| Message ID | 1359394444-16610-1-git-send-email-dave.martin@linaro.org |
|---|---|
| State | New |
| Headers | show |
Hi, Does anyone have a comment on this? Cheers ---Dave On Mon, Jan 28, 2013 at 05:34:04PM +0000, Dave Martin wrote: > It is reasonable for loadable modules to be CPU topology aware > (particular examples include cpufreq and cpuidle drivers). > > This patch exports __cpu_logical_map, so that modules can use the > cpu_logical_map() interface declared in <asm/smp_plat.h>. > > Signed-off-by: Dave Martin <dave.martin@linaro.org> > --- > If anyone has a strong view on whether this should be > EXPORT_SYMBOL_GPL(), I don't have a problem with changing > that. I'm not sure of the precise etiquette here. > Certainly this does not feel like a very "public" interface. > > Perhaps we should wrap this in a real function for export > to modules, rather than encouraging them to poke the > __cpu_logical_map[] array (albeit via a predefined macro). > > > arch/arm/kernel/setup.c | 1 + > 1 files changed, 1 insertions(+), 0 deletions(-) > > diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c > index 3f6cbb2..1b9e5bf 100644 > --- a/arch/arm/kernel/setup.c > +++ b/arch/arm/kernel/setup.c > @@ -428,6 +428,7 @@ void cpu_init(void) > } > > int __cpu_logical_map[NR_CPUS]; > +EXPORT_SYMBOL(__cpu_logical_map); > > void __init smp_setup_processor_id(void) > { > -- > 1.7.4.1 >
On Thu, 7 Feb 2013, Dave Martin wrote: > Hi, > > Does anyone have a comment on this? As you say, I'd be tempted to export some accessor with well defined semantic meaning instead. > > Cheers > ---Dave > > On Mon, Jan 28, 2013 at 05:34:04PM +0000, Dave Martin wrote: > > It is reasonable for loadable modules to be CPU topology aware > > (particular examples include cpufreq and cpuidle drivers). > > > > This patch exports __cpu_logical_map, so that modules can use the > > cpu_logical_map() interface declared in <asm/smp_plat.h>. > > > > Signed-off-by: Dave Martin <dave.martin@linaro.org> > > --- > > If anyone has a strong view on whether this should be > > EXPORT_SYMBOL_GPL(), I don't have a problem with changing > > that. I'm not sure of the precise etiquette here. > > Certainly this does not feel like a very "public" interface. > > > > Perhaps we should wrap this in a real function for export > > to modules, rather than encouraging them to poke the > > __cpu_logical_map[] array (albeit via a predefined macro). > > > > > > arch/arm/kernel/setup.c | 1 + > > 1 files changed, 1 insertions(+), 0 deletions(-) > > > > diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c > > index 3f6cbb2..1b9e5bf 100644 > > --- a/arch/arm/kernel/setup.c > > +++ b/arch/arm/kernel/setup.c > > @@ -428,6 +428,7 @@ void cpu_init(void) > > } > > > > int __cpu_logical_map[NR_CPUS]; > > +EXPORT_SYMBOL(__cpu_logical_map); > > > > void __init smp_setup_processor_id(void) > > { > > -- > > 1.7.4.1 > > >
On Thu, Feb 07, 2013 at 03:05:03PM -0500, Nicolas Pitre wrote: > On Thu, 7 Feb 2013, Dave Martin wrote: > > > Hi, > > > > Does anyone have a comment on this? > > As you say, I'd be tempted to export some accessor with well defined > semantic meaning instead. I think I agree... Modules definitely shouldn't easily be able to write cpu_logical_map. I'll rework something and repost. Cheers ---Dave > > > > > > > Cheers > > ---Dave > > > > On Mon, Jan 28, 2013 at 05:34:04PM +0000, Dave Martin wrote: > > > It is reasonable for loadable modules to be CPU topology aware > > > (particular examples include cpufreq and cpuidle drivers). > > > > > > This patch exports __cpu_logical_map, so that modules can use the > > > cpu_logical_map() interface declared in <asm/smp_plat.h>. > > > > > > Signed-off-by: Dave Martin <dave.martin@linaro.org> > > > --- > > > If anyone has a strong view on whether this should be > > > EXPORT_SYMBOL_GPL(), I don't have a problem with changing > > > that. I'm not sure of the precise etiquette here. > > > Certainly this does not feel like a very "public" interface. > > > > > > Perhaps we should wrap this in a real function for export > > > to modules, rather than encouraging them to poke the > > > __cpu_logical_map[] array (albeit via a predefined macro). > > > > > > > > > arch/arm/kernel/setup.c | 1 + > > > 1 files changed, 1 insertions(+), 0 deletions(-) > > > > > > diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c > > > index 3f6cbb2..1b9e5bf 100644 > > > --- a/arch/arm/kernel/setup.c > > > +++ b/arch/arm/kernel/setup.c > > > @@ -428,6 +428,7 @@ void cpu_init(void) > > > } > > > > > > int __cpu_logical_map[NR_CPUS]; > > > +EXPORT_SYMBOL(__cpu_logical_map); > > > > > > void __init smp_setup_processor_id(void) > > > { > > > -- > > > 1.7.4.1 > > > > >
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 3f6cbb2..1b9e5bf 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -428,6 +428,7 @@ void cpu_init(void) } int __cpu_logical_map[NR_CPUS]; +EXPORT_SYMBOL(__cpu_logical_map); void __init smp_setup_processor_id(void) {
It is reasonable for loadable modules to be CPU topology aware (particular examples include cpufreq and cpuidle drivers). This patch exports __cpu_logical_map, so that modules can use the cpu_logical_map() interface declared in <asm/smp_plat.h>. Signed-off-by: Dave Martin <dave.martin@linaro.org> --- If anyone has a strong view on whether this should be EXPORT_SYMBOL_GPL(), I don't have a problem with changing that. I'm not sure of the precise etiquette here. Certainly this does not feel like a very "public" interface. Perhaps we should wrap this in a real function for export to modules, rather than encouraging them to poke the __cpu_logical_map[] array (albeit via a predefined macro). arch/arm/kernel/setup.c | 1 + 1 files changed, 1 insertions(+), 0 deletions(-)