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@xxxxxxxxx> > > > > Sounds good for me. > > Reviewed-by: WANG Cong <xiyou.wangcong@xxxxxxxxx> Thanks. Added for 2.6.36 to kbuild-2.6.git (this is not a .35 regression AFAICS). Michal -- To unsubscribe from this list: send the line "unsubscribe linux-kbuild" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
