Merge branch 'opp/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm into pm-opp

Pull operating performance points (OPP) framework updates for v5.1
from Viresh Kumar:

"This pull request contains following changes:

- Introduced new OPP helper for power-estimation and used it in
several cpufreq drivers (Quentin Perret, Matthias Kaehlcke, Dietmar
Eggemann, and Yangtao Li).

- OPP Debugfs cleanup (Greg KH).

- OPP core cleanup (Viresh Kumar)."

* 'opp/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
cpufreq: OMAP: Register an Energy Model
cpufreq: imx6q: Register an Energy Model
opp: no need to check return value of debugfs_create functions
cpufreq: mediatek: Register an Energy Model
cpufreq: scmi: Register an Energy Model
cpufreq: arm_big_little: Register an Energy Model
cpufreq: scpi: Register an Energy Model
cpufreq: dt: Register an Energy Model
PM / OPP: Introduce a power estimation helper
PM / OPP: Remove unused parameter of _generic_set_opp_clk_only()

drivers/cpufreq/arm_big_little.c

···
 	policy->cpuinfo.transition_latency =
 				arm_bL_ops->get_transition_latency(cpu_dev);
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	if (is_bL_switching_enabled())
 		per_cpu(cpu_last_req_freq, policy->cpu) = clk_get_cpu_rate(policy->cpu);
 

drivers/cpufreq/cpufreq-dt.c

···
 	policy->cpuinfo.transition_latency = transition_latency;
 	policy->dvfs_possible_from_any_cpu = true;
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	return 0;
 
 out_free_cpufreq_table:

drivers/cpufreq/imx6q-cpufreq.c

···
 	policy->clk = clks[ARM].clk;
 	ret = cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = max_freq;
+	dev_pm_opp_of_register_em(policy->cpus);
 
 	return ret;
 }

drivers/cpufreq/mediatek-cpufreq.c

···
 	policy->driver_data = info;
 	policy->clk = info->cpu_clk;
 
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	return 0;
 }
 

drivers/cpufreq/omap-cpufreq.c

···
 
 	/* FIXME: what's the actual transition time? */
 	result = cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	if (!result)
+	if (!result) {
+		dev_pm_opp_of_register_em(policy->cpus);
 		return 0;
+	}
 
 	freq_table_free();
 fail:

drivers/cpufreq/scmi-cpufreq.c

···
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
 #include <linux/cpu_cooling.h>
+#include <linux/energy_model.h>
 #include <linux/export.h>
 #include <linux/module.h>
 #include <linux/pm_opp.h>
···
 	return 0;
 }
 
+static int __maybe_unused
+scmi_get_cpu_power(unsigned long *power, unsigned long *KHz, int cpu)
+{
+	struct device *cpu_dev = get_cpu_device(cpu);
+	unsigned long Hz;
+	int ret, domain;
+
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", cpu);
+		return -ENODEV;
+	}
+
+	domain = handle->perf_ops->device_domain_id(cpu_dev);
+	if (domain < 0)
+		return domain;
+
+	/* Get the power cost of the performance domain. */
+	Hz = *KHz * 1000;
+	ret = handle->perf_ops->est_power_get(handle, domain, &Hz, power);
+	if (ret)
+		return ret;
+
+	/* The EM framework specifies the frequency in KHz. */
+	*KHz = Hz / 1000;
+
+	return 0;
+}
+
 static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 {
-	int ret;
+	int ret, nr_opp;
 	unsigned int latency;
 	struct device *cpu_dev;
 	struct scmi_data *priv;
 	struct cpufreq_frequency_table *freq_table;
+	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
···
 		return ret;
 	}
 
-	ret = dev_pm_opp_get_opp_count(cpu_dev);
-	if (ret <= 0) {
+	nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+	if (nr_opp <= 0) {
 		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
 		ret = -EPROBE_DEFER;
 		goto out_free_opp;
···
 	policy->cpuinfo.transition_latency = latency;
 
 	policy->fast_switch_possible = true;
+
+	em_register_perf_domain(policy->cpus, nr_opp, &em_cb);
+
 	return 0;
 
 out_free_priv:

drivers/cpufreq/scpi-cpufreq.c

···
 	policy->cpuinfo.transition_latency = latency;
 
 	policy->fast_switch_possible = false;
+
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	return 0;
 
 out_free_cpufreq_table:

drivers/opp/core.c

···
 	return ret;
 }
 
-static inline int
-_generic_set_opp_clk_only(struct device *dev, struct clk *clk,
-			  unsigned long old_freq, unsigned long freq)
+static inline int _generic_set_opp_clk_only(struct device *dev, struct clk *clk,
+					    unsigned long freq)
 {
 	int ret;
 
