6.6-stable review patch. If anyone has any objections, please let me know.
------------------
From: Vincent Guittot vincent.guittot@linaro.org
commit 9942cb22ea458c34fa17b73d143ea32d4df1caca upstream.
Create a new method to get a unique and fixed max frequency. Currently cpuinfo.max_freq or the highest (or last) state of performance domain are used as the max frequency when computing the frequency for a level of utilization, but:
- cpuinfo_max_freq can change at runtime. boost is one example of such change.
- cpuinfo.max_freq and last item of the PD can be different leading to different results between cpufreq and energy model.
We need to save the reference frequency that has been used when computing the CPUs capacity and use this fixed and coherent value to convert between frequency and CPU's capacity.
In fact, we already save the frequency that has been used when computing the capacity of each CPU. We extend the precision to save kHz instead of MHz currently and we modify the type to be aligned with other variables used when converting frequency to capacity and the other way.
[ mingo: Minor edits. ]
Signed-off-by: Vincent Guittot vincent.guittot@linaro.org Signed-off-by: Ingo Molnar mingo@kernel.org Tested-by: Lukasz Luba lukasz.luba@arm.com Reviewed-by: Lukasz Luba lukasz.luba@arm.com Acked-by: Sudeep Holla sudeep.holla@arm.com Link: https://lore.kernel.org/r/20231211104855.558096-2-vincent.guittot@linaro.org Stable-dep-of: e37617c8e53a ("sched/fair: Fix frequency selection for non-invariant case") Signed-off-by: Wentao Guan guanwentao@uniontech.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/include/asm/topology.h | 1 + arch/arm64/include/asm/topology.h | 1 + arch/riscv/include/asm/topology.h | 1 + drivers/base/arch_topology.c | 29 ++++++++++++++--------------- include/linux/arch_topology.h | 7 +++++++ include/linux/sched/topology.h | 8 ++++++++ 6 files changed, 32 insertions(+), 15 deletions(-)
--- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -13,6 +13,7 @@ #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 +#define arch_scale_freq_ref topology_get_freq_ref #endif
/* Replace task scheduler's default cpu-invariant accounting */ --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -23,6 +23,7 @@ void update_freq_counters_refs(void); #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 +#define arch_scale_freq_ref topology_get_freq_ref
#ifdef CONFIG_ACPI_CPPC_LIB #define arch_init_invariance_cppc topology_init_cpu_capacity_cppc --- a/arch/riscv/include/asm/topology.h +++ b/arch/riscv/include/asm/topology.h @@ -9,6 +9,7 @@ #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 +#define arch_scale_freq_ref topology_get_freq_ref
/* Replace task scheduler's default cpu-invariant accounting */ #define arch_scale_cpu_capacity topology_get_cpu_scale --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -19,6 +19,7 @@ #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/sched.h> +#include <linux/units.h>
#define CREATE_TRACE_POINTS #include <trace/events/thermal_pressure.h> @@ -26,7 +27,8 @@ static DEFINE_PER_CPU(struct scale_freq_data __rcu *, sft_data); static struct cpumask scale_freq_counters_mask; static bool scale_freq_invariant; -static DEFINE_PER_CPU(u32, freq_factor) = 1; +DEFINE_PER_CPU(unsigned long, capacity_freq_ref) = 1; +EXPORT_PER_CPU_SYMBOL_GPL(capacity_freq_ref);
static bool supports_scale_freq_counters(const struct cpumask *cpus) { @@ -170,9 +172,9 @@ DEFINE_PER_CPU(unsigned long, thermal_pr * operating on stale data when hot-plug is used for some CPUs. The * @capped_freq reflects the currently allowed max CPUs frequency due to * thermal capping. It might be also a boost frequency value, which is bigger - * than the internal 'freq_factor' max frequency. In such case the pressure - * value should simply be removed, since this is an indication that there is - * no thermal throttling. The @capped_freq must be provided in kHz. + * than the internal 'capacity_freq_ref' max frequency. In such case the + * pressure value should simply be removed, since this is an indication that + * there is no thermal throttling. The @capped_freq must be provided in kHz. */ void topology_update_thermal_pressure(const struct cpumask *cpus, unsigned long capped_freq) @@ -183,10 +185,7 @@ void topology_update_thermal_pressure(co
cpu = cpumask_first(cpus); max_capacity = arch_scale_cpu_capacity(cpu); - max_freq = per_cpu(freq_factor, cpu); - - /* Convert to MHz scale which is used in 'freq_factor' */ - capped_freq /= 1000; + max_freq = arch_scale_freq_ref(cpu);
/* * Handle properly the boost frequencies, which should simply clean @@ -279,13 +278,13 @@ void topology_normalize_cpu_scale(void)
capacity_scale = 1; for_each_possible_cpu(cpu) { - capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu); + capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu); capacity_scale = max(capacity, capacity_scale); }
pr_debug("cpu_capacity: capacity_scale=%llu\n", capacity_scale); for_each_possible_cpu(cpu) { - capacity = raw_capacity[cpu] * per_cpu(freq_factor, cpu); + capacity = raw_capacity[cpu] * per_cpu(capacity_freq_ref, cpu); capacity = div64_u64(capacity << SCHED_CAPACITY_SHIFT, capacity_scale); topology_set_cpu_scale(cpu, capacity); @@ -321,15 +320,15 @@ bool __init topology_parse_cpu_capacity( cpu_node, raw_capacity[cpu]);
/* - * Update freq_factor for calculating early boot cpu capacities. + * Update capacity_freq_ref for calculating early boot CPU capacities. * For non-clk CPU DVFS mechanism, there's no way to get the * frequency value now, assuming they are running at the same - * frequency (by keeping the initial freq_factor value). + * frequency (by keeping the initial capacity_freq_ref value). */ cpu_clk = of_clk_get(cpu_node, 0); if (!PTR_ERR_OR_ZERO(cpu_clk)) { - per_cpu(freq_factor, cpu) = - clk_get_rate(cpu_clk) / 1000; + per_cpu(capacity_freq_ref, cpu) = + clk_get_rate(cpu_clk) / HZ_PER_KHZ; clk_put(cpu_clk); } } else { @@ -411,7 +410,7 @@ init_cpu_capacity_callback(struct notifi cpumask_andnot(cpus_to_visit, cpus_to_visit, policy->related_cpus);
for_each_cpu(cpu, policy->related_cpus) - per_cpu(freq_factor, cpu) = policy->cpuinfo.max_freq / 1000; + per_cpu(capacity_freq_ref, cpu) = policy->cpuinfo.max_freq;
if (cpumask_empty(cpus_to_visit)) { topology_normalize_cpu_scale(); --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -27,6 +27,13 @@ static inline unsigned long topology_get
void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
+DECLARE_PER_CPU(unsigned long, capacity_freq_ref); + +static inline unsigned long topology_get_freq_ref(int cpu) +{ + return per_cpu(capacity_freq_ref, cpu); +} + DECLARE_PER_CPU(unsigned long, arch_freq_scale);
static inline unsigned long topology_get_freq_scale(int cpu) --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -275,6 +275,14 @@ void arch_update_thermal_pressure(const { } #endif
+#ifndef arch_scale_freq_ref +static __always_inline +unsigned int arch_scale_freq_ref(int cpu) +{ + return 0; +} +#endif + static inline int task_node(const struct task_struct *p) { return cpu_to_node(task_cpu(p));