From da458425b7e291f4a7d0cfb1d17a276f3f18ec18 Mon Sep 17 00:00:00 2001 From: Oleg Keri Date: Thu, 10 Sep 2026 08:34:39 +0200 Subject: [PATCH 1/2] arm64: topology: fix arch_freq_get_on_cpu() overflow above 4.19 GHz arch_freq_get_on_cpu() computes the product of the frequency scale and the reference frequency as a u64, but assigns it to an unsigned int before shifting it back down: freq = scale * arch_scale_freq_ref(cpu); freq >>= SCHED_CAPACITY_SHIFT; The product is truncated to 32 bits before the shift, so the result wraps once arch_scale_freq_ref() exceeds 2^32 / SCHED_CAPACITY_SCALE, i.e. 4194304 kHz. On a Snapdragon X2 Elite (Glymur) laptop, whose boost OPP is 4723200 kHz, cpuinfo_avg_freq reports 524283 kHz instead of ~4723200 kHz while the CPU demonstrably runs at the boost frequency: a fixed workload completes in 1.72 s at the 4723200 kHz OPP versus 2.01 s at 4032000 kHz, matching the 1.171 frequency ratio. Keep the arithmetic in 64 bits until after the shift. Fixes: 16d1e27475f6 ("arm64: Provide an AMU-based version of arch_freq_get_on_cpu") Signed-off-by: Oleg Keri Signed-off-by: Linux RISC-V bot --- arch/arm64/kernel/topology.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index d28438f8b83f12..0eca321ff11318 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -245,8 +245,7 @@ int arch_freq_get_on_cpu(int cpu) * (see amu_scale_freq_tick for details) */ scale = arch_scale_freq_capacity(cpu); - freq = scale * arch_scale_freq_ref(cpu); - freq >>= SCHED_CAPACITY_SHIFT; + freq = (scale * arch_scale_freq_ref(cpu)) >> SCHED_CAPACITY_SHIFT; return freq; } From 5d30089eae5110fa3349286a78c148f8dbaf558f Mon Sep 17 00:00:00 2001 From: Oleg Keri Date: Thu, 10 Sep 2026 08:34:40 +0200 Subject: [PATCH 2/2] cpufreq: update capacity_freq_ref when the boost state changes capacity_freq_ref is latched from policy->cpuinfo.max_freq by init_cpu_capacity_callback() on CPUFREQ_CREATE_POLICY, and never updated afterwards. cpufreq_frequency_table_cpuinfo() excludes CPUFREQ_BOOST_FREQ entries while boost is disabled, so on a system that boots with boost off the latched value is the non-boost maximum. Enabling boost later raises policy->cpuinfo.max_freq but leaves capacity_freq_ref behind. Two things then go wrong on arm64, where the AMU drives frequency invariance. amu_scale_freq_tick() caps the computed scale at SCHED_CAPACITY_SCALE, so a CPU running above capacity_freq_ref saturates at 1024: the scheduler cannot tell a boosted CPU from one at the sustained maximum, and utilisation is underestimated. And arch_freq_get_on_cpu(), which reverses that computation, cannot report more than capacity_freq_ref, so cpuinfo_avg_freq is pinned to the non-boost maximum. On a Snapdragon X2 Elite (Glymur) laptop with a 4032000 kHz sustained and a 4723200 kHz boost OPP, cpuinfo_avg_freq reads exactly 4032000 while the CPU runs at 4723200; a fixed workload completes in 1.72 s rather than the 2.01 s that frequency would imply. Factor the update out of init_cpu_capacity_callback() into topology_update_freq_ref() and call it from policy_set_boost(), which is the common path for the global boost knob, the per-policy one, and the CPU online path. Signed-off-by: Oleg Keri Signed-off-by: Linux RISC-V bot --- 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 | 19 +++++++++++++------ drivers/cpufreq/cpufreq.c | 2 ++ include/linux/arch_topology.h | 1 + include/linux/cpufreq.h | 7 +++++++ 7 files changed, 26 insertions(+), 6 deletions(-) diff --git a/arch/arm/include/asm/topology.h b/arch/arm/include/asm/topology.h index ad36b657006746..a776a79885ee43 100644 --- a/arch/arm/include/asm/topology.h +++ b/arch/arm/include/asm/topology.h @@ -11,6 +11,7 @@ #ifndef CONFIG_BL_SWITCHER /* Replace task scheduler's default frequency-invariant accounting */ #define arch_set_freq_scale topology_set_freq_scale +#define arch_update_freq_ref topology_update_freq_ref #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 diff --git a/arch/arm64/include/asm/topology.h b/arch/arm64/include/asm/topology.h index b9eaf4ad708503..a4b96a7ee4a59c 100644 --- a/arch/arm64/include/asm/topology.h +++ b/arch/arm64/include/asm/topology.h @@ -22,6 +22,7 @@ void update_freq_counters_refs(void); /* 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_update_freq_ref topology_update_freq_ref #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 diff --git a/arch/riscv/include/asm/topology.h b/arch/riscv/include/asm/topology.h index fe1a8bf6902d95..a363d72c174f30 100644 --- a/arch/riscv/include/asm/topology.h +++ b/arch/riscv/include/asm/topology.h @@ -11,6 +11,7 @@ /* 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_update_freq_ref topology_update_freq_ref #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 diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c index 8c5e47c28d9a32..79eb1681065d9b 100644 --- a/drivers/base/arch_topology.c +++ b/drivers/base/arch_topology.c @@ -317,6 +317,18 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu) return !ret; } +void topology_update_freq_ref(const struct cpumask *cpus, unsigned int max_freq) +{ + int cpu; + + for_each_cpu(cpu, cpus) { + per_cpu(capacity_freq_ref, cpu) = max_freq; + freq_inv_set_max_ratio(cpu, + per_cpu(capacity_freq_ref, cpu) * HZ_PER_KHZ); + } +} +EXPORT_SYMBOL_GPL(topology_update_freq_ref); + void __weak freq_inv_set_max_ratio(int cpu, u64 max_rate) { } @@ -392,7 +404,6 @@ init_cpu_capacity_callback(struct notifier_block *nb, void *data) { struct cpufreq_policy *policy = data; - int cpu; if (val != CPUFREQ_CREATE_POLICY) return 0; @@ -403,11 +414,7 @@ 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) { - 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); - } + topology_update_freq_ref(policy->related_cpus, policy->cpuinfo.max_freq); if (cpumask_empty(cpus_to_visit)) { if (raw_capacity) { diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 0d0df986fa3df1..289649baa061c4 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -594,6 +594,8 @@ static int policy_set_boost(struct cpufreq_policy *policy, bool enable) return ret; } + arch_update_freq_ref(policy->related_cpus, policy->cpuinfo.max_freq); + return 0; } diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h index ebd7f8935f969f..4974f5e1a7feff 100644 --- a/include/linux/arch_topology.h +++ b/include/linux/arch_topology.h @@ -31,6 +31,7 @@ static inline unsigned long topology_get_freq_scale(int cpu) void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq, unsigned long max_freq); +void topology_update_freq_ref(const struct cpumask *cpus, unsigned int max_freq); bool topology_scale_freq_invariant(void); enum scale_freq_source { diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 35ce665edfd824..5b904e13eb213d 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -1235,6 +1235,13 @@ void arch_set_freq_scale(const struct cpumask *cpus, } #endif +#ifndef arch_update_freq_ref +static __always_inline +void arch_update_freq_ref(const struct cpumask *cpus, unsigned int max_freq) +{ +} +#endif + /* the following are really really optional */ extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs; extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;