Merge back cpufreq material for 5.10.

arch/arm/include/asm/topology.h

@@ -9,6 +9,7 @@
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale

arch/arm64/include/asm/topology.h

@@ -27,6 +27,7 @@ void topology_scale_freq_tick(void);
 
 /* Replace task scheduler's default frequency-invariant accounting */
 #define arch_scale_freq_capacity topology_get_freq_scale
+#define arch_scale_freq_invariant topology_scale_freq_invariant
 
 /* Replace task scheduler's default cpu-invariant accounting */
 #define arch_scale_cpu_capacity topology_get_cpu_scale

arch/arm64/kernel/topology.c

@@ -246,6 +246,13 @@ static int __init init_amu_fie(void)
 		static_branch_enable(&amu_fie_key);
 	}
 
+	/*
+	 * If the system is not fully invariant after AMU init, disable
+	 * partial use of counters for frequency invariance.
+	 */
+	if (!topology_scale_freq_invariant())
+		static_branch_disable(&amu_fie_key);
+
 free_valid_mask:
 	free_cpumask_var(valid_cpus);
 
@@ -253,7 +260,7 @@ static int __init init_amu_fie(void)
 }
 late_initcall_sync(init_amu_fie);
 
-bool arch_freq_counters_available(struct cpumask *cpus)
+bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return amu_freq_invariant() &&
 	       cpumask_subset(cpus, amu_fie_cpus);

drivers/base/arch_topology.c

@@ -21,18 +21,27 @@
 #include <linux/sched.h>
 #include <linux/smp.h>
 
-__weak bool arch_freq_counters_available(struct cpumask *cpus)
+bool topology_scale_freq_invariant(void)
+{
+	return cpufreq_supports_freq_invariance() ||
+	       arch_freq_counters_available(cpu_online_mask);
+}
+
+__weak bool arch_freq_counters_available(const struct cpumask *cpus)
 {
 	return false;
 }
 DEFINE_PER_CPU(unsigned long, freq_scale) = SCHED_CAPACITY_SCALE;
 
-void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
+void arch_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 			 unsigned long max_freq)
 {
 	unsigned long scale;
 	int i;
 
+	if (WARN_ON_ONCE(!cur_freq || !max_freq))
+		return;
+
 	/*
 	 * If the use of counters for FIE is enabled, just return as we don't
 	 * want to update the scale factor with information from CPUFREQ.

drivers/cpufreq/cpufreq-dt.c

@@ -40,16 +40,8 @@ static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct private_data *priv = policy->driver_data;
 	unsigned long freq = policy->freq_table[index].frequency;
-	int ret;
-
-	ret = dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000);
 
-	if (!ret) {
-		arch_set_freq_scale(policy->related_cpus, freq,
-				    policy->cpuinfo.max_freq);
-	}
-
-	return ret;
+	return dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000);
 }
 
 /*

drivers/cpufreq/cpufreq.c

@@ -61,6 +61,12 @@ static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 
+static DEFINE_STATIC_KEY_FALSE(cpufreq_freq_invariance);
+bool cpufreq_supports_freq_invariance(void)
+{
+	return static_branch_likely(&cpufreq_freq_invariance);
+}
+
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -154,8 +160,9 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-__weak void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
-		unsigned long max_freq)
+__weak void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
+				unsigned long max_freq)
 {
 }
 EXPORT_SYMBOL_GPL(arch_set_freq_scale);
@@ -446,6 +453,10 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 
 	cpufreq_notify_post_transition(policy, freqs, transition_failed);
 
+	arch_set_freq_scale(policy->related_cpus,
+			    policy->cur,
+			    policy->cpuinfo.max_freq);
+
 	policy->transition_ongoing = false;
 	policy->transition_task = NULL;
 
@@ -2056,9 +2067,15 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq)
 {
+	unsigned int freq;
+
 	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	freq = cpufreq_driver->fast_switch(policy, target_freq);
 
-	return cpufreq_driver->fast_switch(policy, target_freq);
+	arch_set_freq_scale(policy->related_cpus, freq,
+			    policy->cpuinfo.max_freq);
+
+	return freq;
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 
@@ -2710,6 +2727,15 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	/*
+	 * Mark support for the scheduler's frequency invariance engine for
+	 * drivers that implement target(), target_index() or fast_switch().
+	 */
+	if (!cpufreq_driver->setpolicy) {
+		static_branch_enable_cpuslocked(&cpufreq_freq_invariance);
+		pr_debug("supports frequency invariance");
+	}
+
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
@@ -2779,6 +2805,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	cpus_read_lock();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
+	static_branch_disable_cpuslocked(&cpufreq_freq_invariance);
 	cpuhp_remove_state_nocalls_cpuslocked(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);

drivers/cpufreq/qcom-cpufreq-hw.c

@@ -85,8 +85,6 @@ static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
 	if (icc_scaling_enabled)
 		qcom_cpufreq_set_bw(policy, freq);
 
