| Message ID | a34f549bc75eecd4804aebb7b7794b45769eccf0.1614580695.git.viresh.kumar@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | cpufreq: cppc: Add support for frequency invariance | expand |
On Mon, Mar 01, 2021 at 12:21:17PM +0530, Viresh Kumar wrote: > This patch attempts to make it generic enough so other parts of the > kernel can also provide their own implementation of scale_freq_tick() > callback, which is called by the scheduler periodically to update the > per-cpu freq_scale variable. > > The implementations now need to provide 'struct scale_freq_data' for the > CPUs for which they have hardware counters available, and a callback > gets registered for each possible CPU in a per-cpu variable. > > The arch specific (or ARM AMU) counters are updated to adapt to this and > they take the highest priority if they are available, i.e. they will be > used instead of CPPC based counters for example. > > The special code to rebuild the sched domains, in case invariance status > change for the system, is moved out of arm64 specific code and is added > to arch_topology.c. > > Note that this also defines SCALE_FREQ_SOURCE_CPUFREQ but doesn't use it > and it is added to show that cpufreq is also acts as source of > information for FIE and will be used by default if no other counters are > supported for a platform. > > Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com> > Tested-by: Ionela Voinescu <ionela.voinescu@arm.com> > Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> > --- > arch/arm64/include/asm/topology.h | 10 +-- > arch/arm64/kernel/topology.c | 105 +++++++++++------------------- > drivers/base/arch_topology.c | 85 ++++++++++++++++++++++-- > include/linux/arch_topology.h | 14 +++- > 4 files changed, 134 insertions(+), 80 deletions(-) For the arm64 bits: Acked-by: Will Deacon <will@kernel.org> However... > diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > index de8587cc119e..8f62dbf93f67 100644 > --- a/drivers/base/arch_topology.c > +++ b/drivers/base/arch_topology.c > @@ -21,17 +21,94 @@ > #include <linux/sched.h> > #include <linux/smp.h> > > +static DEFINE_PER_CPU(struct scale_freq_data *, sft_data); > +static struct cpumask scale_freq_counters_mask; > +static bool scale_freq_invariant; > + > +static bool supports_scale_freq_counters(const struct cpumask *cpus) > +{ > + return cpumask_subset(cpus, &scale_freq_counters_mask); > +} > + > bool topology_scale_freq_invariant(void) > { > return cpufreq_supports_freq_invariance() || > - arch_freq_counters_available(cpu_online_mask); > + supports_scale_freq_counters(cpu_online_mask); > } > > -__weak bool arch_freq_counters_available(const struct cpumask *cpus) > +static void update_scale_freq_invariant(bool status) > { > - return false; > + if (scale_freq_invariant == status) > + return; > + > + /* > + * Task scheduler behavior depends on frequency invariance support, > + * either cpufreq or counter driven. If the support status changes as > + * a result of counter initialisation and use, retrigger the build of > + * scheduling domains to ensure the information is propagated properly. > + */ > + if (topology_scale_freq_invariant() == status) { > + scale_freq_invariant = status; > + rebuild_sched_domains_energy(); > + } > } > + > +void topology_set_scale_freq_source(struct scale_freq_data *data, > + const struct cpumask *cpus) > +{ > + struct scale_freq_data *sfd; > + int cpu; > + > + /* > + * Avoid calling rebuild_sched_domains() unnecessarily if FIE is > + * supported by cpufreq. > + */ > + if (cpumask_empty(&scale_freq_counters_mask)) > + scale_freq_invariant = topology_scale_freq_invariant(); > + > + for_each_cpu(cpu, cpus) { > + sfd = per_cpu(sft_data, cpu); > + > + /* Use ARCH provided counters whenever possible */ > + if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) { > + per_cpu(sft_data, cpu) = data; > + cpumask_set_cpu(cpu, &scale_freq_counters_mask); > + } > + } > + > + update_scale_freq_invariant(true); > +} > +EXPORT_SYMBOL_GPL(topology_set_scale_freq_source); I