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

Pull ARM cpufreq driver changes for v5.15 from Viresh Kumar:

"This contains:

 - Update cpufreq-dt blocklist with more platforms (Bjorn Andersson).

 - Allow freq changes from any CPU for qcom-hw driver (Taniya Das).

 - Add DSVS interrupt's support for qcom-hw driver (Thara Gopinath).

 - A new callback (->register_em()) to register EM at a more convenient
   point of time."

* 'cpufreq/arm/linux-next' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  cpufreq: qcom-hw: Set dvfs_possible_from_any_cpu cpufreq driver flag
  cpufreq: blocklist more Qualcomm platforms in cpufreq-dt-platdev
  cpufreq: qcom-cpufreq-hw: Add dcvs interrupt support
  cpufreq: scmi: Use .register_em() to register with energy model
  cpufreq: vexpress: Use .register_em() to register with energy model
  cpufreq: scpi: Use .register_em() to register with energy model
  cpufreq: qcom-cpufreq-hw: Use .register_em() to register with energy model
  cpufreq: omap: Use .register_em() to register with energy model
  cpufreq: mediatek: Use .register_em() to register with energy model
  cpufreq: imx6q: Use .register_em() to register with energy model
  cpufreq: dt: Use .register_em() to register with energy model
  cpufreq: Add callback to register with energy model
  cpufreq: vexpress: Set CPUFREQ_IS_COOLING_DEV flag

12 files changed, 233 insertions, 54 deletions

diff --git a/drivers/base/arch_topology.c b/drivers/base/arch_topology.c
index 921312a8d957..43407665918f 100644
--- a/drivers/base/arch_topology.c
+++ b/drivers/base/arch_topology.c
@@ -149,6 +149,7 @@ 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)
 {
@@ -165,6 +166,7 @@ void topology_set_thermal_pressure(const struct cpumask *cpus,
 	for_each_cpu(cpu, cpus)
 		WRITE_ONCE(per_cpu(thermal_pressure, cpu), th_pressure);
 }
+EXPORT_SYMBOL_GPL(topology_set_thermal_pressure);
 
 static ssize_t cpu_capacity_show(struct device *dev,
 				 struct device_attribute *attr,
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 231e585f6ba2..ca1d103ec449 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -137,11 +137,15 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,apq8096", },
 	{ .compatible = "qcom,msm8996", },
 	{ .compatible = "qcom,qcs404", },
+	{ .compatible = "qcom,sa8155p" },
 	{ .compatible = "qcom,sc7180", },
 	{ .compatible = "qcom,sc7280", },
 	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sdm845", },
+	{ .compatible = "qcom,sm6350", },
 	{ .compatible = "qcom,sm8150", },
+	{ .compatible = "qcom,sm8250", },
+	{ .compatible = "qcom,sm8350", },
 
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index ece52863ba62..8fcaba541539 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -143,8 +143,6 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
 	}
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	return 0;
 
 out_clk_put:
@@ -184,6 +182,7 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.exit = cpufreq_exit,
 	.online = cpufreq_online,
 	.offline = cpufreq_offline,
+	.register_em = cpufreq_register_em_with_opp,
 	.name = "cpufreq-dt",
 	.attr = cpufreq_dt_attr,
 	.suspend = cpufreq_generic_suspend,
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 06c526d66dd3..7d5f170ecad1 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1491,6 +1491,19 @@ static int cpufreq_online(unsigned int cpu)
 		write_lock_irqsave(&cpufreq_driver_lock, flags);
 		list_add(&policy->policy_list, &cpufreq_policy_list);
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+		/*
+		 * Register with the energy model before
+		 * sched_cpufreq_governor_change() is called, which will result
+		 * in rebuilding of the sched domains, which should only be done
+		 * once the energy model is properly initialized for the policy
+		 * first.
+		 *
+		 * Also, this should be called before the policy is registered
+		 * with cooling framework.
+		 */
+		if (cpufreq_driver->register_em)
+			cpufreq_driver->register_em(policy);
 	}
 
 	ret = cpufreq_init_policy(policy);
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 5bf5fc759881..90beb26ed34e 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -192,7 +192,6 @@ static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
 	policy->clk = clks[ARM].clk;
 	cpufreq_generic_init(policy, freq_table, transition_latency);
 	policy->suspend_freq = max_freq;
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
 
