Merge: update cpufreq to v6.0

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/1478

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=2122311

Commits for Tegra and other less supported platforms were applied out of order,
to make it easier to remove them. The large number of commits for Qualcomm and
MediaTek were not applied at all.

Signed-off-by: Mark Langsdorf <mlangsdo@redhat.com>

Approved-by: David Arcari <darcari@redhat.com>
Approved-by: Prarit Bhargava <prarit@redhat.com>
Approved-by: David Airlie <airlied@redhat.com>

Signed-off-by: Herton R. Krzesinski <herton@redhat.com>

Author: Herton R. Krzesinski

Documentation/power/energy-model.rst

@@ -129,6 +129,10 @@ More details about the above APIs can be found in include/linux/energy_model.h.
 3. Example driver
 -----------------
 
+The CPUFreq framework supports dedicated callback for registering
+the EM for a given CPU(s) 'policy' object: cpufreq_driver::register_em().
+That callback has to be implemented properly for a given driver,
+because the framework would call it at the right time during setup.
 This section provides a simple example of a CPUFreq driver registering a
 performance domain in the Energy Model framework using the (fake) 'foo'
 protocol. The driver implements an est_power() function to be provided to the
@@ -158,25 +162,22 @@ EM framework::
   20		return 0;
   21	}
   22
-  23	static int foo_cpufreq_init(struct cpufreq_policy *policy)
+  23	static void foo_cpufreq_register_em(struct cpufreq_policy *policy)
   24	{
   25		struct em_data_callback em_cb = EM_DATA_CB(est_power);
   26		struct device *cpu_dev;
-  27		int nr_opp, ret;
+  27		int nr_opp;
   28
   29		cpu_dev = get_cpu_device(cpumask_first(policy->cpus));
   30
-  31     	/* Do the actual CPUFreq init work ... */
-  32     	ret = do_foo_cpufreq_init(policy);
-  33     	if (ret)
-  34     		return ret;
-  35
-  36     	/* Find the number of OPPs for this policy */
-  37     	nr_opp = foo_get_nr_opp(policy);
+  31     	/* Find the number of OPPs for this policy */
+  32     	nr_opp = foo_get_nr_opp(policy);
+  33
+  34     	/* And register the new performance domain */
+  35     	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
+  36					    true);
+  37	}
   38
-  39     	/* And register the new performance domain */
-  40     	em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb, policy->cpus,
-  41					    true);
-  42
-  43	        return 0;
-  44	}
+  39	static struct cpufreq_driver foo_cpufreq_driver = {
+  40		.register_em = foo_cpufreq_register_em,
+  41	};

arch/arm64/kernel/smp.c

@@ -539,6 +539,7 @@ struct acpi_madt_generic_interrupt *acpi_cpu_get_madt_gicc(int cpu)
 {
 	return &cpu_madt_gicc[cpu];
 }
+EXPORT_SYMBOL_GPL(acpi_cpu_get_madt_gicc);
 
 /*
  * acpi_map_gic_cpu_interface - parse processor MADT entry

drivers/base/arch_topology.c

@@ -151,6 +151,7 @@ void topology_set_freq_scale(const struct cpumask *cpus, unsigned long cur_freq,
 }
 
 DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+EXPORT_PER_CPU_SYMBOL_GPL(cpu_scale);
 
 void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity)
 {

drivers/cpufreq/acpi-cpufreq.c

@@ -78,6 +78,8 @@ static bool boost_state(unsigned int cpu)
 
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_INTEL:
+	case X86_VENDOR_CENTAUR:
+	case X86_VENDOR_ZHAOXIN:
 		rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi);
 		msr = lo | ((u64)hi << 32);
 		return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
@@ -97,6 +99,8 @@ static int boost_set_msr(bool enable)
 
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_INTEL:
+	case X86_VENDOR_CENTAUR:
+	case X86_VENDOR_ZHAOXIN:
 		msr_addr = MSR_IA32_MISC_ENABLE;
 		msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
 		break;

drivers/cpufreq/cppc_cpufreq.c

@@ -61,6 +61,8 @@ static struct cppc_workaround_oem_info wa_info[] = {
 	}
 };
 
+static struct cpufreq_driver cppc_cpufreq_driver;
+
 #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
 
 /* Frequency invariance support */
@@ -75,7 +77,6 @@ struct cppc_freq_invariance {
 static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
 static struct kthread_worker *kworker_fie;
 
-static struct cpufreq_driver cppc_cpufreq_driver;
 static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
 static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
@@ -440,15 +441,199 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 	}
 	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
 }
-
 #else
-
 static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 {
 	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
 }
 #endif
 
