>                 case UFS_MAGIC_LFN:
>                 case UFS_MAGIC_FEA:

Your email client replaces tabs with spaces.  I fixed that up.

> diff -urN linux-2.6.33.1.orig/fs/ufs/ufs_fs.h linux-2.6.33.1/fs/ufs/ufs_fs.h
> --- linux-2.6.33.1.orig/fs/ufs/ufs_fs.h 2010-03-15 16:09:39.000000000 +0000
> +++ linux-2.6.33.1/fs/ufs/ufs_fs.h      2010-05-11 21:20:35.000000000 +0100
> @@ -48,6 +48,7 @@
>  #define UFS_SECTOR_SIZE 512
>  #define UFS_SECTOR_BITS 9
>  #define UFS_MAGIC  0x00011954
> +#define UFS_MAGIC_BW 0x0f242697
>  #define UFS2_MAGIC 0x19540119
>  #define UFS_CIGAM  0x54190100 /* byteswapped MAGIC */

Perhaps we should move these to magic.h.  I'm not sure what benefit
that would provide, really.

Re: Mounting BorderWare UFS File Systems

[Thomas Stewart]

* Andrew Morton <akpm@linux-foundation.org> [2010-05-12 21:56:45]:
> On Tue, 11 May 2010 22:53:04 +0100
> Thomas Stewart <thomas@stewarts.org.uk> wrote:
> 
> > number. I don't think this needs to get into mainline, but hopefully
> > this will hit the archives to save anyone else the effort.
> 
> Oh, I expect we'll merge it - we're crazy like that.  Thanks.

Sounds good.

> It would be preferred if you could send us your Signed-off-by: for this
> change, please.  It's described in Documentation/SubmittingPatches.

Feel free to add one, in the furture I'll add it and get the tabs right.

Thanks for your time :-)

Regards
--
Tom