• J
    udf: fix possible leakage of blocks · 74584ae5
    Jan Kara 提交于
    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: NJan Kara <jack@suse.cz>
    Cc: Eric Sandeen <sandeen@sandeen.net>
    Cc: Cyrill Gorcunov <gorcunov@gmail.com>
    Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
    Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
    74584ae5
udfdecl.h 6.6 KB