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

Pull ARM cpufreq driver updates for v5.1 from Viresh Kumar:

"This pull request contains following changes:

 - New Armada 8k cpufreq driver (Gregory CLEMENT).
 - qcom driver cleanups (Amit Kucheria, Taniya Das, Yangtao Li).
 - s5pv210 driver cleanup (Paweł Chmiel).
 - tegra driver cleanup (Yangtao Li).
 - Minor update to MAINTAINERS file (Baruch Siach)."

* 'cpufreq/arm/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  cpufreq: qcom-hw: Register an Energy Model
  cpufreq: qcom: Read voltage LUT and populate OPP
  cpufreq: qcom-hw: Move to device_initcall
  cpufreq: tegra124: add missing of_node_put()
  cpufreq: qcom-kryo: make some variables static
  MAINTAINERS: Update the active pm tree for ARM
  cpufreq: ap806: add cpufreq driver for Armada 8K
  MAINTAINERS: add new entries for Armada 8K cpufreq driver
  cpufreq: s5pv210: Defer probe if getting regulators fail
  MAINTAINERS: use common indentation
  PM / OPP: Introduce a power estimation helper
  PM / OPP: Remove unused parameter of _generic_set_opp_clk_only()

9 files changed, 411 insertions, 36 deletions

diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index ca8567c3152c..f08bb0075316 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -25,6 +25,17 @@ config ARM_ARMADA_37XX_CPUFREQ
 	  This adds the CPUFreq driver support for Marvell Armada 37xx SoCs.
 	  The Armada 37xx PMU supports 4 frequency and VDD levels.
 
+config ARM_ARMADA_8K_CPUFREQ
+	tristate "Armada 8K CPUFreq driver"
+	depends on ARCH_MVEBU && CPUFREQ_DT
+	help
+	  This enables the CPUFreq driver support for Marvell
+	  Armada8k SOCs.
+	  Armada8K device has the AP806 which supports scaling
+	  to any full integer divider.
+
+	  If in doubt, say N.
+
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 08c071be2491..689b26c6f949 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -50,6 +50,7 @@ obj-$(CONFIG_X86_SFI_CPUFREQ)		+= sfi-cpufreq.o
 obj-$(CONFIG_ARM_BIG_LITTLE_CPUFREQ)	+= arm_big_little.o
 
