Re: [PATCH 2.6.35-rc6] kconfig: fix MODULES-related bug in case of no .config

[Michal Marek <mmarek@suse.cz>]

On Wed, Jul 28, 2010 at 02:23:13PM +0800, Américo Wang wrote:
> On Tue, Jul 27, 2010 at 09:57:43PM +0200, Ulf Magnusson wrote:
> >On Tue, Jul 27, 2010 at 09:27:27PM +0200, Ulf Magnusson wrote:
> >> Hi,
> >> 
> >> There seems to be a kconfig bug due to MODULES not always being evaluated if no
> >> .config is found. Take the following Kconfig as an example:
> >> 
> >> config MODULES
> >> 	def_bool y
> >> 
> >> config FOO
> >> 	def_tristate m
> >> 
> >> With no .config, the following configuration is generated:
> >> 
> >> CONFIG_MODULES=y
> >> CONFIG_FOO=y
> >> 
> >> With an empty .config, the following:
> >> 
> >> CONFIG_MODULES=y
> >> CONFIG_FOO=m
> >> 
> >> Tristate choice statements can also exhibit the problem, due to having an
> >> implicit rev_dep (select) containing "m".
> >> 
> >> The problem is that MODULES is never evaluted in conf_read_simple() unless
> >> there's a .config. The following patch fixes this.
> 
> <snip>
> 
> >
> >Silly error in the patch. The correct patch follows.

Even the previous patch was correct, sym_calc_value() does nothing if
the argument is NULL.

> >
> >Signed-off-by: Ulf Magnusson <ulfalizer.lkml@gmail.com>
> >
> 
> Sounds good for me.
> 
> Reviewed-by: WANG Cong <xiyou.wangcong@gmail.com>

Thanks. Added for  2.6.36 to kbuild-2.6.git (this is not a .35
regression AFAICS).

Michal