···
 	}
 
 	/* Change frequency */
-	ret = _generic_set_opp_clk_only(dev, opp_table->clk, old_freq, freq);
+	ret = _generic_set_opp_clk_only(dev, opp_table->clk, freq);
 	if (ret)
 		goto restore_voltage;
 
···
 	return 0;
 
 restore_freq:
-	if (_generic_set_opp_clk_only(dev, opp_table->clk, freq, old_freq))
+	if (_generic_set_opp_clk_only(dev, opp_table->clk, old_freq))
 		dev_err(dev, "%s: failed to restore old-freq (%lu Hz)\n",
 			__func__, old_freq);
 restore_voltage:
···
 						 opp->supplies);
 	} else {
 		/* Only frequency scaling */
-		ret = _generic_set_opp_clk_only(dev, clk, old_freq, freq);
+		ret = _generic_set_opp_clk_only(dev, clk, freq);
 	}
 
 	/* Scaling down? Configure required OPPs after frequency */
···
 						struct opp_table *opp_table)
 {
 	struct opp_device *opp_dev;
-	int ret;
 
 	opp_dev = kzalloc(sizeof(*opp_dev), GFP_KERNEL);
 	if (!opp_dev)
···
 	list_add(&opp_dev->node, &opp_table->dev_list);
 
 	/* Create debugfs entries for the opp_table */
-	ret = opp_debug_register(opp_dev, opp_table);
-	if (ret)
-		dev_err(dev, "%s: Failed to register opp debugfs (%d)\n",
-			__func__, ret);
+	opp_debug_register(opp_dev, opp_table);
 
 	return opp_dev;
 }
···
 	new_opp->opp_table = opp_table;
 	kref_init(&new_opp->kref);
 
-	ret = opp_debug_create_one(new_opp, opp_table);
-	if (ret)
-		dev_err(dev, "%s: Failed to register opp to debugfs (%d)\n",
-			__func__, ret);
+	opp_debug_create_one(new_opp, opp_table);
 
 	if (!_opp_supported_by_regulators(new_opp, opp_table)) {
 		new_opp->available = false;

drivers/opp/debugfs.c

···
 	debugfs_remove_recursive(opp->dentry);
 }
 
-static bool opp_debug_create_supplies(struct dev_pm_opp *opp,
+static void opp_debug_create_supplies(struct dev_pm_opp *opp,
 				      struct opp_table *opp_table,
 				      struct dentry *pdentry)
 {
···
 		/* Create per-opp directory */
 		d = debugfs_create_dir(name, pdentry);
 
-		if (!d)
-			return false;
+		debugfs_create_ulong("u_volt_target", S_IRUGO, d,
+				     &opp->supplies[i].u_volt);
 
-		if (!debugfs_create_ulong("u_volt_target", S_IRUGO, d,
-					  &opp->supplies[i].u_volt))
-			return false;
+		debugfs_create_ulong("u_volt_min", S_IRUGO, d,
+				     &opp->supplies[i].u_volt_min);
 
-		if (!debugfs_create_ulong("u_volt_min", S_IRUGO, d,
-					  &opp->supplies[i].u_volt_min))
-			return false;
+		debugfs_create_ulong("u_volt_max", S_IRUGO, d,
+				     &opp->supplies[i].u_volt_max);
 
-		if (!debugfs_create_ulong("u_volt_max", S_IRUGO, d,
-					  &opp->supplies[i].u_volt_max))
-			return false;
-
-		if (!debugfs_create_ulong("u_amp", S_IRUGO, d,
-					  &opp->supplies[i].u_amp))
-			return false;
+		debugfs_create_ulong("u_amp", S_IRUGO, d,
+				     &opp->supplies[i].u_amp);
 	}
-
-	return true;
 }
 
-int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
+void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 {
 	struct dentry *pdentry = opp_table->dentry;
 	struct dentry *d;
···
 
 	/* Create per-opp directory */
 	d = debugfs_create_dir(name, pdentry);
-	if (!d)
-		return -ENOMEM;
 
-	if (!debugfs_create_bool("available", S_IRUGO, d, &opp->available))
-		return -ENOMEM;
+	debugfs_create_bool("available", S_IRUGO, d, &opp->available);
+	debugfs_create_bool("dynamic", S_IRUGO, d, &opp->dynamic);
+	debugfs_create_bool("turbo", S_IRUGO, d, &opp->turbo);
+	debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend);
+	debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate);
+	debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate);
+	debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
+			     &opp->clock_latency_ns);
 
