arch/arm64/kernel/topology.c | 6 ++---- include/linux/sched/topology.h | 5 +++++ kernel/sched/sched.h | 2 -- 3 files changed, 7 insertions(+), 6 deletions(-)
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.
Compute it with cap_scale(), turned into a static inline taking u64 and
moved to <linux/sched/topology.h> so it is usable outside kernel/sched.
Fixes: 16d1e27475f6 ("arm64: Provide an AMU-based version of arch_freq_get_on_cpu")
Signed-off-by: Oleg Keri <okerixx@gmail.com>
---
Changes in v5:
- cap_scale() becomes a static inline taking u64 arguments instead of
a macro, as Dietmar proposed and Peter agreed, after Peter pointed out
that the macro relies on one operand being u64. It now lives in
<linux/sched/topology.h>, where SCHED_CAPACITY_SHIFT is visible,
rather than <linux/topology.h>.
- Patch 2/2 of v4 is dropped: it duplicated Ananthu C V's series [1],
which I tested instead. This fix is needed with that series, since
it puts the reference above 4194304 kHz from boot.
- v4: https://lore.kernel.org/all/20260917125112.2283-1-okerixx@gmail.com/
[1] https://lore.kernel.org/all/20260908-schedutil-boost-frequency-handling-v2-0-25312a713699@oss.qualcomm.com/
arch/arm64/kernel/topology.c | 6 ++----
include/linux/sched/topology.h | 5 +++++
kernel/sched/sched.h | 2 --
3 files changed, 7 insertions(+), 6 deletions(-)
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index d28438f8b83f..39dd7f8575cd 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -19,6 +19,7 @@
#include <linux/init.h>
#include <linux/percpu.h>
#include <linux/sched/isolation.h>
+#include <linux/sched/topology.h>
#include <linux/xarray.h>
#include <asm/cpu.h>
@@ -186,7 +187,6 @@ int arch_freq_get_on_cpu(int cpu)
struct amu_cntr_sample *amu_sample;
unsigned int start_cpu = cpu;
unsigned long last_update;
- unsigned int freq = 0;
u64 scale;
if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
@@ -245,9 +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;
- return freq;
+ return cap_scale(arch_scale_freq_ref(cpu), scale);
}
static void amu_fie_setup(const struct cpumask *cpus)
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index b5d9d7c2b8ad..922b2f015e89 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -234,6 +234,11 @@ static inline void rebuild_sched_domains_energy(void)
}
#endif
+static inline u64 cap_scale(u64 value, u64 scale)
+{
+ return value * scale >> SCHED_CAPACITY_SHIFT;
+}
+
#ifndef arch_scale_cpu_capacity
/**
* arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6c3ad70e58b8..45796fccdc84 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -236,8 +236,6 @@ static inline int task_has_dl_policy(struct task_struct *p)
return dl_policy(p->policy);
}
-#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
-
static inline void update_avg(u64 *avg, u64 sample)
{
s64 diff = sample - *avg;
base-commit: 0d9d0dbf2fddcff5859d623e90ca73c4054276e1
--
2.55.0On Thu, Sep 17, 2026 at 08:20:59PM +0200, Oleg Keri wrote:
> 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.
>
> Compute it with cap_scale(), turned into a static inline taking u64 and
> moved to <linux/sched/topology.h> so it is usable outside kernel/sched.
>
> Fixes: 16d1e27475f6 ("arm64: Provide an AMU-based version of arch_freq_get_on_cpu")
> Signed-off-by: Oleg Keri <okerixx@gmail.com>
> ---
> Changes in v5:
> - cap_scale() becomes a static inline taking u64 arguments instead of
> a macro, as Dietmar proposed and Peter agreed, after Peter pointed out
> that the macro relies on one operand being u64. It now lives in
> <linux/sched/topology.h>, where SCHED_CAPACITY_SHIFT is visible,
> rather than <linux/topology.h>.
> - Patch 2/2 of v4 is dropped: it duplicated Ananthu C V's series [1],
> which I tested instead. This fix is needed with that series, since
> it puts the reference above 4194304 kHz from boot.
> - v4: https://lore.kernel.org/all/20260917125112.2283-1-okerixx@gmail.com/
>
> [1] https://lore.kernel.org/all/20260908-schedutil-boost-frequency-handling-v2-0-25312a713699@oss.qualcomm.com/
>
> arch/arm64/kernel/topology.c | 6 ++----
> include/linux/sched/topology.h | 5 +++++
> kernel/sched/sched.h | 2 --
> 3 files changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index d28438f8b83f..39dd7f8575cd 100644
> --- a/arch/arm64/kernel/topology.c
> +++ b/arch/arm64/kernel/topology.c
> @@ -19,6 +19,7 @@
> #include <linux/init.h>
> #include <linux/percpu.h>
> #include <linux/sched/isolation.h>
> +#include <linux/sched/topology.h>
> #include <linux/xarray.h>
>
> #include <asm/cpu.h>
> @@ -186,7 +187,6 @@ int arch_freq_get_on_cpu(int cpu)
> struct amu_cntr_sample *amu_sample;
> unsigned int start_cpu = cpu;
> unsigned long last_update;
> - unsigned int freq = 0;
> u64 scale;
>
> if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
> @@ -245,9 +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;
> - return freq;
> + return cap_scale(arch_scale_freq_ref(cpu), scale);
> }
>
> static void amu_fie_setup(const struct cpumask *cpus)
The arm64 part looks fine to me, so for that:
Acked-by: Will Deacon <will@kernel.org>
However...
> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
> index b5d9d7c2b8ad..922b2f015e89 100644
> --- a/include/linux/sched/topology.h
> +++ b/include/linux/sched/topology.h
> @@ -234,6 +234,11 @@ static inline void rebuild_sched_domains_energy(void)
> }
> #endif
>
> +static inline u64 cap_scale(u64 value, u64 scale)
> +{
> + return value * scale >> SCHED_CAPACITY_SHIFT;
> +}
... does this introduce unnecessary 64-bit arithmetic for 32-bit
architectures that currently pass 'unsigned long' to the existing macro?
Will
Hi Will, On Tue, Sep 22, 2026, Will Deacon wrote: > ... does this introduce unnecessary 64-bit arithmetic for 32-bit > architectures that currently pass 'unsigned long' to the existing macro? Good catch. The truncation happens in the unsigned int temporary in arch_freq_get_on_cpu(), so v6 will drop that temporary and leave kernel/sched alone. Thanks, Oleg
On 17.09.26 20:20, Oleg Keri wrote:
> 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.
>
> Compute it with cap_scale(), turned into a static inline taking u64 and
> moved to <linux/sched/topology.h> so it is usable outside kernel/sched.
>
> Fixes: 16d1e27475f6 ("arm64: Provide an AMU-based version of arch_freq_get_on_cpu")
> Signed-off-by: Oleg Keri <okerixx@gmail.com>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
> ---
> Changes in v5:
> - cap_scale() becomes a static inline taking u64 arguments instead of
> a macro, as Dietmar proposed and Peter agreed, after Peter pointed out
> that the macro relies on one operand being u64. It now lives in
> <linux/sched/topology.h>, where SCHED_CAPACITY_SHIFT is visible,
> rather than <linux/topology.h>.
> - Patch 2/2 of v4 is dropped: it duplicated Ananthu C V's series [1],
> which I tested instead. This fix is needed with that series, since
> it puts the reference above 4194304 kHz from boot.
> - v4: https://lore.kernel.org/all/20260917125112.2283-1-okerixx@gmail.com/
>
> [1] https://lore.kernel.org/all/20260908-schedutil-boost-frequency-handling-v2-0-25312a713699@oss.qualcomm.com/
>
> arch/arm64/kernel/topology.c | 6 ++----
> include/linux/sched/topology.h | 5 +++++
> kernel/sched/sched.h | 2 --
> 3 files changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index d28438f8b83f..39dd7f8575cd 100644
> --- a/arch/arm64/kernel/topology.c
> +++ b/arch/arm64/kernel/topology.c
> @@ -19,6 +19,7 @@
> #include <linux/init.h>
> #include <linux/percpu.h>
> #include <linux/sched/isolation.h>
> +#include <linux/sched/topology.h>
> #include <linux/xarray.h>
>
> #include <asm/cpu.h>
> @@ -186,7 +187,6 @@ int arch_freq_get_on_cpu(int cpu)
> struct amu_cntr_sample *amu_sample;
> unsigned int start_cpu = cpu;
> unsigned long last_update;
> - unsigned int freq = 0;
> u64 scale;
>
> if (!amu_fie_cpu_supported(cpu) || !arch_scale_freq_ref(cpu))
> @@ -245,9 +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;
> - return freq;
> + return cap_scale(arch_scale_freq_ref(cpu), scale);
> }
>
> static void amu_fie_setup(const struct cpumask *cpus)
> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
> index b5d9d7c2b8ad..922b2f015e89 100644
> --- a/include/linux/sched/topology.h
> +++ b/include/linux/sched/topology.h
> @@ -234,6 +234,11 @@ static inline void rebuild_sched_domains_energy(void)
> }
> #endif
>
> +static inline u64 cap_scale(u64 value, u64 scale)
> +{
> + return value * scale >> SCHED_CAPACITY_SHIFT;
> +}
> +
> #ifndef arch_scale_cpu_capacity
> /**
> * arch_scale_cpu_capacity - get the capacity scale factor of a given CPU.
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 6c3ad70e58b8..45796fccdc84 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -236,8 +236,6 @@ static inline int task_has_dl_policy(struct task_struct *p)
> return dl_policy(p->policy);
> }
>
> -#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
> -
> static inline void update_avg(u64 *avg, u64 sample)
> {
> s64 diff = sample - *avg;
>
> base-commit: 0d9d0dbf2fddcff5859d623e90ca73c4054276e1
© 2016 - 2026 Red Hat, Inc.