 	return 0;
 }
@@ -204,6 +203,7 @@ static struct cpufreq_driver imx6q_cpufreq_driver = {
 	.target_index = imx6q_set_target,
 	.get = cpufreq_generic_get,
 	.init = imx6q_cpufreq_init,
+	.register_em = cpufreq_register_em_with_opp,
 	.name = "imx6q-cpufreq",
 	.attr = cpufreq_generic_attr,
 	.suspend = cpufreq_generic_suspend,
diff --git a/drivers/cpufreq/mediatek-cpufreq.c b/drivers/cpufreq/mediatek-cpufreq.c
index 87019d5a9547..866163883b48 100644
--- a/drivers/cpufreq/mediatek-cpufreq.c
+++ b/drivers/cpufreq/mediatek-cpufreq.c
@@ -448,8 +448,6 @@ static int mtk_cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = info;
 	policy->clk = info->cpu_clk;
 
-	dev_pm_opp_of_register_em(info->cpu_dev, policy->cpus);
-
 	return 0;
 }
 
@@ -471,6 +469,7 @@ static struct cpufreq_driver mtk_cpufreq_driver = {
 	.get = cpufreq_generic_get,
 	.init = mtk_cpufreq_init,
 	.exit = mtk_cpufreq_exit,
+	.register_em = cpufreq_register_em_with_opp,
 	.name = "mtk-cpufreq",
 	.attr = cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index e035ee216b0f..1b50df06c6bc 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -131,7 +131,6 @@ static int omap_cpu_init(struct cpufreq_policy *policy)
 
 	/* FIXME: what's the actual transition time? */
 	cpufreq_generic_init(policy, freq_table, 300 * 1000);
-	dev_pm_opp_of_register_em(mpu_dev, policy->cpus);
 
 	return 0;
 }
@@ -150,6 +149,7 @@ static struct cpufreq_driver omap_driver = {
 	.get		= cpufreq_generic_get,
 	.init		= omap_cpu_init,
 	.exit		= omap_cpu_exit,
+	.register_em	= cpufreq_register_em_with_opp,
 	.name		= "omap",
 	.attr		= cpufreq_generic_attr,
 };
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index f86859bf76f1..a2be0df7e174 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -7,12 +7,14 @@
 #include <linux/cpufreq.h>
 #include <linux/init.h>
 #include <linux/interconnect.h>
+#include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 #include <linux/pm_opp.h>
 #include <linux/slab.h>
+#include <linux/spinlock.h>
 
 #define LUT_MAX_ENTRIES			40U
 #define LUT_SRC				GENMASK(31, 30)
@@ -22,10 +24,13 @@
 #define CLK_HW_DIV			2
 #define LUT_TURBO_IND			1
 
+#define HZ_PER_KHZ			1000
+
 struct qcom_cpufreq_soc_data {
 	u32 reg_enable;
 	u32 reg_freq_lut;
 	u32 reg_volt_lut;
+	u32 reg_current_vote;
 	u32 reg_perf_state;
 	u8 lut_row_size;
 };
@@ -34,6 +39,16 @@ struct qcom_cpufreq_data {
 	void __iomem *base;
 	struct resource *res;
 	const struct qcom_cpufreq_soc_data *soc_data;
+
+	/*
+	 * Mutex to synchronize between de-init sequence and re-starting LMh
+	 * polling/interrupts
+	 */
+	struct mutex throttle_lock;
+	int throttle_irq;
+	bool cancel_throttle;
+	struct delayed_work throttle_work;
+	struct cpufreq_policy *policy;
 };
 
 static unsigned long cpu_hw_rate, xo_rate;
@@ -251,10 +266,92 @@ static void qcom_get_related_cpus(int index, struct cpumask *m)
 	}
 }
 
