linux.git/fs/ext4, branch v2.6.23

ext34: ensure do_split leaves enough free space in both blocks

2007-09-19T18:24:18+00:00

The do_split() function for htree dir blocks is intended to split a leaf
block to make room for a new entry.  It sorts the entries in the original
block by hash value, then moves the last half of the entries to the new
block - without accounting for how much space this actually moves.  (IOW,
it moves half of the entry *count* not half of the entry *space*).  If by
chance we have both large & small entries, and we move only the smallest
entries, and we have a large new entry to insert, we may not have created
enough space for it.

The patch below stores each record size when calculating the dx_map, and
then walks the hash-sorted dx_map, calculating how many entries must be
moved to more evenly split the existing entries between the old block and
the new block, guaranteeing enough space for the new entry.

The dx_map "offs" member is reduced to u16 so that the overall map size
does not change - it is temporarily stored at the end of the new block, and
if it grows too large it may be overwritten.  By making offs and size both
u16, we won't grow the map size.

Also add a few comments to the functions involved.

This fixes the testcase reported by hooanon05@yahoo.co.jp on the
linux-ext4 list, "ext3 dir_index causes an error"

Thanks to Andreas Dilger for discussing the problem & solution with me.

Signed-off-by: Eric Sandeen 
Signed-off-by: Andreas Dilger 
Tested-by: Junjiro Okajima 
Cc: Theodore Ts'o 
Cc: 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

dir_index: error out instead of BUG on corrupt dx dirs

2007-09-19T18:24:18+00:00

Convert asserts (BUGs) in dx_probe from bad on-disk data to recoverable
errors with helpful warnings.  With help catching other asserts from Duane
Griffin 

Signed-off-by: Eric Sandeen 
Acked-by: Duane Griffin 
Acked-by: Theodore Ts'o 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

quota: fix infinite loop

2007-09-12T00:21:19+00:00

If we fail to start a transaction when releasing dquot, we have to call
dquot_release() anyway to mark dquot structure as inactive.  Otherwise we
end in an infinite loop inside dqput().

Signed-off-by: Jan Kara 
Cc: xb 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

"ext4_ext_put_in_cache" uses __u32 to receive physical block number

2007-07-31T22:39:37+00:00

Yan Zheng wrote:

> I think I found a bug in ext4/extents.c, "ext4_ext_put_in_cache" uses
> "__u32" to receive physical block number.  "ext4_ext_put_in_cache" is
> used in "ext4_ext_get_blocks", it sets ext4 inode's extent cache
> according most recently tree lookup (higher 16 bits of saved physical
> block number are always zero). when serving a mapping request,
> "ext4_ext_get_blocks" first check whether the logical block is in
> inode's extent cache. if the logical block is in the cache and the
> cached region isn't a gap, "ext4_ext_get_blocks" gets physical block
> number by using cached region's physical block number and offset in
> the cached region.  as described above, "ext4_ext_get_blocks" may
> return wrong result when there are physical block numbers bigger than
> 0xffffffff.
>

You are right.  Thanks for reporting this!

Signed-off-by: Mingming Cao 
Cc: Yan Zheng 
Cc: 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

fix inode_table test in ext234_check_descriptors

2007-07-26T18:35:17+00:00

ext[234]_check_descriptors sanity checks block group descriptor geometry at
mount time, testing whether the block bitmap, inode bitmap, and inode table
reside wholly within the blockgroup.  However, the inode table test is off
by one so that if the last block in the inode table resides on the last
block of the block group, the test incorrectly fails.  This is because it
tests the last block as (start + length) rather than (start + length - 1).

This can be seen by trying to mount a filesystem made such as:

 mkfs.ext2 -F -b 1024 -m 0 -g 256 -N 3744 fsfile 1024

which yields:

 EXT2-fs error (device loop0): ext2_check_descriptors: Inode table for group 0 not in group (block 101)!
 EXT2-fs: group descriptors corrupted!

There is a similar bug in e2fsprogs, patch already sent for that.

(I wonder if inside(), outside(), and/or in_range() should someday be
used in this and other tests throughout the ext filesystems...)

Signed-off-by: Eric Sandeen 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

mm: Remove slab destructors from kmem_cache_create().