 obj-$(CONFIG_ARM_ARMADA_37XX_CPUFREQ)	+= armada-37xx-cpufreq.o
+obj-$(CONFIG_ARM_ARMADA_8K_CPUFREQ)	+= armada-8k-cpufreq.o
 obj-$(CONFIG_ARM_BRCMSTB_AVS_CPUFREQ)	+= brcmstb-avs-cpufreq.o
 obj-$(CONFIG_ACPI_CPPC_CPUFREQ)		+= cppc_cpufreq.o
 obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
diff --git a/drivers/cpufreq/armada-8k-cpufreq.c b/drivers/cpufreq/armada-8k-cpufreq.c
new file mode 100644
index 000000000000..8a5ddb93fc58
--- /dev/null
+++ b/drivers/cpufreq/armada-8k-cpufreq.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * CPUFreq support for Armada 8K
+ *
+ * Copyright (C) 2018 Marvell
+ *
+ * Omri Itach <omrii@marvell.com>
+ * Gregory Clement <gregory.clement@bootlin.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+/*
+ * Setup the opps list with the divider for the max frequency, that
+ * will be filled at runtime.
+ */
+static const int opps_div[] __initconst = {1, 2, 3, 4};
+
+static struct platform_device *armada_8k_pdev;
+
+struct freq_table {
+	struct device *cpu_dev;
+	unsigned int freq[ARRAY_SIZE(opps_div)];
+};
+
+/* If the CPUs share the same clock, then they are in the same cluster. */
+static void __init armada_8k_get_sharing_cpus(struct clk *cur_clk,
+					      struct cpumask *cpumask)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct device *cpu_dev;
+		struct clk *clk;
+
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			pr_warn("Failed to get cpu%d device\n", cpu);
+			continue;
+		}
+
+		clk = clk_get(cpu_dev, 0);
+		if (IS_ERR(clk)) {
+			pr_warn("Cannot get clock for CPU %d\n", cpu);
+		} else {
+			if (clk_is_match(clk, cur_clk))
+				cpumask_set_cpu(cpu, cpumask);
+
+			clk_put(clk);
+		}
+	}
+}
+
+static int __init armada_8k_add_opp(struct clk *clk, struct device *cpu_dev,
+				    struct freq_table *freq_tables,
+				    int opps_index)
+{
+	unsigned int cur_frequency;
+	unsigned int freq;
+	int i, ret;
+
+	/* Get nominal (current) CPU frequency. */
+	cur_frequency = clk_get_rate(clk);
+	if (!cur_frequency) {
+		dev_err(cpu_dev, "Failed to get clock rate for this CPU\n");
+		return -EINVAL;
+	}
+
+	freq_tables[opps_index].cpu_dev = cpu_dev;
+
+	for (i = 0; i < ARRAY_SIZE(opps_div); i++) {
+		freq = cur_frequency / opps_div[i];
+
+		ret = dev_pm_opp_add(cpu_dev, freq, 0);
+		if (ret)
+			return ret;
+
+		freq_tables[opps_index].freq[i] = freq;
+	}
+
+	return 0;
+}
+
+static void armada_8k_cpufreq_free_table(struct freq_table *freq_tables)
+{
+	int opps_index, nb_cpus = num_possible_cpus();
+
+	for (opps_index = 0 ; opps_index <= nb_cpus; opps_index++) {
+		int i;
+
+		/* If cpu_dev is NULL then we reached the end of the array */
+		if (!freq_tables[opps_index].cpu_dev)
+			break;
+
+		for (i = 0; i < ARRAY_SIZE(opps_div); i++) {
+			/*
+			 * A 0Hz frequency is not valid, this meant
+			 * that it was not yet initialized so there is
+			 * no more opp to free
+			 */
+			if (freq_tables[opps_index].freq[i] == 0)
+				break;
+
+			dev_pm_opp_remove(freq_tables[opps_index].cpu_dev,
+					  freq_tables[opps_index].freq[i]);
+		}
+	}
+
+	kfree(freq_tables);
+}
+
+static int __init armada_8k_cpufreq_init(void)
+{
+	int ret = 0, opps_index = 0, cpu, nb_cpus;
+	struct freq_table *freq_tables;
+	struct device_node *node;
+	struct cpumask cpus;
+
+	node = of_find_compatible_node(NULL, NULL, "marvell,ap806-cpu-clock");
+	if (!node || !of_device_is_available(node))
+		return -ENODEV;
+
+	nb_cpus = num_possible_cpus();
+	freq_tables = kcalloc(nb_cpus, sizeof(*freq_tables), GFP_KERNEL);
+	cpumask_copy(&cpus, cpu_possible_mask);
+
+	/*
+	 * For each CPU, this loop registers the operating points
+	 * supported (which are the nominal CPU frequency and full integer
+	 * divisions of it).
+	 */
+	for_each_cpu(cpu, &cpus) {
+		struct cpumask shared_cpus;
+		struct device *cpu_dev;
+		struct clk *clk;
+
+		cpu_dev = get_cpu_device(cpu);
+
+		if (!cpu_dev) {
+			pr_err("Cannot get CPU %d\n", cpu);
+			continue;
+		}
+
+		clk = clk_get(cpu_dev, 0);
+
+		if (IS_ERR(clk)) {
+			pr_err("Cannot get clock for CPU %d\n", cpu);
+			ret = PTR_ERR(clk);
+			goto remove_opp;
+		}
+
+		ret = armada_8k_add_opp(clk, cpu_dev, freq_tables, opps_index);
+		if (ret) {
+			clk_put(clk);
+			goto remove_opp;
+		}
+
+		opps_index++;
+		cpumask_clear(&shared_cpus);
+		armada_8k_get_sharing_cpus(clk, &shared_cpus);
+		dev_pm_opp_set_sharing_cpus(cpu_dev, &shared_cpus);
+		cpumask_andnot(&cpus, &cpus, &shared_cpus);
+		clk_put(clk);
+	}
+
+	armada_8k_pdev = platform_device_register_simple("cpufreq-dt", -1,
+							 NULL, 0);
+	ret = PTR_ERR_OR_ZERO(armada_8k_pdev);
+	if (ret)
+		goto remove_opp;
+
+	platform_set_drvdata(armada_8k_pdev, freq_tables);
+
+	return 0;
+
+remove_opp:
+	armada_8k_cpufreq_free_table(freq_tables);
+	return ret;
+}
+module_init(armada_8k_cpufreq_init);
+
+static void __exit armada_8k_cpufreq_exit(void)
+{
+	struct freq_table *freq_tables = platform_get_drvdata(armada_8k_pdev);
+
+	platform_device_unregister(armada_8k_pdev);
+	armada_8k_cpufreq_free_table(freq_tables);
+}
+module_exit(armada_8k_cpufreq_exit);
+
+MODULE_AUTHOR("Gregory Clement <gregory.clement@bootlin.com>");
+MODULE_DESCRIPTION("Armada 8K cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index c88b51304d89..4b0b50403901 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -10,18 +10,21 @@
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
+#include <linux/pm_opp.h>
 #include <linux/slab.h>
 