+static unsigned int qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
+{
+	unsigned int val = readl_relaxed(data->base + data->soc_data->reg_current_vote);
+
+	return (val & 0x3FF) * 19200;
+}
+
+static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
+{
+	unsigned long max_capacity, capacity, freq_hz, throttled_freq;
+	struct cpufreq_policy *policy = data->policy;
+	int cpu = cpumask_first(policy->cpus);
+	struct device *dev = get_cpu_device(cpu);
+	struct dev_pm_opp *opp;
+	unsigned int freq;
+
+	/*
+	 * Get the h/w throttled frequency, normalize it using the
+	 * registered opp table and use it to calculate thermal pressure.
+	 */
+	freq = qcom_lmh_get_throttle_freq(data);
+	freq_hz = freq * HZ_PER_KHZ;
+
+	opp = dev_pm_opp_find_freq_floor(dev, &freq_hz);
+	if (IS_ERR(opp) && PTR_ERR(opp) == -ERANGE)
+		dev_pm_opp_find_freq_ceil(dev, &freq_hz);
+
+	throttled_freq = freq_hz / HZ_PER_KHZ;
+
+	/* Update thermal pressure */
+
+	max_capacity = arch_scale_cpu_capacity(cpu);
+	capacity = mult_frac(max_capacity, throttled_freq, policy->cpuinfo.max_freq);
+
+	/* Don't pass boost capacity to scheduler */
+	if (capacity > max_capacity)
+		capacity = max_capacity;
+
+	arch_set_thermal_pressure(policy->cpus, max_capacity - capacity);
+
+	/*
+	 * In the unlikely case policy is unregistered do not enable
+	 * polling or h/w interrupt
+	 */
+	mutex_lock(&data->throttle_lock);
+	if (data->cancel_throttle)
+		goto out;
+
+	/*
+	 * If h/w throttled frequency is higher than what cpufreq has requested
+	 * for, then stop polling and switch back to interrupt mechanism.
+	 */
+	if (throttled_freq >= qcom_cpufreq_hw_get(cpu))
+		enable_irq(data->throttle_irq);
+	else
+		mod_delayed_work(system_highpri_wq, &data->throttle_work,
+				 msecs_to_jiffies(10));
+
+out:
+	mutex_unlock(&data->throttle_lock);
+}
+
+static void qcom_lmh_dcvs_poll(struct work_struct *work)
+{
+	struct qcom_cpufreq_data *data;
+
+	data = container_of(work, struct qcom_cpufreq_data, throttle_work.work);
+	qcom_lmh_dcvs_notify(data);
+}
+
+static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
+{
+	struct qcom_cpufreq_data *c_data = data;
+
+	/* Disable interrupt and enable polling */
+	disable_irq_nosync(c_data->throttle_irq);
+	qcom_lmh_dcvs_notify(c_data);
+
+	return 0;
+}
+
 static const struct qcom_cpufreq_soc_data qcom_soc_data = {
 	.reg_enable = 0x0,
 	.reg_freq_lut = 0x110,
 	.reg_volt_lut = 0x114,
+	.reg_current_vote = 0x704,
 	.reg_perf_state = 0x920,
 	.lut_row_size = 32,
 };
@@ -274,6 +371,51 @@ static const struct of_device_id qcom_cpufreq_hw_match[] = {
 };
 MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match);
 
+static int qcom_cpufreq_hw_lmh_init(struct cpufreq_policy *policy, int index)
+{
+	struct qcom_cpufreq_data *data = policy->driver_data;
+	struct platform_device *pdev = cpufreq_get_driver_data();
+	char irq_name[15];
+	int ret;
+
+	/*
+	 * Look for LMh interrupt. If no interrupt line is specified /
+	 * if there is an error, allow cpufreq to be enabled as usual.
+	 */
+	data->throttle_irq = platform_get_irq(pdev, index);
+	if (data->throttle_irq <= 0)
+		return data->throttle_irq == -EPROBE_DEFER ? -EPROBE_DEFER : 0;
+
+	data->cancel_throttle = false;
+	data->policy = policy;
+
+	mutex_init(&data->throttle_lock);
+	INIT_DEFERRABLE_WORK(&data->throttle_work, qcom_lmh_dcvs_poll);
+
+	snprintf(irq_name, sizeof(irq_name), "dcvsh-irq-%u", policy->cpu);
+	ret = request_threaded_irq(data->throttle_irq, NULL, qcom_lmh_dcvs_handle_irq,
+				   IRQF_ONESHOT, irq_name, data);
+	if (ret) {
+		dev_err(&pdev->dev, "Error registering %s: %d\n", irq_name, ret);
+		return 0;
+	}
+
+	return 0;
+}
+
+static void qcom_cpufreq_hw_lmh_exit(struct qcom_cpufreq_data *data)
+{
+	if (data->throttle_irq <= 0)
+		return;
+
+	mutex_lock(&data->throttle_lock);
+	data->cancel_throttle = true;
+	mutex_unlock(&data->throttle_lock);
+
+	cancel_delayed_work_sync(&data->throttle_work);
+	free_irq(data->throttle_irq, data);
+}
+
 static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 {
 	struct platform_device *pdev = cpufreq_get_driver_data();
@@ -348,6 +490,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	}
 
 	policy->driver_data = data;
+	policy->dvfs_possible_from_any_cpu = true;
 
