| Message ID | 20231104105907.1365392-8-vincent.guittot@linaro.org |
|---|---|
| State | Superseded |
| Headers | show |
| Series | consolidate and cleanup CPU capacity | expand |
On Sat, Nov 04, 2023 at 11:59:07AM +0100, Vincent Guittot wrote: > Use the new capacity_ref_freq to set the ratio that is used by AMU for > computing the arch_scale_freq_capacity(). > This helps to keep everything aligned using the same reference for > computing CPUs capacity. > > The default value of the ratio (stored in per_cpu(arch_max_freq_scale)) > ensures that arch_scale_freq_capacity() returns max capacity until it is > set to its correct value with the cpu capacity and capacity_ref_freq. > > Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> > --- > arch/arm64/kernel/topology.c | 26 ++++++++++++++------------ > drivers/base/arch_topology.c | 12 +++++++++++- > include/linux/arch_topology.h | 1 + > 3 files changed, 26 insertions(+), 13 deletions(-) > > diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c > index 817d788cd866..615c1a20129f 100644 > --- a/arch/arm64/kernel/topology.c > +++ b/arch/arm64/kernel/topology.c > @@ -82,7 +82,12 @@ int __init parse_acpi_topology(void) > #undef pr_fmt > #define pr_fmt(fmt) "AMU: " fmt > > -static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale); > +/* > + * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until > + * the CPU capacity and its associated frequency have been correctly > + * initialized. > + */ > +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) = 1UL << (2 * SCHED_CAPACITY_SHIFT); This doesn't seem to match the comment? SCHED_CAPACITY_SCALE doesn't have the '2 *' multiplier. > static DEFINE_PER_CPU(u64, arch_const_cycles_prev); > static DEFINE_PER_CPU(u64, arch_core_cycles_prev); > static cpumask_var_t amu_fie_cpus; > @@ -112,14 +117,14 @@ static inline bool freq_counters_valid(int cpu) > return true; > } > > -static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) > +void freq_inv_set_max_ratio(int cpu, u64 max_rate) > { > - u64 ratio; > + u64 ratio, ref_rate = arch_timer_get_rate(); > > if (unlikely(!max_rate || !ref_rate)) { > - pr_debug("CPU%d: invalid maximum or reference frequency.\n", > + WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n", > cpu); > - return -EINVAL; > + return; > } > > /* > @@ -139,12 +144,12 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) > ratio = div64_u64(ratio, max_rate); > if (!ratio) { > WARN_ONCE(1, "Reference frequency too low.\n"); > - return -EINVAL; > + return; > } > > - per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio; > + WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio); Why is WRITE_ONCE() now needed? > - return 0; > + return; Pointless 'return;' statement. Will
On Tue, 7 Nov 2023 at 13:01, Will Deacon <will@kernel.org> wrote: > > On Tue, Nov 07, 2023 at 12:18:20PM +0100, Vincent Guittot wrote: > > On Tue, 7 Nov 2023 at 11:38, Will Deacon <will@kernel.org> wrote: > > > > > > On Sat, Nov 04, 2023 at 11:59:07AM +0100, Vincent Guittot wrote: > > > > Use the new capacity_ref_freq to set the ratio that is used by AMU for > > > > computing the arch_scale_freq_capacity(). > > > > This helps to keep everything aligned using the same reference for > > > > computing CPUs capacity. > > > > > > > > The default value of the ratio (stored in per_cpu(arch_max_freq_scale)) > > > > ensures that arch_scale_freq_capacity() returns max capacity until it is > > > > set to its correct value with the cpu capacity and capacity_ref_freq. > > > > > > > > Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> > > > > --- > > > > arch/arm64/kernel/topology.c | 26 ++++++++++++++------------ > > > > drivers/base/arch_topology.c | 12 +++++++++++- > > > > include/linux/arch_topology.h | 1 + > > > > 3 files changed, 26 insertions(+), 13 deletions(-) > > > > > > > > diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c > > > > index 817d788cd866..615c1a20129f 100644 > > > > --- a/arch/arm64/kernel/topology.c > > > > +++ b/arch/arm64/kernel/topology.c > > > > @@ -82,7 +82,12 @@ int __init parse_acpi_topology(void) > > > > #undef pr_fmt > > > > #define pr_fmt(fmt) "AMU: " fmt > > > > > > > > -static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale); > > > > +/* > > > > + * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until > > > > + * the CPU capacity and its associated frequency have been correctly > > > > + * initialized. > > > > + */ > > > > +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) = 1UL << (2 * SCHED_CAPACITY_SHIFT); > > > > > > This doesn't seem to match the comment? SCHED_CAPACITY_SCALE doesn't have > > > the '2 *' multiplier. > > > > The comment in freq_inv_set_max_ratio() says: > > > > * We use a factor of 2 * SCHED_CAPACITY_SHIFT -> SCHED_CAPACITY_SCALE² > > * in order to ensure a good resolution for arch_max_freq_scale for > > * very low reference frequencies (down to the KHz range which should > > * be unlikely). > > > > Then there is a " * arch_max_freq_scale) >> SCHED_CAPACITY_SHIFT" > > when computing the scale which brings the result back to > > SCHED_CAPACITY_SHIFT > > Ah, I see; I'd not spotted that amu_scale_freq_tick() is doing some > arithmetic on the value (it doesn't return anything because it's 'void'). > It's slightly confusing because the comment talks about SCHED_CAPACITY_SCALE > whereas all the code works on the shift, but I get it now. > > > > > static DEFINE_PER_CPU(u64, arch_const_cycles_prev); > > > > static DEFINE_PER_CPU(u64, arch_core_cycles_prev); > > > > static cpumask_var_t amu_fie_cpus; > > > > @@ -112,14 +117,14 @@ static inline bool freq_counters_valid(int cpu) > > > > return true; > > > > } > > > > > > > > -static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) > > > > +void freq_inv_set_max_ratio(int cpu, u64 max_rate) > > > > { > > > > - u64 ratio; > > > > + u64 ratio, ref_rate = arch_timer_get_rate(); > > > > > > > > if (unlikely(!max_rate || !ref_rate)) { > > > > - pr_debug("CPU%d: invalid maximum or reference frequency.