 #define LUT_MAX_ENTRIES			40U
 #define LUT_SRC				GENMASK(31, 30)
 #define LUT_L_VAL			GENMASK(7, 0)
 #define LUT_CORE_COUNT			GENMASK(18, 16)
+#define LUT_VOLT			GENMASK(11, 0)
 #define LUT_ROW_SIZE			32
 #define CLK_HW_DIV			2
 
 /* Register offsets */
 #define REG_ENABLE			0x0
-#define REG_LUT_TABLE			0x110
+#define REG_FREQ_LUT			0x110
+#define REG_VOLT_LUT			0x114
 #define REG_PERF_STATE			0x920
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -70,11 +73,12 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 	return policy->freq_table[index].frequency;
 }
 
-static int qcom_cpufreq_hw_read_lut(struct device *dev,
+static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 				    struct cpufreq_policy *policy,
 				    void __iomem *base)
 {
 	u32 data, src, lval, i, core_count, prev_cc = 0, prev_freq = 0, freq;
+	u32 volt;
 	unsigned int max_cores = cpumask_weight(policy->cpus);
 	struct cpufreq_frequency_table	*table;
 
@@ -83,23 +87,28 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 		return -ENOMEM;
 
 	for (i = 0; i < LUT_MAX_ENTRIES; i++) {
-		data = readl_relaxed(base + REG_LUT_TABLE + i * LUT_ROW_SIZE);
+		data = readl_relaxed(base + REG_FREQ_LUT +
+				      i * LUT_ROW_SIZE);
 		src = FIELD_GET(LUT_SRC, data);
 		lval = FIELD_GET(LUT_L_VAL, data);
 		core_count = FIELD_GET(LUT_CORE_COUNT, data);
 
+		data = readl_relaxed(base + REG_VOLT_LUT +
+				      i * LUT_ROW_SIZE);
+		volt = FIELD_GET(LUT_VOLT, data) * 1000;
+
 		if (src)
 			freq = xo_rate * lval / 1000;
 		else
 			freq = cpu_hw_rate / 1000;
 
-		/* Ignore boosts in the middle of the table */
-		if (core_count != max_cores) {
-			table[i].frequency = CPUFREQ_ENTRY_INVALID;
-		} else {
+		if (freq != prev_freq && core_count == max_cores) {
 			table[i].frequency = freq;
-			dev_dbg(dev, "index=%d freq=%d, core_count %d\n", i,
+			dev_pm_opp_add(cpu_dev, freq * 1000, volt);
+			dev_dbg(cpu_dev, "index=%d freq=%d, core_count %d\n", i,
 				freq, core_count);
+		} else {
+			table[i].frequency = CPUFREQ_ENTRY_INVALID;
 		}
 