2007-07-20T01:11:58+00:00

Slab destructors were no longer supported after Christoph's
c59def9f222d44bb7e2f0a559f2906191a0862d7 change. They've been
BUGs for both slab and slub, and slob never supported them
either.

This rips out support for the dtor pointer from kmem_cache_create()
completely and fixes up every single callsite in the kernel (there were
about 224, not including the slab allocator definitions themselves,
or the documentation references).

Signed-off-by: Paul Mundt

fix ext4/JBD2 build warnings

2007-07-19T17:04:47+00:00

Looking at the current linus-git tree jbd_debug() define in
include/linux/jbd2.h

extern u8 journal_enable_debug;

#define jbd_debug(n, f, a...)                                           \
        do {                                                            \
                if ((n) <= journal_enable_debug) {                      \
                        printk (KERN_DEBUG "(%s, %d): %s: ",            \
                                __FILE__, __LINE__, __FUNCTION__);      \
                        printk (f, ## a);                               \
                }                                                       \
        } while (0)
> fs/ext4/inode.c: In function âext4_write_inodeâ:
> fs/ext4/inode.c:2906: warning: comparison is always true due to limited
> range of data type
>
> fs/jbd2/recovery.c: In function âjbd2_journal_recoverâ:
> fs/jbd2/recovery.c:254: warning: comparison is always true due to
> limited range of data type
> fs/jbd2/recovery.c:257: warning: comparison is always true due to
> limited range of data type
>
> fs/jbd2/recovery.c: In function âjbd2_journal_skip_recoveryâ:
> fs/jbd2/recovery.c:301: warning: comparison is always true due to
> limited range of data type
>
Noticed all warnings are occurs when the debug level is 0. Then found
the "jbd2: Move jbd2-debug file to debugfs" patch
http://git.kernel.org/?p=linux/kernel/git/torvalds/linux-2.6.git;a=commit;h=0f49d5d019afa4e94253bfc92f0daca3badb990b

changed the jbd2_journal_enable_debug from int type to u8, makes the
jbd_debug comparision is always true when the debugging level is 0. Thus
the compile warning occurs.

Thought about changing the jbd2_journal_enable_debug data type back to
int, but can't, because the jbd2-debug is moved to debug fs, where
calling debugfs_create_u8() to create the debugfs entry needs the value
to be u8 type.

Even if we changed the data type back to int, the code is still buggy,
kernel should not print jbd2 debug message if the
jbd2_journal_enable_debug is set to 0. But this is not the case.

The fix is change the level of debugging to 1. The same should fixed in
ext3/JBD, but currently ext3 jbd-debug via /proc fs is broken, so we
probably should fix it all together.

Signed-off-by: Mingming Cao 
Cc: Jeff Garzik 
Cc: Theodore Tso 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

readahead: split ondemand readahead interface into two functions

2007-07-19T17:04:44+00:00

Split ondemand readahead interface into two functions.  I think this makes it
a little clearer for non-readahead experts (like Rusty).

Internally they both call ondemand_readahead(), but the page argument is
changed to an obvious boolean flag.

Signed-off-by: Rusty Russell 
Signed-off-by: Fengguang Wu 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

readahead: convert ext3/ext4 invocations

2007-07-19T17:04:44+00:00

Convert ext3/ext4 dir reads to use on-demand readahead.

Readahead for dirs operates _not_ on file level, but on blockdev level.  This
makes a difference when the data blocks are not continuous.  And the read
routine is somehow opaque: there's no handy info about the status of current
page.  So a simplified call scheme is employed: to call into readahead
whenever the current page falls out of readahead windows.

Signed-off-by: Fengguang Wu 
Cc: Steven Pratt 
Cc: Ram Pai 
Cc: Rusty Russell 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

ext4: extent macros cleanup

2007-07-18T13:09:15+00:00

Use the EXT_LAST_INDEX macro; that's what it's there for.

Clean up ext4_ext_ext_grow_indepth() so the correct EXT_FIRST_INDEX or
EXT_FIRST_MACRO is used as necessary.  The two macros are equivalent, so
the C will collapse the if statement out, but it makes the code much
more readable.

Signed-off-by: Dmitry Monakhov 
Acked-by: Alex Tomas 
Signed-off-by: Dave Kleikamp 
Singed-off-by: Mingming Cao 
Signed-off-by: "Theodore Ts'o"