linux/fs/ext4
Eric Sandeen e9e3bcecf4 ext4: serialize unaligned asynchronous DIO
ext4 has a data corruption case when doing non-block-aligned
asynchronous direct IO into a sparse file, as demonstrated
by xfstest 240.

The root cause is that while ext4 preallocates space in the
hole, mappings of that space still look "new" and 
dio_zero_block() will zero out the unwritten portions.  When
more than one AIO thread is going, they both find this "new"
block and race to zero out their portion; this is uncoordinated
and causes data corruption.

Dave Chinner fixed this for xfs by simply serializing all
unaligned asynchronous direct IO.  I've done the same here.
The difference is that we only wait on conversions, not all IO.
This is a very big hammer, and I'm not very pleased with
stuffing this into ext4_file_write().  But since ext4 is
DIO_LOCKING, we need to serialize it at this high level.

I tried to move this into ext4_ext_direct_IO, but by then
we have the i_mutex already, and we will wait on the
work queue to do conversions - which must also take the
i_mutex.  So that won't work.

This was originally exposed by qemu-kvm installing to
a raw disk image with a normal sector-63 alignment.  I've
tested a backport of this patch with qemu, and it does
avoid the corruption.  It is also quite a lot slower
(14 min for package installs, vs. 8 min for well-aligned)
but I'll take slow correctness over fast corruption any day.

Mingming suggested that we can track outstanding
conversions, and wait on those so that non-sparse
files won't be affected, and I've implemented that here;
unaligned AIO to nonsparse files won't take a perf hit.

[tytso@mit.edu: Keep the mutex as a hashed array instead
 of bloating the ext4 inode]

[tytso@mit.edu: Fix up namespace issues so that global
 variables are protected with an "ext4_" prefix.]

Signed-off-by: Eric Sandeen <sandeen@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>
2011-02-12 08:17:34 -05:00
..
acl.c ext2,3,4: provide simple rcu-walk ACL implementation 2011-01-07 17:50:30 +11:00
acl.h fs: provide rcu-walk aware permission i_ops 2011-01-07 17:50:29 +11:00
balloc.c ext4: replace i_delalloc_reserved_flag with EXT4_STATE_DELALLOC_RESERVED 2011-01-10 12:12:36 -05:00
bitmap.c
block_validity.c ext4: rename {exit,init}_ext4_*() to ext4_{exit,init}_*() 2010-10-27 21:30:14 -04:00
dir.c ext4: Use ext4_error_file() to print the pathname to the corrupted inode 2011-01-10 12:10:55 -05:00
ext4.h ext4: serialize unaligned asynchronous DIO 2011-02-12 08:17:34 -05:00
ext4_extents.h ext4: drop ec_type from the ext4_ext_cache structure 2011-01-10 12:13:26 -05:00
ext4_jbd2.c ext4: Pass line numbers to ext4_error() and friends 2010-07-27 11:56:40 -04:00
ext4_jbd2.h ext4: dynamically allocate the jbd2_inode in ext4_inode_info as necessary 2011-01-10 12:29:43 -05:00
extents.c ext4: serialize unaligned asynchronous DIO 2011-02-12 08:17:34 -05:00
file.c ext4: serialize unaligned asynchronous DIO 2011-02-12 08:17:34 -05:00
fsync.c ext4: flush the i_completed_io_list during ext4_truncate 2011-01-10 12:47:05 -05:00
hash.c
ialloc.c ext4: drop i_state_flags on architectures with 64-bit longs 2011-01-10 12:18:25 -05:00
inode.c Merge branch 'for-next' of git://git.kernel.org/pub/scm/linux/kernel/git/jikos/trivial 2011-01-13 10:05:56 -08:00
ioctl.c ext4: Add EXT4_IOC_TRIM ioctl to handle batched discard 2010-11-19 21:47:07 -05:00
Kconfig ext4: Don't ask about supporting ext2/3 in ext4 if ext4 is not configured 2009-12-21 10:54:09 -05:00
Makefile ext4: use bio layer instead of buffer layer in mpage_da_submit_io 2010-10-27 21:30:10 -04:00
mballoc.c ext4: make grpinfo slab cache names static 2011-02-12 08:12:18 -05:00
mballoc.h ext4: consolidate in_range() definitions 2010-03-03 23:55:01 -05:00
migrate.c ext4: ext4_ext_migrate should use NULL not 0 2011-01-10 12:11:00 -05:00
move_extent.c ext4: rename {ext,idx}_pblock and inline small extent functions 2010-10-27 21:30:14 -04:00
namei.c ext4: add error checking to calls to ext4_handle_dirty_metadata() 2011-01-10 12:46:59 -05:00
page-io.c ext4: serialize unaligned asynchronous DIO 2011-02-12 08:17:34 -05:00
resize.c Merge branch 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4 2011-01-11 14:37:31 -08:00
super.c ext4: serialize unaligned asynchronous DIO 2011-02-12 08:17:34 -05:00
symlink.c ext4: symlink must be handled via filesystem specific operation 2010-05-16 02:00:00 -04:00
xattr.c ext2,ext3,ext4: clarify comment for extN_xattr_set_handle 2011-01-10 12:10:30 -05:00
xattr.h ext4: fix compile with CONFIG_EXT4_FS_XATTR disabled 2010-10-28 09:29:17 -07:00
xattr_security.c ext4: constify xattr_handler 2010-05-21 18:31:19 -04:00
xattr_trusted.c ext4: constify xattr_handler 2010-05-21 18:31:19 -04:00
xattr_user.c ext4: constify xattr_handler 2010-05-21 18:31:19 -04:00