| commit | 98397ff3cddcfdedd2ba1701bd30a73c1d733769 | [log] [tgz] |
|---|---|---|
| author | Jaegeuk Kim <jaegeuk@kernel.org> | Fri Jun 13 13:07:31 2014 +0900 |
| committer | Jaegeuk Kim <jaegeuk@kernel.org> | Mon Jun 23 10:05:08 2014 +0900 |
| tree | 2f3180fcfe2057df1c849482cebd7d1b6fe1c179 | |
| parent | ead432756ab2c76b1f1de742a1c8a06992cb98eb [diff] |
f2fs: fix not to allocate unnecessary blocks during fallocate
This patch fixes the fallocate bug like below. (See xfstests/255)
In fallocate(fd, 0, 20480),
expand_inode_data processes
for (index = pg_start; index <= pg_end; index++) {
f2fs_reserve_block();
...
}
So, even though fallocate requests 20480, 5 blocks, f2fs allocates 6 blocks
including pg_end.
So, this patch adds one condition to avoid block allocation.
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>