+#if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL)
+
+static DEFINE_PER_CPU(unsigned int, efficiency_class);
+static void cppc_cpufreq_register_em(struct cpufreq_policy *policy);
+
+/* Create an artificial performance state every CPPC_EM_CAP_STEP capacity unit. */
+#define CPPC_EM_CAP_STEP	(20)
+/* Increase the cost value by CPPC_EM_COST_STEP every performance state. */
+#define CPPC_EM_COST_STEP	(1)
+/* Add a cost gap correspnding to the energy of 4 CPUs. */
+#define CPPC_EM_COST_GAP	(4 * SCHED_CAPACITY_SCALE * CPPC_EM_COST_STEP \
+				/ CPPC_EM_CAP_STEP)
+
+static unsigned int get_perf_level_count(struct cpufreq_policy *policy)
+{
+	struct cppc_perf_caps *perf_caps;
+	unsigned int min_cap, max_cap;
+	struct cppc_cpudata *cpu_data;
+	int cpu = policy->cpu;
+
+	cpu_data = policy->driver_data;
+	perf_caps = &cpu_data->perf_caps;
+	max_cap = arch_scale_cpu_capacity(cpu);
+	min_cap = div_u64(max_cap * perf_caps->lowest_perf, perf_caps->highest_perf);
+	if ((min_cap == 0) || (max_cap < min_cap))
+		return 0;
+	return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;
+}
+
+/*
+ * The cost is defined as:
+ *   cost = power * max_frequency / frequency
+ */
+static inline unsigned long compute_cost(int cpu, int step)
+{
+	return CPPC_EM_COST_GAP * per_cpu(efficiency_class, cpu) +
+			step * CPPC_EM_COST_STEP;
+}
+
+static int cppc_get_cpu_power(struct device *cpu_dev,
+		unsigned long *power, unsigned long *KHz)
+{
+	unsigned long perf_step, perf_prev, perf, perf_check;
+	unsigned int min_step, max_step, step, step_check;
+	unsigned long prev_freq = *KHz;
+	unsigned int min_cap, max_cap;
+	struct cpufreq_policy *policy;
+
+	struct cppc_perf_caps *perf_caps;
+	struct cppc_cpudata *cpu_data;
+
+	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	cpu_data = policy->driver_data;
+	perf_caps = &cpu_data->perf_caps;
+	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
+	min_cap = div_u64(max_cap * perf_caps->lowest_perf,
+			perf_caps->highest_perf);
+
+	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+	min_step = min_cap / CPPC_EM_CAP_STEP;
+	max_step = max_cap / CPPC_EM_CAP_STEP;
+
+	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	step = perf_prev / perf_step;
+
+	if (step > max_step)
+		return -EINVAL;
+
+	if (min_step == max_step) {
+		step = max_step;
+		perf = perf_caps->highest_perf;
+	} else if (step < min_step) {
+		step = min_step;
+		perf = perf_caps->lowest_perf;
+	} else {
+		step++;
+		if (step == max_step)
+			perf = perf_caps->highest_perf;
+		else
+			perf = step * perf_step;
+	}
+
+	*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
+	perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+	step_check = perf_check / perf_step;
+
+	/*
+	 * To avoid bad integer approximation, check that new frequency value
+	 * increased and that the new frequency will be converted to the
+	 * desired step value.
+	 */
+	while ((*KHz == prev_freq) || (step_check != step)) {
+		perf++;
+		*KHz = cppc_cpufreq_perf_to_khz(cpu_data, perf);
+		perf_check = cppc_cpufreq_khz_to_perf(cpu_data, *KHz);
+		step_check = perf_check / perf_step;
+	}
+
+	/*
+	 * With an artificial EM, only the cost value is used. Still the power
+	 * is populated such as 0 < power < EM_MAX_POWER. This allows to add
+	 * more sense to the artificial performance states.
+	 */
+	*power = compute_cost(cpu_dev->id, step);
+
+	return 0;
+}
+
+static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz,
+		unsigned long *cost)
+{
+	unsigned long perf_step, perf_prev;
+	struct cppc_perf_caps *perf_caps;
+	struct cpufreq_policy *policy;
+	struct cppc_cpudata *cpu_data;
+	unsigned int max_cap;
+	int step;
+
+	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	cpu_data = policy->driver_data;
+	perf_caps = &cpu_data->perf_caps;
+	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
+
+	perf_prev = cppc_cpufreq_khz_to_perf(cpu_data, KHz);
+	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+	step = perf_prev / perf_step;
+
+	*cost = compute_cost(cpu_dev->id, step);
+
+	return 0;
+}
+
+static int populate_efficiency_class(void)
+{
+	struct acpi_madt_generic_interrupt *gicc;
+	DECLARE_BITMAP(used_classes, 256) = {};
+	int class, cpu, index;
+
+	for_each_possible_cpu(cpu) {
+		gicc = acpi_cpu_get_madt_gicc(cpu);
+		class = gicc->efficiency_class;
+		bitmap_set(used_classes, class, 1);
+	}
+
+	if (bitmap_weight(used_classes, 256) <= 1) {
+		pr_debug("Efficiency classes are all equal (=%d). "
+			"No EM registered", class);
+		return -EINVAL;
+	}
+
+	/*
+	 * Squeeze efficiency class values on [0:#efficiency_class-1].
+	 * Values are per spec in [0:255].
+	 */
+	index = 0;
+	for_each_set_bit(class, used_classes, 256) {
+		for_each_possible_cpu(cpu) {
+			gicc = acpi_cpu_get_madt_gicc(cpu);
+			if (gicc->efficiency_class == class)
+				per_cpu(efficiency_class, cpu) = index;
+		}
+		index++;
+	}
+	cppc_cpufreq_driver.register_em = cppc_cpufreq_register_em;
+
+	return 0;
+}
+
+static void cppc_cpufreq_register_em(struct cpufreq_policy *policy)
+{
+	struct cppc_cpudata *cpu_data;
+	struct em_data_callback em_cb =
+		EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost);
+
+	cpu_data = policy->driver_data;
+	em_dev_register_perf_domain(get_cpu_device(policy->cpu),
+			get_perf_level_count(policy), &em_cb,
+			cpu_data->shared_cpu_map, 0);
+}
+
+#else
+static int populate_efficiency_class(void)
+{
+	return 0;
+}
+#endif
 
