Skip to contentSkip to conversation

Mounting BorderWare UFS File Systems

PATCH Thomas Stewart 2 participants 3 messages May 11, 2010 – May 19, 2010

lore
Share & tools
lore
#0 lore raw

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.

fs/ufs/super.c 2010-05-11 21:23:06.000000000 +0100 renamed from fs/ufs/super.c 2010-05-11 20:07:08.000000000 +0100 +2 -0
diff -urN linux-2.6.33.1.orig/fs/ufs/super.c linux-2.6.33.1/fs/ufs/super.c
@@ -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:
fs/ufs/ufs_fs.h 2010-05-11 21:20:35.000000000 +0100 renamed from fs/ufs/ufs_fs.h 2010-03-15 16:09:39.000000000 +0000 +1 -0
diff -urN linux-2.6.33.1.orig/fs/ufs/ufs_fs.h linux-2.6.33.1/fs/ufs/ufs_fs.h
@@ -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

#1 lore raw
Quoted 13 lines · On Tue, 11 May 2010 22:53:04 +0100 Thomas Stewart <[email protected]>…

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.

Quoted 10 lines

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.

Quoted 12 lines

diff -urN linux-2.6.33.1.orig/fs/ufs/super.c linux-2.6.33.1/fs/ufs/super.c

fs/ufs/super.c 2010-05-11 21:23:06.000000000 +0100 renamed from fs/ufs/super.c 2010-05-11 20:07:08.000000000 +0100 +1 -0
@@ -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:

fs/ufs/super.c 2010-05-11 21:23:06.000000000 +0100 line 934

Quoted 7 lines
fs/ufs/super.c 2010-05-11 21:23:06.000000000 +0100 renamed from fs/ufs/super.c 2010-05-11 20:07:08.000000000 +0100 +1 -0
@@ -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.

fs/ufs/ufs_fs.h 2010-05-11 21:20:35.000000000 +0100 line 53

Quoted 10 lines

diff -urN linux-2.6.33.1.orig/fs/ufs/ufs_fs.h linux-2.6.33.1/fs/ufs/ufs_fs.h

fs/ufs/ufs_fs.h 2010-05-11 21:20:35.000000000 +0100 renamed from fs/ufs/ufs_fs.h 2010-03-15 16:09:39.000000000 +0000 +1 -0
@@ -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.

#2 lore raw
Quoted 7 lines · Andrew Morton
Quoted 2 lines · On Tue, 11 May 2010 22:53:04 +0100 Thomas Stewart <[email protected]>…

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.

Quoted 2 lines

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