-	if (!debugfs_create_bool("dynamic", S_IRUGO, d, &opp->dynamic))
-		return -ENOMEM;
-
-	if (!debugfs_create_bool("turbo", S_IRUGO, d, &opp->turbo))
-		return -ENOMEM;
-
-	if (!debugfs_create_bool("suspend", S_IRUGO, d, &opp->suspend))
-		return -ENOMEM;
-
-	if (!debugfs_create_u32("performance_state", S_IRUGO, d, &opp->pstate))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("rate_hz", S_IRUGO, d, &opp->rate))
-		return -ENOMEM;
-
-	if (!opp_debug_create_supplies(opp, opp_table, d))
-		return -ENOMEM;
-
-	if (!debugfs_create_ulong("clock_latency_ns", S_IRUGO, d,
-				  &opp->clock_latency_ns))
-		return -ENOMEM;
+	opp_debug_create_supplies(opp, opp_table, d);
 
 	opp->dentry = d;
-	return 0;
 }
 
-static int opp_list_debug_create_dir(struct opp_device *opp_dev,
-				     struct opp_table *opp_table)
+static void opp_list_debug_create_dir(struct opp_device *opp_dev,
+				      struct opp_table *opp_table)
 {
 	const struct device *dev = opp_dev->dev;
 	struct dentry *d;
···
 
 	/* Create device specific directory */
 	d = debugfs_create_dir(opp_table->dentry_name, rootdir);
-	if (!d) {
-		dev_err(dev, "%s: Failed to create debugfs dir\n", __func__);
-		return -ENOMEM;
-	}
 
 	opp_dev->dentry = d;
 	opp_table->dentry = d;
-
-	return 0;
 }
 
-static int opp_list_debug_create_link(struct opp_device *opp_dev,
-				      struct opp_table *opp_table)
+static void opp_list_debug_create_link(struct opp_device *opp_dev,
+				       struct opp_table *opp_table)
 {
-	const struct device *dev = opp_dev->dev;
 	char name[NAME_MAX];
-	struct dentry *d;
 
 	opp_set_dev_name(opp_dev->dev, name);
 
 	/* Create device specific directory link */
-	d = debugfs_create_symlink(name, rootdir, opp_table->dentry_name);
-	if (!d) {
-		dev_err(dev, "%s: Failed to create link\n", __func__);
-		return -ENOMEM;
-	}
-
-	opp_dev->dentry = d;
-
-	return 0;
+	opp_dev->dentry = debugfs_create_symlink(name, rootdir,
+						 opp_table->dentry_name);
 }
 
 /**
···
  * Dynamically adds device specific directory in debugfs 'opp' directory. If the
  * device-opp is shared with other devices, then links will be created for all
  * devices except the first.
- *
- * Return: 0 on success, otherwise negative error.
  */
-int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
+void opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table)
 {
-	if (!rootdir) {
-		pr_debug("%s: Uninitialized rootdir\n", __func__);
-		return -EINVAL;
-	}
-
 	if (opp_table->dentry)
-		return opp_list_debug_create_link(opp_dev, opp_table);
-
-	return opp_list_debug_create_dir(opp_dev, opp_table);
+		opp_list_debug_create_link(opp_dev, opp_table);
+	else
+		opp_list_debug_create_dir(opp_dev, opp_table);
 }
 
 static void opp_migrate_dentry(struct opp_device *opp_dev,
···
 {
 	/* Create /sys/kernel/debug/opp directory */
 	rootdir = debugfs_create_dir("opp", NULL);
-	if (!rootdir) {
-		pr_err("%s: Failed to create root directory\n", __func__);
-		return -ENOMEM;
-	}
 
 	return 0;
 }

drivers/opp/of.c

···
 #include <linux/pm_domain.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/energy_model.h>
 
 #include "opp.h"
 