don't get why you need to export this in this patch. The arm64 topology code is never built as a module. > + > +void topology_clear_scale_freq_source(enum scale_freq_source source, > + const struct cpumask *cpus) > +{ > + struct scale_freq_data *sfd; > + int cpu; > + > + for_each_cpu(cpu, cpus) { > + sfd = per_cpu(sft_data, cpu); > + > + if (sfd && sfd->source == source) { > + per_cpu(sft_data, cpu) = NULL; > + cpumask_clear_cpu(cpu, &scale_freq_counters_mask); > + } > + } > + > + update_scale_freq_invariant(false); > +} > +EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source); Same here. > + > +void topology_scale_freq_tick(void) > +{ > + struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data); > + > + if (sfd) > + sfd->set_freq_scale(); > +} > + > DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE; > +EXPORT_SYMBOL_GPL(freq_scale); And here. This one probably wants a less generic name as well if it's going to be exported. Will
On 08-03-21, 14:52, Will Deacon wrote: > On Mon, Mar 01, 2021 at 12:21:17PM +0530, Viresh Kumar wrote: > > +EXPORT_SYMBOL_GPL(topology_set_scale_freq_source); > > I don't get why you need to export this in this patch. The arm64 topology > code is never built as a module. > > > +EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source); > > Same here. > > > +EXPORT_SYMBOL_GPL(freq_scale); > > And here. After this patch, any part of the kernel can use these helpers/variables to run their own implementation of tick-freq-scale and so this patch looked to be the right place for that to me. And the second patch in the series updates the CPPC cpufreq driver (tristate) to use these exported symbols, so we have the first user who needs the exported symbols as well. > This one probably wants a less generic name as well if it's going > to be exported. x86 names it arch_freq_scale, perhaps we should stick to that instead. -- viresh
On Tue, Mar 09, 2021 at 09:46:43AM +0530, Viresh Kumar wrote: > On 08-03-21, 14:52, Will Deacon wrote: > > On Mon, Mar 01, 2021 at 12:21:17PM +0530, Viresh Kumar wrote: > > > +EXPORT_SYMBOL_GPL(topology_set_scale_freq_source); > > > > I don't get why you need to export this in this patch. The arm64 topology > > code is never built as a module. > > > > > +EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source); > > > > Same here. > > > > > +EXPORT_SYMBOL_GPL(freq_scale); > > > > And here. > > After this patch, any part of the kernel can use these > helpers/variables to run their own implementation of tick-freq-scale > and so this patch looked to be the right place for that to me. > > And the second patch in the series updates the CPPC cpufreq driver > (tristate) to use these exported symbols, so we have the first user > who needs the exported symbols as well. Ok, then how about putting the exports in their own patch that immediately precedes the patch which uses them? I think that would make it much clearer. > > This one probably wants a less generic name as well if it's going > > to be exported. > > x86 names it arch_freq_scale, perhaps we should stick to that instead. Sounds like a improvement, thanks. Will
On Monday 01 Mar 2021 at 12:21:17 (+0530), Viresh Kumar wrote: > This patch attempts to make it generic enough so other parts of the > kernel can also provide their own implementation of scale_freq_tick() > callback, which is called by the scheduler periodically to update the > per-cpu freq_scale variable. > > The implementations now need to provide 'struct scale_freq_data' for the > CPUs for which they have hardware counters available, and a callback > gets registered for each possible CPU in a per-cpu variable. > > The arch specific (or ARM AMU) counters are updated to adapt to this and > they take the highest priority if they are available, i.e. they will be > used instead of CPPC based counters for example. > > The special code to rebuild the sched domains, in case invariance status > change for the system, is moved out of arm64 specific code and is added > to arch_topology.c. > > Note that this also defines SCALE_FREQ_SOURCE_CPUFREQ but doesn't use it > and it is added to show that cpufreq is also acts as source of > information for FIE and will be used by default if no other counters are > supported for a platform. > > Reviewed-by: Ionela Voinescu <ionela.voinescu@arm.com> > Tested-by: Ionela Voinescu <ionela.voinescu@arm.com> > Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> > --- > arch/arm64/include/asm/topology.h | 10 +-- > arch/arm64/kernel/topology.c | 105 +++++++++++------------------- > drivers/base/arch_topology.c | 85 ++++++++++++++++++++++-- > include/linux/arch_topology.h | 14 +++- > 4 files changed, 134 insertions(+), 80 deletions(-) > > diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h > index 3b8dca4eb08d..ec2db3419c41 100644 > --- a/arch/arm64/include/asm/topology.h > +++ b/arch/arm64/include/asm/topology.h > @@ -17,17 +17,9 @@ int pcibus_to_node(struct pci_bus *bus); > #include <linux/arch_topology.h> > > void update_freq_counters_refs(void); > -void topology_scale_freq_tick(void); > - > -#ifdef CONFIG_ARM64_AMU_EXTN > -/* > - * Replace task scheduler's default counter-based > - * frequency-invariance scale factor setting. > - */ > -#define arch_scale_freq_tick topology_scale_freq_tick > -#endif /* CONFIG_ARM64_AMU_EXTN */ > > /* Replace task scheduler's default frequency-invariant accounting */ > +#define arch_scale_freq_tick topology_scale_freq_tick > #define arch_set_freq_scale topology_set_freq_scale > #define arch_scale_freq_capacity topology_get_freq_scale > #define arch_scale_freq_invariant topology_scale_freq_invariant > diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c > index e08a4126453a..47fca7376c93 100644 > --- a/arch/arm64/kernel/topology.c > +++ b/arch/arm64/kernel/topology.c > @@ -199,12 +199,47 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) > return 0; > } > > -static DEFINE_STATIC_KEY_FALSE(amu_fie_key); > -#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key) > +static void amu_scale_freq_tick(void) > +{ > + u64 prev_core_cnt, prev_const_cnt; > + u64 core_cnt, const_cnt, scale; > + > + prev_const_cnt = this_cpu_read(arch_const_cycles_prev); > + prev_core_cnt = this_cpu_read(arch_core_cycles_prev); > + > + update_freq_counters_refs(); > + > + const_cnt = this_cpu_read(arch_const_cycles_prev); > + core_cnt = this_cpu_read(arch_core_cycles_prev); > + > + if (unlikely(core_cnt <= prev_core_cnt || > + const_cnt <= prev_const_cnt)) > + return; > + > + /* > + * /\core arch_max_freq_scale > + * scale = ------- * -------------------- > + * /\const SCHED_CAPACITY_SCALE > + * > + * See validate_cpu_freq_invariance_counters() for details on > + * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. > + */ > + scale = core_cnt - prev_core_cnt; > + scale *= this_cpu_read(arch_max_freq_scale); > + scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, > + const_cnt - prev_const_cnt); > + > + scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); > + this_cpu_write(freq_scale, (unsigned long)scale); > +} > + > +static struct scale_freq_data amu_sfd = { > + .source = SCALE_FREQ_SOURCE_ARCH, > + .set_freq_scale = amu_scale_freq_tick, > +}; > > static void amu_fie_setup(const struct cpumask *cpus) > { > - bool invariant; > int cpu; > > /* We are already set since the last insmod of cpufreq driver */ > @@ -221,25 +256,10 @@ static void amu_fie_setup(const struct cpumask *cpus) > > cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus); > > - invariant = topology_scale_freq_invariant(); > - > - /* We aren't fully invariant yet */ > - if (!invariant && !cpumask_equal(amu_fie_cpus, cpu_present_mask)) > - return; > - > - static_branch_enable(&amu_fie_key); > + topology_set_scale_freq_source(&amu_sfd, amu_fie_cpus); > > pr_debug("CPUs[%*pbl]: counters will be used for FIE.", > cpumask_pr_args(cpus)); > - > - /* > - * Task scheduler