diff mbox series

[v6,7/7] arm64/amu: Use capacity_ref_freq to set AMU ratio

Message ID 20231109101438.1139696-8-vincent.guittot@linaro.org (mailing list archive)
State Handled Elsewhere, archived
Headers show
Series consolidate and cleanup CPU capacity | expand

Commit Message

Vincent Guittot Nov. 9, 2023, 10:14 a.m. UTC 
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>
Acked-by: Sudeep Holla <sudeep.holla@arm.com>
---
 arch/arm64/kernel/topology.c  | 26 +++++++++++++-------------
 drivers/base/arch_topology.c  | 12 +++++++++++-
 include/linux/arch_topology.h |  1 +
 3 files changed, 25 insertions(+), 14 deletions(-)

Comments

Beata Michalska Nov. 14, 2023, 1:06 p.m. UTC | #1 
On Thu, Nov 09, 2023 at 11:14:38AM +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>
> Acked-by: Sudeep Holla <sudeep.holla@arm.com>
> ---
>  arch/arm64/kernel/topology.c  | 26 +++++++++++++-------------
>  drivers/base/arch_topology.c  | 12 +++++++++++-
>  include/linux/arch_topology.h |  1 +
>  3 files changed, 25 insertions(+), 14 deletions(-)
> 
> diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> index 817d788cd866..1a2c72f3e7f8 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 +144,10 @@ 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;
> -
> -	return 0;
> +	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
>  }
>  
>  static void amu_scale_freq_tick(void)
> @@ -195,10 +198,7 @@ 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);
> +	}
Just wondering if this is really necessary as freq_inv_set_max_ratio will
originally be called upon cpufreq notification being triggered (with
CPUFREQ_CREATE_POLICY event) which should happen after the newly introduced
capacity_freq_ref gets properly set up, so wouldn't the change of flipping
cpufreq_get_hw_max_freq(cpu) to capacity_freq_ref do just fine ?
Then pushing AMU specific call to generic arch code  would not be necessary.
Or did I miss smth on the way ?

---
BR
B.

>  
>  	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_ */
> -- 
> 2.34.1
>
Beata Michalska Nov. 15, 2023, 9:42 a.m. UTC | #2 
On Tue, Nov 14, 2023 at 02:07:01PM +0100, Beata Michalska wrote:
> On Thu, Nov 09, 2023 at 11:14:38AM +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>
> > Acked-by: Sudeep Holla <sudeep.holla@arm.com>
> > ---
> >  arch/arm64/kernel/topology.c  | 26 +++++++++++++-------------
> >  drivers/base/arch_topology.c  | 12 +++++++++++-
> >  include/linux/arch_topology.h |  1 +
> >  3 files changed, 25 insertions(+), 14 deletions(-)
> > 
> > diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
> > index 817d788cd866..1a2c72f3e7f8 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 +144,10 @@ 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;
> > -
> > -	return 0;
> > +	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
> >  }
> >  
> >  static void amu_scale_freq_tick(void)
> > @@ -195,10 +198,7 @@ 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);
> > +	}
> Just wondering if this is really necessary as freq_inv_set_max_ratio will
> originally be called upon cpufreq notification being triggered (with
> CPUFREQ_CREATE_POLICY event) which should happen after the newly introduced
> capacity_freq_ref gets properly set up, so wouldn't the change of flipping
> cpufreq_get_hw_max_freq(cpu) to capacity_freq_ref do just fine ?
> Then pushing AMU specific call to generic arch code  would not be necessary.
> Or did I miss smth on the way ?
> 
I guess you can ignore my comment as init_cpu_capacity_callback (where we now
set the capacity_freq_ref) works on the same basis so there is no guarantee it
will be triggered before AMU callback.
Still having the freq_inv_set_max_ratio sitting in arch_topology.c somehow
doesn't sit well with me. We could potentially check capacity_freq_ref against
its init value and act accordingly but that is gruesome as well.

> ---
> BR
> B.
> 
> >  
> >  	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_ */
> > -- 
> > 2.34.1
> >
Will Deacon Nov. 21, 2023, 3:43 p.m. UTC | #3 
On Thu, Nov 09, 2023 at 11:14:38AM +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>
> Acked-by: Sudeep Holla <sudeep.holla@arm.com>
> ---
>  arch/arm64/kernel/topology.c  | 26 +++++++++++++-------------
>  drivers/base/arch_topology.c  | 12 +++++++++++-
>  include/linux/arch_topology.h |  1 +
>  3 files changed, 25 insertions(+), 14 deletions(-)

Acked-by: Will Deacon <will@kernel.org>

Will
diff mbox series

Patch

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 817d788cd866..1a2c72f3e7f8 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 +144,10 @@  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;
-
-	return 0;
+	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
 }
 
 static void amu_scale_freq_tick(void)
@@ -195,10 +198,7 @@  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_ */