···
 	return of_node_get(opp->np);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
+
+/*
+ * Callback function provided to the Energy Model framework upon registration.
+ * This computes the power estimated by @CPU at @kHz if it is the frequency
+ * of an existing OPP, or at the frequency of the first OPP above @kHz otherwise
+ * (see dev_pm_opp_find_freq_ceil()). This function updates @kHz to the ceiled
+ * frequency and @mW to the associated power. The power is estimated as
+ * P = C * V^2 * f with C being the CPU's capacitance and V and f respectively
+ * the voltage and frequency of the OPP.
+ *
+ * Returns -ENODEV if the CPU device cannot be found, -EINVAL if the power
+ * calculation failed because of missing parameters, 0 otherwise.
+ */
+static int __maybe_unused _get_cpu_power(unsigned long *mW, unsigned long *kHz,
+					 int cpu)
+{
+	struct device *cpu_dev;
+	struct dev_pm_opp *opp;
+	struct device_node *np;
+	unsigned long mV, Hz;
+	u32 cap;
+	u64 tmp;
+	int ret;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return -ENODEV;
+
+	np = of_node_get(cpu_dev->of_node);
+	if (!np)
+		return -EINVAL;
+
+	ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap);
+	of_node_put(np);
+	if (ret)
+		return -EINVAL;
+
+	Hz = *kHz * 1000;
+	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &Hz);
+	if (IS_ERR(opp))
+		return -EINVAL;
+
+	mV = dev_pm_opp_get_voltage(opp) / 1000;
+	dev_pm_opp_put(opp);
+	if (!mV)
+		return -EINVAL;
+
+	tmp = (u64)cap * mV * mV * (Hz / 1000000);
+	do_div(tmp, 1000000000);
+
+	*mW = (unsigned long)tmp;
+	*kHz = Hz / 1000;
+
+	return 0;
+}
+
+/**
+ * dev_pm_opp_of_register_em() - Attempt to register an Energy Model
+ * @cpus	: CPUs for which an Energy Model has to be registered
+ *
+ * This checks whether the "dynamic-power-coefficient" devicetree property has
+ * been specified, and tries to register an Energy Model with it if it has.
+ */
+void dev_pm_opp_of_register_em(struct cpumask *cpus)
+{
+	struct em_data_callback em_cb = EM_DATA_CB(_get_cpu_power);
+	int ret, nr_opp, cpu = cpumask_first(cpus);
+	struct device *cpu_dev;
+	struct device_node *np;
+	u32 cap;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev)
+		return;
+
+	nr_opp = dev_pm_opp_get_opp_count(cpu_dev);
+	if (nr_opp <= 0)
+		return;
+
+	np = of_node_get(cpu_dev->of_node);
+	if (!np)
+		return;
+
+	/*
+	 * Register an EM only if the 'dynamic-power-coefficient' property is
+	 * set in devicetree. It is assumed the voltage values are known if that
+	 * property is set since it is useless otherwise. If voltages are not
+	 * known, just let the EM registration fail with an error to alert the
+	 * user about the inconsistent configuration.
+	 */
+	ret = of_property_read_u32(np, "dynamic-power-coefficient", &cap);
+	of_node_put(np);
+	if (ret || !cap)
+		return;
+
+	em_register_perf_domain(cpus, nr_opp, &em_cb);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_register_em);

drivers/opp/opp.h

···
 
 #ifdef CONFIG_DEBUG_FS
 void opp_debug_remove_one(struct dev_pm_opp *opp);
-int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
-int opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
+void opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table);
+void opp_debug_register(struct opp_device *opp_dev, struct opp_table *opp_table);
 void opp_debug_unregister(struct opp_device *opp_dev, struct opp_table *opp_table);
 #else
 static inline void opp_debug_remove_one(struct dev_pm_opp *opp) {}
 
-static inline int opp_debug_create_one(struct dev_pm_opp *opp,
-				       struct opp_table *opp_table)
-{ return 0; }
-static inline int opp_debug_register(struct opp_device *opp_dev,
-				     struct opp_table *opp_table)
-{ return 0; }
+static inline void opp_debug_create_one(struct dev_pm_opp *opp,
+					struct opp_table *opp_table) { }
+
+static inline void opp_debug_register(struct opp_device *opp_dev,
+				      struct opp_table *opp_table) { }
 
 static inline void opp_debug_unregister(struct opp_device *opp_dev,
 					struct opp_table *opp_table)

include/linux/pm_opp.h

···
 struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev);
 struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp);
 int of_get_required_opp_performance_state(struct device_node *np, int index);
+void dev_pm_opp_of_register_em(struct cpumask *cpus);
 #else
 static inline int dev_pm_opp_of_add_table(struct device *dev)
 {
···
 {
 	return NULL;
 }
+
+static inline void dev_pm_opp_of_register_em(struct cpumask *cpus)
+{
+}
+
 static inline int of_get_required_opp_performance_state(struct device_node *np, int index)
 {
 	return -ENOTSUPP;