summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorHuang Shijie <shijie8@gmail.com>2012-08-18 13:07:41 -0400
committerGreg Kroah-Hartman <gregkh@linuxfoundation.org>2012-10-13 05:38:58 +0900
commite82df24e733c04385e8d8c32d3062292668bf8c0 (patch)
treef22327330a1e8e32a6138347aa105d298fb00cdf /net
parentc62f9945efea31db203fd4fb77e830ddffdcabf6 (diff)
downloadlwn-e82df24e733c04385e8d8c32d3062292668bf8c0.tar.gz
lwn-e82df24e733c04385e8d8c32d3062292668bf8c0.zip
mtd: mtdpart: break it as soon as we parse out the partitions
commit c51803ddba10d80d9f246066802c6e359cf1d44c upstream. We may cause a memory leak when the @types has more then one parser. Take the `default_mtd_part_types` for example. The default_mtd_part_types has two parsers now: `cmdlinepart` and `ofpart`. Assume the following case: The kernel command line sets the partitions like: #gpmi-nand:20m(boot),20m(kernel),1g(rootfs),-(user) But the devicetree file(such as arch/arm/boot/dts/imx28-evk.dts) also sets the same partitions as the kernel command line does. In the current code, the partitions parsed out by the `ofpart` will overwrite the @pparts which has already set by the `cmdlinepart` parser, and the the partitions parsed out by the `cmdlinepart` is missed. A memory leak occurs. So we should break the code as soon as we parse out the partitions, In actually, this patch makes a priority order between the parsers. If one parser has already parsed out the partitions successfully, it's no need to use another parser anymore. Signed-off-by: Huang Shijie <shijie8@gmail.com> Signed-off-by: Artem Bityutskiy <artem.bityutskiy@linux.intel.com> Signed-off-by: David Woodhouse <David.Woodhouse@intel.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'net')
0 files changed, 0 insertions, 0 deletions