| Message ID | 20200614010755.9129-1-valentin.schneider@arm.com |
|---|---|
| Headers | show |
| Series | sched, arch_topology: Thermal pressure configuration cleanup | expand |
Sorry for getting back to this only now; On 22/06/20 09:37, Vincent Guittot wrote: > On Sun, 21 Jun 2020 at 00:28, Valentin Schneider <valentin.schneider@arm.com> wrote: >> On 20/06/20 18:49, Ionela Voinescu wrote: >> > On Thursday 18 Jun 2020 at 17:03:24 (+0200), Vincent Guittot wrote: >> >> Having this weak function declared in cpufreq_cooling is weird. This >> >> means that we will have to do so for each one that wants to use it. >> >> >> >> Can't you declare an empty function in a common header file ? >> > >> > Do we expect anyone other than cpufreq_cooling to call >> > arch_set_thermal_pressure()? >> > >> > I'm not against any of the options, either having it here as a week >> > default definition (same as done for arch_set_freq_scale() in cpufreq.c) >> > or in a common header (as done for arch_scale_freq_capacity() in sched.h). >> > >> >> Same thoughts here; I was going for the arch_set_freq_scale() way. >> >> > But for me, Valentin's implementation seems more natural as setters are >> > usually only called from within the framework that does the control >> > (throttling for thermal or frequency setting for cpufreq) and we >> > probably want to think twice if we want to call them from other places. >> > >> >> Well TBH I was tempted to go the other way and keep the definition in >> core.c, given a simple per-cpu value is fairly generic. More precisely, it > > Having all definitions in the same place is my main concern here. > If topology.c defines arch_set_thermal_pressure it should also provide > the empty function when the feature is not available or possible > instead of relying of each user of the interface to define a weak > function just in case. > include/linux/sched/topology.h already defines a stub for arch_scale_thermal_pressure(), I suppose we could have one for arch_set_thermal_pressure() there. That would require having something like #define arch_set_thermal_pressure topology_set_thermal_pressure in the arm & arm64 include/asm/topology.h headers, with topology_set_thermal_pressure() being what arch_set_thermal_pressure() currently is in this patchset. This would set an odd precedent in that so far we only ever had to #define getter functions, the setters being either: - entirely contained within arch_topology. (for the CPU scale) - defined in arch_topology, declared in cpufreq and contained there (for the freq scale). It made the most sense to me to follow the arch_set_freq_scale() pattern and contain the thermal pressure setter within cpufreq_cooling, especially since I didn't see a strong point in breaking the current patterns.
On Sun, 5 Jul 2020 at 16:19, Valentin Schneider <valentin.schneider@arm.com> wrote: > > > Sorry for getting back to this only now; > > On 22/06/20 09:37, Vincent Guittot wrote: > > On Sun, 21 Jun 2020 at 00:28, Valentin Schneider <valentin.schneider@arm.com> wrote: > >> On 20/06/20 18:49, Ionela Voinescu wrote: > >> > On Thursday 18 Jun 2020 at 17:03:24 (+0200), Vincent Guittot wrote: > >> >> Having this weak function declared in cpufreq_cooling is weird. This > >> >> means that we will have to do so for each one that wants to use it. > >> >> > >> >> Can't you declare an empty function in a common header file ? > >> > > >> > Do we expect anyone other than cpufreq_cooling to call > >> > arch_set_thermal_pressure()? > >> > > >> > I'm not against any of the options, either having it here as a week > >> > default definition (same as done for arch_set_freq_scale() in cpufreq.c) > >> > or in a common header (as done for arch_scale_freq_capacity() in sched.h). > >> > > >> > >> Same thoughts here; I was going for the arch_set_freq_scale() way. > >> > >> > But for me, Valentin's implementation seems more natural as setters are > >> > usually only called from within the framework that does the control > >> > (throttling for thermal or frequency setting for cpufreq) and we > >> > probably want to think twice if we want to call them from other places. > >> > > >> > >> Well TBH I was tempted to go the other way and keep the definition in > >> core.c, given a simple per-cpu value is fairly generic. More precisely, it > > > > Having all definitions in the same place is my main concern here. > > If topology.c defines arch_set_thermal_pressure it should also provide > > the empty function when the feature is not available or possible > > instead of relying of each user of the interface to define a weak > > function just in case. > > > > include/linux/sched/topology.h already defines a stub for > arch_scale_thermal_pressure(), I suppose we could have one for > arch_set_thermal_pressure() there. > > That would require having something like > > #define arch_set_thermal_pressure topology_set_thermal_pressure > > in the arm & arm64 include/asm/topology.h headers, with > topology_set_thermal_pressure() being what arch_set_thermal_pressure() > currently is in this patchset. That looks like a better solution IMO. At least everything is gathered in the same place: topology_get/set_thermal_pressure are in arch_topology.c and arch_scale_thermal_pressure/arch_set_thermal_pressure in the respective topology.h > > > This would set an odd precedent in that so far we only ever had to #define > getter functions, the setters being either: > - entirely contained within arch_topology. (for the CPU scale) > - defined in arch_topology, declared in cpufreq and contained there (for > the freq scale). > > It made the most sense to me to follow the arch_set_freq_scale() pattern > and contain the thermal pressure setter within cpufreq_cooling, especially > since I didn't see a strong point in breaking the current patterns.