diff options
| author | Andrew Morton <akpm@digeo.com> | 2002-10-04 20:34:57 -0700 |
|---|---|---|
| committer | Russell King <rmk@flint.arm.linux.org.uk> | 2002-10-04 20:34:57 -0700 |
| commit | a7634cff600fd7c70d1a9aafbd1d0e6979af219b (patch) | |
| tree | f9b43e904d281319734b0b0eae11bdf43f4cd0d4 /include/linux | |
| parent | 911ceab5e55798499796dcef6ea32f51eff8ead6 (diff) | |
[PATCH] O_DIRECT invalidation fix
If the alignment checks in generic_direct_IO() fail, we end up not
forcing writeback of dirty pagecache pages, but we still run
invalidate_inode_pages2(). The net result is that dirty pagecache gets
incorrectly removed. I guess this will expose unwritten disk blocks.
So move the sync up into generic_file_direct_IO(), where we perform the
invalidation. So we know that pagecache and disk are in sync before we
do anything else.
Diffstat (limited to 'include/linux')
0 files changed, 0 insertions, 0 deletions