behavior depends on frequency invariance support, > - * either cpufreq or counter driven. If the support status changes as > - * a result of counter initialisation and use, retrigger the build of > - * scheduling domains to ensure the information is propagated properly. > - */ > - if (!invariant) > - rebuild_sched_domains_energy(); > } > > static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val, > @@ -283,53 +303,6 @@ static int __init init_amu_fie(void) > } > core_initcall(init_amu_fie); > > -bool arch_freq_counters_available(const struct cpumask *cpus) > -{ > - return amu_freq_invariant() && > - cpumask_subset(cpus, amu_fie_cpus); > -} > - > -void topology_scale_freq_tick(void) > -{ > - u64 prev_core_cnt, prev_const_cnt; > - u64 core_cnt, const_cnt, scale; > - int cpu = smp_processor_id(); > - > - if (!amu_freq_invariant()) > - return; > - > - if (!cpumask_test_cpu(cpu, amu_fie_cpus)) > - return; > - > - prev_const_cnt = this_cpu_read(arch_const_cycles_prev); > - prev_core_cnt = this_cpu_read(arch_core_cycles_prev); > - > - update_freq_counters_refs(); > - > - const_cnt = this_cpu_read(arch_const_cycles_prev); > - core_cnt = this_cpu_read(arch_core_cycles_prev); > - > - if (unlikely(core_cnt <= prev_core_cnt || > - const_cnt <= prev_const_cnt)) > - return; > - > - /* > - * /\core arch_max_freq_scale > - * scale = ------- * -------------------- > - * /\const SCHED_CAPACITY_SCALE > - * > - * See validate_cpu_freq_invariance_counters() for details on > - * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. > - */ > - scale = core_cnt - prev_core_cnt; > - scale *= this_cpu_read(arch_max_freq_scale); > - scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, > - const_cnt - prev_const_cnt); > - > - scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); > - this_cpu_write(freq_scale, (unsigned long)scale); > -} > - > #ifdef CONFIG_ACPI_CPPC_LIB > #include <acpi/cppc_acpi.h> > > diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c > index de8587cc119e..8f62dbf93f67 100644 > --- a/drivers/base/arch_topology.c > +++ b/drivers/base/arch_topology.c > @@ -21,17 +21,94 @@ > #include <linux/sched.h> > #include <linux/smp.h> > > +static DEFINE_PER_CPU(struct scale_freq_data *, sft_data); > +static struct cpumask scale_freq_counters_mask; > +static bool scale_freq_invariant; > + > +static bool supports_scale_freq_counters(const struct cpumask *cpus) > +{ > + return cpumask_subset(cpus, &scale_freq_counters_mask); > +} > + > bool topology_scale_freq_invariant(void) > { > return cpufreq_supports_freq_invariance() || > - arch_freq_counters_available(cpu_online_mask); > + supports_scale_freq_counters(cpu_online_mask); > } > > -__weak bool arch_freq_counters_available(const struct cpumask *cpus) > +static void update_scale_freq_invariant(bool status) > { > - return false; > + if (scale_freq_invariant == status) > + return; > + > + /* > + * Task scheduler behavior depends on frequency invariance support, > + * either cpufreq or counter driven. If the support status changes as > + * a result of counter initialisation and use, retrigger the build of > + * scheduling domains to ensure the information is propagated properly. > + */ > + if (topology_scale_freq_invariant() == status) { > + scale_freq_invariant = status; > + rebuild_sched_domains_energy(); > + } > } > + > +void topology_set_scale_freq_source(struct scale_freq_data *data, > + const struct cpumask *cpus) > +{ > + struct scale_freq_data *sfd; > + int cpu; > + > + /* > + * Avoid calling rebuild_sched_domains() unnecessarily if FIE is > + * supported by cpufreq. > + */ > + if (cpumask_empty(&scale_freq_counters_mask)) > + scale_freq_invariant = topology_scale_freq_invariant(); > + > + for_each_cpu(cpu, cpus) { > + sfd = per_cpu(sft_data, cpu); > + > + /* Use ARCH provided counters whenever possible */ > + if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) { > + per_cpu(sft_data, cpu) = data; > + cpumask_set_cpu(cpu, &scale_freq_counters_mask); > + } > + } > + > + update_scale_freq_invariant(true); > +} > +EXPORT_SYMBOL_GPL(topology_set_scale_freq_source); > + > +void