kconfig: fix MODULES-related bug in case of no .config
in [Kernel]
|
Prev: [PATCH 2.6.35-rc6] kconfig: fix MODULES-related bug in case of no .config
Next: ata_port_flush_task, BUG: unable to handle kernel paging request
From: Ulf Magnusson on 27 Jul 2010 16:00 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. > > Signed-off-by: Ulf Magnusson <ulfalizer.lkml(a)gmail.com> > > diff -uNr linux.vanilla/scripts/kconfig/confdata.c linux.new/scripts/kconfig/confdata.c > --- linux.vanilla/scripts/kconfig/confdata.c 2010-07-27 16:47:43.443006287 +0200 > +++ linux.new/scripts/kconfig/confdata.c 2010-07-27 16:50:19.795005537 +0200 > @@ -170,8 +170,10 @@ > if (in) > goto load; > sym_add_change_count(1); > - if (!sym_defconfig_list) > + if (!sym_defconfig_list) { > + sym_calc_value(modules_sym); > return 1; > + } > > for_all_defaults(sym_defconfig_list, prop) { > if (expr_calc_value(prop->visible.expr) == no || Silly error in the patch. The correct patch follows. Signed-off-by: Ulf Magnusson <ulfalizer.lkml(a)gmail.com> diff -uNr linux.vanilla/scripts/kconfig/confdata.c linux.new/scripts/kconfig/confdata.c --- linux.vanilla/scripts/kconfig/confdata.c 2010-07-27 16:47:43.443006287 +0200 +++ linux.new/scripts/kconfig/confdata.c 2010-07-27 21:48:07.471550551 +0200 @@ -170,8 +170,11 @@ if (in) goto load; sym_add_change_count(1); - if (!sym_defconfig_list) + if (!sym_defconfig_list) { + if (modules_sym) + sym_calc_value(modules_sym); return 1; + } for_all_defaults(sym_defconfig_list, prop) { if (expr_calc_value(prop->visible.expr) == no || -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Américo Wang on 28 Jul 2010 02:20 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. > >Signed-off-by: Ulf Magnusson <ulfalizer.lkml(a)gmail.com> > Sounds good for me. Reviewed-by: WANG Cong <xiyou.wangcong(a)gmail.com> >diff -uNr linux.vanilla/scripts/kconfig/confdata.c linux.new/scripts/kconfig/confdata.c >--- linux.vanilla/scripts/kconfig/confdata.c 2010-07-27 16:47:43.443006287 +0200 >+++ linux.new/scripts/kconfig/confdata.c 2010-07-27 21:48:07.471550551 +0200 >@@ -170,8 +170,11 @@ > if (in) > goto load; > sym_add_change_count(1); >- if (!sym_defconfig_list) >+ if (!sym_defconfig_list) { >+ if (modules_sym) >+ sym_calc_value(modules_sym); > return 1; >+ } > > for_all_defaults(sym_defconfig_list, prop) { > if (expr_calc_value(prop->visible.expr) == no || >-- >To unsubscribe from this list: send the line "unsubscribe linux-kernel" in >the body of a message to majordomo(a)vger.kernel.org >More majordomo info at http://vger.kernel.org/majordomo-info.html >Please read the FAQ at http://www.tux.org/lkml/ -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
From: Michal Marek on 29 Jul 2010 11:00
On Wed, Jul 28, 2010 at 02:23:13PM +0800, Am�rico 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(a)gmail.com> > > > > Sounds good for me. > > Reviewed-by: WANG Cong <xiyou.wangcong(a)gmail.com> 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-kernel" in the body of a message to majordomo(a)vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/ |