\n", > > > > + WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n", > > > > cpu); > > > > - return -EINVAL; > > > > + return; > > > > } > > > > > > > > /* > > > > @@ -139,12 +144,12 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) > > > > ratio = div64_u64(ratio, max_rate); > > > > if (!ratio) { > > > > WARN_ONCE(1, "Reference frequency too low.\n"); > > > > - return -EINVAL; > > > > + return; > > > > } > > > > > > > > - per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio; > > > > + WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio); > > > > > > Why is WRITE_ONCE() now needed? > > > > the tick can already use it. We want to make sure to use either the > > old or the new one but not an intermediate value > > Isn't that already the case without this patch? In other words, this should > be a separate change. Currently the ratio is set in the same notifier callback before registering the AMU function in topology_scale_freq_tick whereas there are now done in 2 separate notifier callbacks (still for the same event) but we don't know the order > > Will
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index 817d788cd866..615c1a20129f 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -82,7 +82,12 @@ int __init parse_acpi_topology(void) #undef pr_fmt #define pr_fmt(fmt) "AMU: " fmt -static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale); +/* + * Ensure that amu_scale_freq_tick() will return SCHED_CAPACITY_SCALE until + * the CPU capacity and its associated frequency have been correctly + * initialized. + */ +static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) = 1UL << (2 * SCHED_CAPACITY_SHIFT); static DEFINE_PER_CPU(u64, arch_const_cycles_prev); static DEFINE_PER_CPU(u64, arch_core_cycles_prev); static cpumask_var_t amu_fie_cpus; @@ -112,14 +117,14 @@ static inline bool freq_counters_valid(int cpu) return true; } -static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) +void freq_inv_set_max_ratio(int cpu, u64 max_rate) { - u64 ratio; + u64 ratio, ref_rate = arch_timer_get_rate(); if (unlikely(!max_rate || !ref_rate)) { - pr_debug("CPU%d: invalid maximum or reference frequency.\n", + WARN_ONCE(1, "CPU%d: invalid maximum or reference frequency.\n", cpu); - return -EINVAL; + return; } /* @@ -139,12 +144,12 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate) ratio = div64_u64(ratio, max_rate); if (!ratio) { WARN_ONCE(1, "Reference frequency too low.\n"); - return -EINVAL; + return; } - per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio; + WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio); - return 0; + return; } static void amu_scale_freq_tick(void) @@ -195,10 +200,7 @@ static void amu_fie_setup(const struct cpumask *cpus) return; for_each_cpu(cpu, cpus) { - if (!freq_counters_valid(cpu) || - freq_inv_set_max_ratio(cpu, - cpufreq_get_hw_max_freq(cpu) * 1000ULL, - arch_timer_get_rate())) + if (!freq_counters_valid(cpu)) return; } diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 0a2e43728286..0906114963ff 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -344,6 +344,10 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) return !ret; } +void __weak freq_inv_set_max_ratio(int cpu, u64 max_rate) +{ +} + #ifdef CONFIG_ACPI_CPPC_LIB #include <acpi/cppc_acpi.h> @@ -381,6 +385,9 @@ void topology_init_cpu_capacity_cppc(void) } for_each_possible_cpu(cpu) { + freq_inv_set_max_ratio(cpu, + per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ); + capacity = raw_capacity[cpu]; capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT, capacity_scale); @@ -422,8 +429,11 @@ init_cpu_capacity_callback(struct notifier_block *nb, cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus); - for_each_cpu(cpu, policy->related_cpus) + for_each_cpu(cpu, policy->related_cpus) { per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq; + freq_inv_set_max_ratio(cpu, + per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ); + } if (cpumask_empty(cpus_to_visit)) { topology_normalize_cpu_scale(); diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index 32c24ff4f2a8..a63d61ca55af 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -99,6 +99,7 @@ void update_siblings_masks(unsigned int cpu); void remove_cpu_topology(unsigned int cpuid); void reset_cpu_topology(void); int parse_acpi_topology(void); +void freq_inv_set_max_ratio(int cpu, u64 max_rate); #endif #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
Use the new capacity_ref_freq to set the ratio that is used by AMU for computing the arch_scale_freq_capacity(). This helps to keep everything aligned using the same reference for computing CPUs capacity. The default value of the ratio (stored in per_cpu(arch_max_freq_scale)) ensures that arch_scale_freq_capacity() returns max capacity until it is set to its correct value with the cpu capacity and capacity_ref_freq. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> --- arch/arm64/kernel/topology.c | 26 ++++++++++++++------------ drivers/base/arch_topology.c | 12 +++++++++++- include/linux/arch_topology.h | 1 + 3 files changed, 26 insertions(+), 13 deletions(-)