topology_clear_scale_freq_source(enum scale_freq_source source, > + const struct cpumask *cpus) > +{ > + struct scale_freq_data *sfd; > + int cpu; > + > + for_each_cpu(cpu, cpus) { > + sfd = per_cpu(sft_data, cpu); > + > + if (sfd && sfd->source == source) { > + per_cpu(sft_data, cpu) = NULL; > + cpumask_clear_cpu(cpu, &scale_freq_counters_mask); > + } > + } > + > + update_scale_freq_invariant(false); > +} > +EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source); > + > +void topology_scale_freq_tick(void) > +{ > + struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data); > + > + if (sfd) > + sfd->set_freq_scale(); > +} > + > DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE; > +EXPORT_SYMBOL_GPL(freq_scale); > > void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, > unsigned long max_freq) > @@ -47,7 +124,7 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, > * want to update the scale factor with information from CPUFREQ. > * Instead the scale factor will be updated from arch_scale_freq_tick. > */ > - if (arch_freq_counters_available(cpus)) > + if (supports_scale_freq_counters(cpus)) > return; > > scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq; > diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h > index 0f6cd6b73a61..3bcfba5c21a7 100644 > --- a/include/linux/arch_topology.h > +++ b/include/linux/arch_topology.h > @@ -34,7 +34,19 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, > unsigned long max_freq); > bool topology_scale_freq_invariant(void); > > -bool arch_freq_counters_available(const struct cpumask *cpus); > +enum scale_freq_source { > + SCALE_FREQ_SOURCE_CPUFREQ = 0, > + SCALE_FREQ_SOURCE_ARCH, > +}; > + > +struct scale_freq_data { > + enum scale_freq_source source; > + void (*set_freq_scale)(void); > +}; > + > +void topology_scale_freq_tick(void); > +void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); > +void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); Nit: can you split these lines? Ionela. > > DECLARE_PER_CPU(unsigned long, thermal_pressure); > > -- > 2.25.0.rc1.19.g042ed3e048af >
On 09-03-21, 15:11, Ionela Voinescu wrote: > On Monday 01 Mar 2021 at 12:21:17 (+0530), Viresh Kumar wrote: > > diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h > > index 0f6cd6b73a61..3bcfba5c21a7 100644 > > --- a/include/linux/arch_topology.h > > +++ b/include/linux/arch_topology.h > > @@ -34,7 +34,19 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, > > unsigned long max_freq); > > bool topology_scale_freq_invariant(void); We don't normally add blank lines between declarations (variables or function), like what's done here. > > > > -bool arch_freq_counters_available(const struct cpumask *cpus); > > +enum scale_freq_source { > > + SCALE_FREQ_SOURCE_CPUFREQ = 0, > > + SCALE_FREQ_SOURCE_ARCH, > > +}; > > + > > +struct scale_freq_data { > > + enum scale_freq_source source; > > + void (*set_freq_scale)(void); > > +}; > > + > > +void topology_scale_freq_tick(void); > > +void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); > > +void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); > > Nit: can you split these lines? And so in order to be consistent across the file, I haven't added one here. -- viresh
diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index 3b8dca4eb08d..ec2db3419c41 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -17,17 +17,9 @@ int pcibus_to_node(struct pci_bus *bus); #include <linux/arch_topology.h> void update_freq_counters_refs(void); -void topology_scale_freq_tick(void); - -#ifdef CONFIG_ARM64_AMU_EXTN -/* - * Replace task scheduler's default counter-based - * frequency-invariance scale factor setting. - */ -#define arch_scale_freq_tick topology_scale_freq_tick -#endif /* CONFIG_ARM64_AMU_EXTN */ /* Replace task scheduler's default frequency-invariant accounting */ +#define