summaryrefslogtreecommitdiffstats
path: root/ipc
diff options
context:
space:
mode:
authorJan Kara <jack@suse.cz>2007-06-16 10:16:14 -0700
committerLinus Torvalds <torvalds@woody.linux-foundation.org>2007-06-16 13:16:16 -0700
commit74584ae509befc2ed711810e7df4b075473869b2 (patch)
tree9cb1b4a06b8583895c96d9b1a959d81df3950a06 /ipc
parent4b356be019d0c28f67af02809df7072c1c8f7d32 (diff)
downloadlinux-74584ae509befc2ed711810e7df4b075473869b2.tar.gz
linux-74584ae509befc2ed711810e7df4b075473869b2.tar.bz2
linux-74584ae509befc2ed711810e7df4b075473869b2.zip
udf: fix possible leakage of blocks
We have to take care that when we call udf_discard_prealloc() from udf_clear_inode() we have to write inode ourselves afterwards (otherwise, some changes might be lost leading to leakage of blocks, use of free blocks or improperly aligned extents). Also udf_discard_prealloc() does two different things - it removes preallocated blocks and truncates the last extent to exactly match i_size. We move the latter functionality to udf_truncate_tail_extent(), call udf_discard_prealloc() when last reference to a file is dropped and call udf_truncate_tail_extent() when inode is being removed from inode cache (udf_clear_inode() call). We cannot call udf_truncate_tail_extent() earlier as subsequent open+write would find the last block of the file mapped and happily write to the end of it, although the last extent says it's shorter. [akpm@linux-foundation.org: Make checkpatch.pl happier] Signed-off-by: Jan Kara <jack@suse.cz> Cc: Eric Sandeen <sandeen@sandeen.net> Cc: Cyrill Gorcunov <gorcunov@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'ipc')
0 files changed, 0 insertions, 0 deletions