 		/*
@@ -116,6 +125,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 			if (prev_cc != max_cores) {
 				prev->frequency = prev_freq;
 				prev->flags = CPUFREQ_BOOST_FREQ;
+				dev_pm_opp_add(cpu_dev,	prev_freq * 1000, volt);
 			}
 
 			break;
@@ -127,6 +137,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *dev,
 
 	table[i].frequency = CPUFREQ_TABLE_END;
 	policy->freq_table = table;
+	dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
 
 	return 0;
 }
@@ -159,10 +170,18 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	struct device *dev = &global_pdev->dev;
 	struct of_phandle_args args;
 	struct device_node *cpu_np;
+	struct device *cpu_dev;
 	struct resource *res;
 	void __iomem *base;
 	int ret, index;
 
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("%s: failed to get cpu%d device\n", __func__,
+		       policy->cpu);
+		return -ENODEV;
+	}
+
 	cpu_np = of_cpu_device_node_get(policy->cpu);
 	if (!cpu_np)
 		return -EINVAL;
@@ -199,12 +218,21 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 
 	policy->driver_data = base + REG_PERF_STATE;
 
-	ret = qcom_cpufreq_hw_read_lut(dev, policy, base);
+	ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy, base);
 	if (ret) {
 		dev_err(dev, "Domain-%d failed to read LUT\n", index);
 		goto error;
 	}
 
+	ret = dev_pm_opp_get_opp_count(cpu_dev);
+	if (ret <= 0) {
+		dev_err(cpu_dev, "Failed to add OPPs\n");
+		ret = -ENODEV;
+		goto error;
+	}
+
+	dev_pm_opp_of_register_em(policy->cpus);
+
 	policy->fast_switch_possible = true;
 
 	return 0;
@@ -215,8 +243,10 @@ error:
 
 static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
 {
+	struct device *cpu_dev = get_cpu_device(policy->cpu);
 	void __iomem *base = policy->driver_data - REG_PERF_STATE;
 
+	dev_pm_opp_remove_all_dynamic(cpu_dev);
 	kfree(policy->freq_table);
 	devm_iounmap(&global_pdev->dev, base);
 
@@ -297,7 +327,7 @@ static int __init qcom_cpufreq_hw_init(void)
 {
 	return platform_driver_register(&qcom_cpufreq_hw_driver);
 }
-subsys_initcall(qcom_cpufreq_hw_init);
+device_initcall(qcom_cpufreq_hw_init);
 
 static void __exit qcom_cpufreq_hw_exit(void)
 {
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
index 2a3675c24032..1c8583cc06a2 100644
--- a/drivers/cpufreq/qcom-cpufreq-kryo.c
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -42,7 +42,7 @@ enum _msm8996_version {
 	NUM_OF_MSM8996_VERSIONS,
 };
 
-struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
+static struct platform_device *cpufreq_dt_pdev, *kryo_cpufreq_pdev;
 
 static enum _msm8996_version qcom_cpufreq_kryo_get_msm_id(void)
 {
diff --git a/drivers/cpufreq/s5pv210-cpufreq.c b/drivers/cpufreq/s5pv210-cpufreq.c
index dbecd7667db2..5b4289460bc9 100644
--- a/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/drivers/cpufreq/s5pv210-cpufreq.c
@@ -584,7 +584,7 @@ static struct notifier_block s5pv210_cpufreq_reboot_notifier = {
 static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
-	int id;
+	int id, result = 0;
 
 	/*
 	 * HACK: This is a temporary workaround to get access to clock
@@ -594,18 +594,39 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 	 * this whole driver as soon as S5PV210 gets migrated to use
 	 * cpufreq-dt driver.
 	 */
+	arm_regulator = regulator_get(NULL, "vddarm");
+	if (IS_ERR(arm_regulator)) {
+		if (PTR_ERR(arm_regulator) == -EPROBE_DEFER)
+			pr_debug("vddarm regulator not ready, defer\n");
+		else
+			pr_err("failed to get regulator vddarm\n");
+		return PTR_ERR(arm_regulator);
+	}
+
+	int_regulator = regulator_get(NULL, "vddint");
+	if (IS_ERR(int_regulator)) {
+		if (PTR_ERR(int_regulator) == -EPROBE_DEFER)
+			pr_debug("vddint regulator not ready, defer\n");
+		else
+			pr_err("failed to get regulator vddint\n");
+		result = PTR_ERR(int_regulator);
+		goto err_int_regulator;
+	}
+
 	np = of_find_compatible_node(NULL, NULL, "samsung,s5pv210-clock");
 	if (!np) {
 		pr_err("%s: failed to find clock controller DT node\n",
 			__func__);
-		return -ENODEV;
+		result = -ENODEV;
+		goto err_clock;
 	}
 