-	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
 	return 0;
 }
 
@@ -113,16 +111,11 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 {
 	void __iomem *perf_state_reg = policy->driver_data;
 	unsigned int index;
-	unsigned long freq;
 
 	index = policy->cached_resolved_idx;
 	writel_relaxed(index, perf_state_reg);
 
-	freq = policy->freq_table[index].frequency;
-	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
-
-	return freq;
+	return policy->freq_table[index].frequency;
 }
 
 static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,

drivers/cpufreq/scmi-cpufreq.c

@@ -48,16 +48,11 @@ static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 static int
 scmi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	int ret;
 	struct scmi_data *priv = policy->driver_data;
 	struct scmi_perf_ops *perf_ops = handle->perf_ops;
 	u64 freq = policy->freq_table[index].frequency;
 
-	ret = perf_ops->freq_set(handle, priv->domain_id, freq * 1000, false);
-	if (!ret)
-		arch_set_freq_scale(policy->related_cpus, freq,
-				    policy->cpuinfo.max_freq);
-	return ret;
+	return perf_ops->freq_set(handle, priv->domain_id, freq * 1000, false);
 }
 
 static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy,
@@ -67,11 +62,8 @@ static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	struct scmi_perf_ops *perf_ops = handle->perf_ops;
 
 	if (!perf_ops->freq_set(handle, priv->domain_id,
-				target_freq * 1000, true)) {
-		arch_set_freq_scale(policy->related_cpus, target_freq,
-				    policy->cpuinfo.max_freq);
+				target_freq * 1000, true))
 		return target_freq;
-	}
 
 	return 0;
 }

drivers/cpufreq/scpi-cpufreq.c

@@ -47,9 +47,8 @@ static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
 static int
 scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned long freq = policy->freq_table[index].frequency;
+	u64 rate = policy->freq_table[index].frequency * 1000;
 	struct scpi_data *priv = policy->driver_data;
-	u64 rate = freq * 1000;
 	int ret;
 
 	ret = clk_set_rate(priv->clk, rate);
@@ -60,9 +59,6 @@ scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 	if (clk_get_rate(priv->clk) != rate)
 		return -EIO;
 
-	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
-
 	return 0;
 }
 

drivers/cpufreq/vexpress-spc-cpufreq.c

@@ -182,7 +182,6 @@ static int ve_spc_cpufreq_set_target(struct cpufreq_policy *policy,
 {
 	u32 cpu = policy->cpu, cur_cluster, new_cluster, actual_cluster;
 	unsigned int freqs_new;
-	int ret;
 
 	cur_cluster = cpu_to_cluster(cpu);
 	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
@@ -197,15 +196,8 @@ static int ve_spc_cpufreq_set_target(struct cpufreq_policy *policy,
 			new_cluster = A15_CLUSTER;
 	}
 
-	ret = ve_spc_cpufreq_set_rate(cpu, actual_cluster, new_cluster,
-				      freqs_new);
-
-	if (!ret) {
-		arch_set_freq_scale(policy->related_cpus, freqs_new,
-				    policy->cpuinfo.max_freq);
-	}
-
-	return ret;
+	return ve_spc_cpufreq_set_rate(cpu, actual_cluster, new_cluster,
+				       freqs_new);
 }
 
 static inline u32 get_table_count(struct cpufreq_frequency_table *table)

include/linux/arch_topology.h

@@ -30,7 +30,9 @@ static inline unsigned long topology_get_freq_scale(int cpu)
 	return per_cpu(freq_scale, cpu);
 }
 
-bool arch_freq_counters_available(struct cpumask *cpus);
+bool topology_scale_freq_invariant(void);
+
+bool arch_freq_counters_available(const struct cpumask *cpus);
 
 DECLARE_PER_CPU(unsigned long, thermal_pressure);
 

include/linux/cpufreq.h

@@ -217,6 +217,7 @@ void refresh_frequency_limits(struct cpufreq_policy *policy);
 void cpufreq_update_policy(unsigned int cpu);
 void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
+bool cpufreq_supports_freq_invariance(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
 void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
@@ -237,6 +238,10 @@ static inline unsigned int cpufreq_get_hw_max_freq(unsigned int cpu)
 {
 	return 0;
 }
+static inline bool cpufreq_supports_freq_invariance(void)
+{
+	return false;
+}
 static inline void disable_cpufreq(void) { }
 #endif
 
@@ -1006,7 +1011,8 @@ static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
 extern void arch_freq_prepare_all(void);
 extern unsigned int arch_freq_get_on_cpu(int cpu);
 
-extern void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
+extern void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
 				unsigned long max_freq);
 
 /* the following are really really optional */