arch_scale_freq_tick topology_scale_freq_tick #define arch_set_freq_scale topology_set_freq_scale #define arch_scale_freq_capacity topology_get_freq_scale #define arch_scale_freq_invariant topology_scale_freq_invariant diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index e08a4126453a..47fca7376c93 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -199,12 +199,47 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) return 0; } -static DEFINE_STATIC_KEY_FALSE(amu_fie_key); -#define amu_freq_invariant() static_branch_unlikely(&amu_fie_key) +static void amu_scale_freq_tick(void) +{ + u64 prev_core_cnt, prev_const_cnt; + u64 core_cnt, const_cnt, scale; + + prev_const_cnt = this_cpu_read(arch_const_cycles_prev); + prev_core_cnt = this_cpu_read(arch_core_cycles_prev); + + update_freq_counters_refs(); + + const_cnt = this_cpu_read(arch_const_cycles_prev); + core_cnt = this_cpu_read(arch_core_cycles_prev); + + if (unlikely(core_cnt <= prev_core_cnt || + const_cnt <= prev_const_cnt)) + return; + + /* + * /\core arch_max_freq_scale + * scale = ------- * -------------------- + * /\const SCHED_CAPACITY_SCALE + * + * See validate_cpu_freq_invariance_counters() for details on + * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. + */ + scale = core_cnt - prev_core_cnt; + scale *= this_cpu_read(arch_max_freq_scale); + scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, + const_cnt - prev_const_cnt); + + scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); + this_cpu_write(freq_scale, (unsigned long)scale); +} + +static struct scale_freq_data amu_sfd = { + .source = SCALE_FREQ_SOURCE_ARCH, + .set_freq_scale = amu_scale_freq_tick, +}; static void amu_fie_setup(const struct cpumask *cpus) { - bool invariant; int cpu; /* We are already set since the last insmod of cpufreq driver */ @@ -221,25 +256,10 @@ static void amu_fie_setup(const struct cpumask *cpus) cpumask_or(amu_fie_cpus, amu_fie_cpus, cpus); - invariant = topology_scale_freq_invariant(); - - /* We aren't fully invariant yet */ - if (!invariant && !cpumask_equal(amu_fie_cpus, cpu_present_mask)) - return; - - static_branch_enable(&amu_fie_key); + topology_set_scale_freq_source(&amu_sfd, amu_fie_cpus); pr_debug("CPUs[%*pbl]: counters will be used for FIE.", cpumask_pr_args(cpus)); - - /* - * Task scheduler behavior depends on frequency invariance support, - * either cpufreq or counter driven. If the support status changes as - * a result of counter initialisation and use, retrigger the build of - * scheduling domains to ensure the information is propagated properly. - */ - if (!invariant) - rebuild_sched_domains_energy(); } static int init_amu_fie_callback(struct notifier_block *nb, unsigned long val, @@ -283,53 +303,6 @@ static int __init init_amu_fie(void) } core_initcall(init_amu_fie); -bool arch_freq_counters_available(const struct cpumask *cpus) -{ - return amu_freq_invariant() && - cpumask_subset(cpus, amu_fie_cpus); -} - -void topology_scale_freq_tick(void) -{ - u64 prev_core_cnt, prev_const_cnt; - u64 core_cnt, const_cnt, scale; - int cpu = smp_processor_id(); - - if (!amu_freq_invariant()) - return; - - if (!cpumask_test_cpu(cpu, amu_fie_cpus)) - return; - - prev_const_cnt = this_cpu_read(arch_const_cycles_prev); - prev_core_cnt = this_cpu_read(arch_core_cycles_prev); - - update_freq_counters_refs(); - - const_cnt = this_cpu_read(arch_const_cycles_prev); - core_cnt = this_cpu_read(arch_core_cycles_prev); - - if (unlikely(core_cnt <= prev_core_cnt || - const_cnt <= prev_const_cnt)) - return; - - /* - * /\core arch_max_freq_scale - * scale = ------- * -------------------- - * /\const SCHED_CAPACITY_SCALE - * - * See validate_cpu_freq_invariance_counters() for details on - * arch_max_freq_scale and the use of SCHED_CAPACITY_SHIFT. - */ - scale = core_cnt - prev_core_cnt; - scale *= this_cpu_read(arch_max_freq_scale); - scale = div64_u64(scale >> SCHED_CAPACITY_SHIFT, - const_cnt - prev_const_cnt); - - scale = min_t(unsigned