 static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 {
@@ -558,6 +743,7 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	policy->fast_switch_possible = cppc_allow_fast_switch();
+	policy->dvfs_possible_from_any_cpu = true;
 
 	/*
 	 * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost
@@ -766,6 +952,7 @@ static int __init cppc_cpufreq_init(void)
 
 	cppc_check_hisi_workaround();
 	cppc_freq_invariance_init();
+	populate_efficiency_class();
 
 	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
 	if (ret)

drivers/cpufreq/cpufreq-dt.c

@@ -29,9 +29,9 @@ struct private_data {
 
 	cpumask_var_t cpus;
 	struct device *cpu_dev;
-	struct opp_table *opp_table;
 	struct cpufreq_frequency_table *freq_table;
 	bool have_static_opps;
+	int opp_token;
 };
 
 static LIST_HEAD(priv_list);
@@ -194,7 +194,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 	struct private_data *priv;
 	struct device *cpu_dev;
 	bool fallback = false;
-	const char *reg_name;
+	const char *reg_name[] = { NULL, NULL };
 	int ret;
 
 	/* Check if this CPU is already covered by some other policy */
@@ -219,12 +219,11 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 	 * OPP layer will be taking care of regulators now, but it needs to know
 	 * the name of the regulator first.
 	 */
-	reg_name = find_supply_name(cpu_dev);
-	if (reg_name) {
-		priv->opp_table = dev_pm_opp_set_regulators(cpu_dev, &reg_name,
-							    1);
-		if (IS_ERR(priv->opp_table)) {
-			ret = PTR_ERR(priv->opp_table);
+	reg_name[0] = find_supply_name(cpu_dev);
+	if (reg_name[0]) {
+		priv->opp_token = dev_pm_opp_set_regulators(cpu_dev, reg_name);
+		if (priv->opp_token < 0) {
+			ret = priv->opp_token;
 			if (ret != -EPROBE_DEFER)
 				dev_err(cpu_dev, "failed to set regulators: %d\n",
 					ret);
@@ -296,7 +295,7 @@ static int dt_cpufreq_early_init(struct device *dev, int cpu)
 out:
 	if (priv->have_static_opps)
 		dev_pm_opp_of_cpumask_remove_table(priv->cpus);
-	dev_pm_opp_put_regulators(priv->opp_table);
+	dev_pm_opp_put_regulators(priv->opp_token);
 free_cpumask:
 	free_cpumask_var(priv->cpus);
 	return ret;
@@ -310,7 +309,7 @@ static void dt_cpufreq_release(void)
 		dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &priv->freq_table);
 		if (priv->have_static_opps)
 			dev_pm_opp_of_cpumask_remove_table(priv->cpus);
-		dev_pm_opp_put_regulators(priv->opp_table);
+		dev_pm_opp_put_regulators(priv->opp_token);
 		free_cpumask_var(priv->cpus);
 		list_del(&priv->node);
 	}