[RFC v3 6/6] arm64/amu: use capacity_ref_freq to set AMU ratio

[Vincent Guittot]

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 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@xxxxxxxxxx>
---
 arch/arm64/kernel/topology.c  | 18 ++++++++++--------
 drivers/base/arch_topology.c  | 14 ++++++++++++--
 include/linux/arch_topology.h |  1 +
 3 files changed, 23 insertions(+), 10 deletions(-)

diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 817d788cd866..0f8f6e90c46d 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_SHIFT until
+ * the CPU capacity and its assosciated frequency have been correctly
+ * initialized.
+ */
+static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, arch_max_freq_scale) = (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;
@@ -112,9 +117,9 @@ 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)
+int 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",
@@ -142,7 +147,7 @@ static int freq_inv_set_max_ratio(int cpu, u64 max_rate, u64 ref_rate)
 		return -EINVAL;
 	}
 
-	per_cpu(arch_max_freq_scale, cpu) = (unsigned long)ratio;
+	WRITE_ONCE(per_cpu(arch_max_freq_scale, cpu), (unsigned long)ratio);
 
 	return 0;
 }
@@ -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 2372ce791bb4..3a604b77b12d 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -344,6 +344,11 @@ bool __init topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu)
 	return !ret;
 }
 
+int __weak freq_inv_set_max_ratio(int cpu, u64 max_rate)
+{
+	return 0;
+}
+
 #ifdef CONFIG_ACPI_CPPC_LIB
 #include <acpi/cppc_acpi.h>
 
@@ -369,7 +374,6 @@ void topology_init_cpu_capacity_cppc(void)
 			capacity_scale = max_t(u64, capacity_scale, raw_capacity[cpu]);
 
 			per_cpu(capacity_ref_freq, cpu) = cppc_perf_to_khz(&perf_caps, raw_capacity[cpu]);
-
 			pr_debug("cpu_capacity: CPU%d cpu_capacity=%u (raw).\n",
 				 cpu, raw_capacity[cpu]);
 			continue;
@@ -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_ref_freq, cpu));
+
 		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_ref_freq, cpu) = policy->cpuinfo.max_freq;
+		freq_inv_set_max_ratio(cpu,
+				       per_cpu(capacity_ref_freq, cpu));
+	}
 
 	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 38ca6c76af56..b6e95d763279 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);
+int freq_inv_set_max_ratio(int cpu, u64 max_rate);
 #endif
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
-- 
2.34.1