long, scale, SCHED_CAPACITY_SCALE); - this_cpu_write(freq_scale, (unsigned long)scale); -} - #ifdef CONFIG_ACPI_CPPC_LIB #include <acpi/cppc_acpi.h> diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index de8587cc119e..8f62dbf93f67 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -21,17 +21,94 @@ #include <linux/sched.h> #include <linux/smp.h> +static DEFINE_PER_CPU(struct scale_freq_data *, sft_data); +static struct cpumask scale_freq_counters_mask; +static bool scale_freq_invariant; + +static bool supports_scale_freq_counters(const struct cpumask *cpus) +{ + return cpumask_subset(cpus, &scale_freq_counters_mask); +} + bool topology_scale_freq_invariant(void) { return cpufreq_supports_freq_invariance() || - arch_freq_counters_available(cpu_online_mask); + supports_scale_freq_counters(cpu_online_mask); } -__weak bool arch_freq_counters_available(const struct cpumask *cpus) +static void update_scale_freq_invariant(bool status) { - return false; + if (scale_freq_invariant == status) + return; + + /* + * Task scheduler behavior depends on frequency invariance support, + * either cpufreq or counter driven. If the support status changes as + * a result of counter initialisation and use, retrigger the build of + * scheduling domains to ensure the information is propagated properly. + */ + if (topology_scale_freq_invariant() == status) { + scale_freq_invariant = status; + rebuild_sched_domains_energy(); + } } + +void topology_set_scale_freq_source(struct scale_freq_data *data, + const struct cpumask *cpus) +{ + struct scale_freq_data *sfd; + int cpu; + + /* + * Avoid calling rebuild_sched_domains() unnecessarily if FIE is + * supported by cpufreq. + */ + if (cpumask_empty(&scale_freq_counters_mask)) + scale_freq_invariant = topology_scale_freq_invariant(); + + for_each_cpu(cpu, cpus) { + sfd = per_cpu(sft_data, cpu); + + /* Use ARCH provided counters whenever possible */ + if (!sfd || sfd->source != SCALE_FREQ_SOURCE_ARCH) { + per_cpu(sft_data, cpu) = data; + cpumask_set_cpu(cpu, &scale_freq_counters_mask); + } + } + + update_scale_freq_invariant(true); +} +EXPORT_SYMBOL_GPL(topology_set_scale_freq_source); + +void topology_clear_scale_freq_source(enum scale_freq_source source, + const struct cpumask *cpus) +{ + struct scale_freq_data *sfd; + int cpu; + + for_each_cpu(cpu, cpus) { + sfd = per_cpu(sft_data, cpu); + + if (sfd && sfd->source == source) { + per_cpu(sft_data, cpu) = NULL; + cpumask_clear_cpu(cpu, &scale_freq_counters_mask); + } + } + + update_scale_freq_invariant(false); +} +EXPORT_SYMBOL_GPL(topology_clear_scale_freq_source); + +void topology_scale_freq_tick(void) +{ + struct scale_freq_data *sfd = *this_cpu_ptr(&sft_data); + + if (sfd) + sfd->set_freq_scale(); +} + DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE; +EXPORT_SYMBOL_GPL(freq_scale); void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, unsigned long max_freq) @@ -47,7 +124,7 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, * want to update the scale factor with information from CPUFREQ. * Instead the scale factor will be updated from arch_scale_freq_tick. */ - if (arch_freq_counters_available(cpus)) + if (supports_scale_freq_counters(cpus)) return; scale = (cur_freq << SCHED_CAPACITY_SHIFT) / max_freq; diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 0f6cd6b73a61..3bcfba5c21a7 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -34,7 +34,19 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, unsigned long max_freq); bool topology_scale_freq_invariant(void); -bool arch_freq_counters_available(const struct cpumask *cpus); +enum scale_freq_source { + SCALE_FREQ_SOURCE_CPUFREQ = 0, + SCALE_FREQ_SOURCE_ARCH, +}; + +struct scale_freq_data { + enum scale_freq_source source; + void (*set_freq_scale)(void); +}; + +void topology_scale_freq_tick(void); +void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus); +void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus); DECLARE_PER_CPU(unsigned long, thermal_pressure);