 	clk_base = of_iomap(np, 0);
 	of_node_put(np);
 	if (!clk_base) {
 		pr_err("%s: failed to map clock registers\n", __func__);
-		return -EFAULT;
+		result = -EFAULT;
+		goto err_clock;
 	}
 
 	for_each_compatible_node(np, NULL, "samsung,s5pv210-dmc") {
@@ -614,7 +635,8 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 			pr_err("%s: failed to get alias of dmc node '%pOFn'\n",
 				__func__, np);
 			of_node_put(np);
-			return id;
+			result = id;
+			goto err_clk_base;
 		}
 
 		dmc_base[id] = of_iomap(np, 0);
@@ -622,33 +644,40 @@ static int s5pv210_cpufreq_probe(struct platform_device *pdev)
 			pr_err("%s: failed to map dmc%d registers\n",
 				__func__, id);
 			of_node_put(np);
-			return -EFAULT;
+			result = -EFAULT;
+			goto err_dmc;
 		}
 	}
 
 	for (id = 0; id < ARRAY_SIZE(dmc_base); ++id) {
 		if (!dmc_base[id]) {
 			pr_err("%s: failed to find dmc%d node\n", __func__, id);
-			return -ENODEV;
+			result = -ENODEV;
+			goto err_dmc;
 		}
 	}
 
-	arm_regulator = regulator_get(NULL, "vddarm");
-	if (IS_ERR(arm_regulator)) {
-		pr_err("failed to get regulator vddarm\n");
-		return PTR_ERR(arm_regulator);
-	}
-
-	int_regulator = regulator_get(NULL, "vddint");
-	if (IS_ERR(int_regulator)) {
-		pr_err("failed to get regulator vddint\n");
-		regulator_put(arm_regulator);
-		return PTR_ERR(int_regulator);
-	}
-
 	register_reboot_notifier(&s5pv210_cpufreq_reboot_notifier);
 
 	return cpufreq_register_driver(&s5pv210_driver);
+
+err_dmc:
+	for (id = 0; id < ARRAY_SIZE(dmc_base); ++id)
+		if (dmc_base[id]) {
+			iounmap(dmc_base[id]);
+			dmc_base[id] = NULL;
+		}
+
+err_clk_base:
+	iounmap(clk_base);
+
+err_clock:
+	regulator_put(int_regulator);
+
+err_int_regulator:
+	regulator_put(arm_regulator);
+
+	return result;
 }
 
 static struct platform_driver s5pv210_cpufreq_platdrv = {
diff --git a/drivers/cpufreq/tegra124-cpufreq.c b/drivers/cpufreq/tegra124-cpufreq.c
index 43530254201a..4bb154f6c54c 100644
--- a/drivers/cpufreq/tegra124-cpufreq.c
+++ b/drivers/cpufreq/tegra124-cpufreq.c
@@ -134,6 +134,8 @@ static int tegra124_cpufreq_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, priv);
 
+	of_node_put(np);
+
 	return 0;
 
 out_switch_to_pllx:
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 18f1639dbc4a..4e00301060cf 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -533,9 +533,8 @@ static int _set_opp_voltage(struct device *dev, struct regulator *reg,
 	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;
 
@@ -572,7 +571,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
 	}
 
 	/* 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;
 
@@ -586,7 +585,7 @@ static int _generic_set_opp_regulator(const struct opp_table *opp_table,
 	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:
@@ -759,7 +758,7 @@ int dev_pm_opp_set_rate(struct device *dev, unsigned long target_freq)
 						 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 */
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index 06f0f632ec47..cd58959e5158 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -20,6 +20,7 @@
 #include <linux/pm_domain.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/energy_model.h>
 
 #include "opp.h"
 
@@ -1047,3 +1048,101 @@ struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
 	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);