 	ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy);
 	if (ret) {
@@ -362,14 +505,16 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 		goto error;
 	}
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	if (policy_has_boost_freq(policy)) {
 		ret = cpufreq_enable_boost_support();
 		if (ret)
 			dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
 	}
 
+	ret = qcom_cpufreq_hw_lmh_init(policy, index);
+	if (ret)
+		goto error;
+
 	return 0;
 error:
 	kfree(data);
@@ -389,6 +534,7 @@ static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
 
 	dev_pm_opp_remove_all_dynamic(cpu_dev);
 	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
+	qcom_cpufreq_hw_lmh_exit(data);
 	kfree(policy->freq_table);
 	kfree(data);
 	iounmap(base);
@@ -412,6 +558,7 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = {
 	.get		= qcom_cpufreq_hw_get,
 	.init		= qcom_cpufreq_hw_cpu_init,
 	.exit		= qcom_cpufreq_hw_cpu_exit,
+	.register_em	= cpufreq_register_em_with_opp,
 	.fast_switch    = qcom_cpufreq_hw_fast_switch,
 	.name		= "qcom-cpufreq-hw",
 	.attr		= qcom_cpufreq_hw_attr,
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 75f818d04b48..1e0cd4d165f0 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -22,7 +22,9 @@
 
 struct scmi_data {
 	int domain_id;
+	int nr_opp;
 	struct device *cpu_dev;
+	cpumask_var_t opp_shared_cpus;
 };
 
 static struct scmi_protocol_handle *ph;
@@ -123,9 +125,6 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	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);
-	cpumask_var_t opp_shared_cpus;
-	bool power_scale_mw;
 
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
@@ -133,9 +132,15 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	if (!zalloc_cpumask_var(&opp_shared_cpus, GFP_KERNEL))
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv)
 		return -ENOMEM;
 
+	if (!zalloc_cpumask_var(&priv->opp_shared_cpus, GFP_KERNEL)) {
+		ret = -ENOMEM;
+		goto out_free_priv;
+	}
+
 	/* Obtain CPUs that share SCMI performance controls */
 	ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus);
 	if (ret) {
@@ -148,14 +153,14 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	 * The OPP 'sharing cpus' info may come from DT through an empty opp
 	 * table and opp-shared.
 	 */
-	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, opp_shared_cpus);
-	if (ret || !cpumask_weight(opp_shared_cpus)) {
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
+	if (ret || !cpumask_weight(priv->opp_shared_cpus)) {
 		/*
 		 * Either opp-table is not set or no opp-shared was found.
 		 * Use the CPU mask from SCMI to designate CPUs sharing an OPP
 		 * table.
 		 */
-		cpumask_copy(opp_shared_cpus, policy->cpus);
+		cpumask_copy(priv->opp_shared_cpus, policy->cpus);
 	}
 
 	 /*
@@ -180,7 +185,7 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 			goto out_free_opp;
 		}
 
-		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, opp_shared_cpus);
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, priv->opp_shared_cpus);
 		if (ret) {
 			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
 				__func__, ret);
@@ -188,21 +193,13 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 			goto out_free_opp;
 		}
 
-		power_scale_mw = perf_ops->power_scale_mw_get(ph);
-		em_dev_register_perf_domain(cpu_dev, nr_opp, &em_cb,
-					    opp_shared_cpus, power_scale_mw);
-	}
-
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto out_free_opp;
+		priv->nr_opp = nr_opp;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
-		goto out_free_priv;
+		goto out_free_opp;
 	}
 
 	priv->cpu_dev = cpu_dev;
@@ -223,17 +220,16 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible =
 		perf_ops->fast_switch_possible(ph, cpu_dev);
 
-	free_cpumask_var(opp_shared_cpus);
 	return 0;
 
-out_free_priv:
-	kfree(priv);
-
 out_free_opp:
 	dev_pm_opp_remove_all_dynamic(cpu_dev);
 
 out_free_cpumask:
-	free_cpumask_var(opp_shared_cpus);
+	free_cpumask_var(priv->opp_shared_cpus);
+
+out_free_priv:
+	kfree(priv);
 
 	return ret;
 }
@@ -244,11 +240,33 @@ static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
 
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
 	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+	free_cpumask_var(priv->opp_shared_cpus);
 	kfree(priv);
 
 	return 0;
 }
 
+static void scmi_cpufreq_register_em(struct cpufreq_policy *policy)
+{
+	struct em_data_callback em_cb = EM_DATA_CB(scmi_get_cpu_power);
+	bool power_scale_mw = perf_ops->power_scale_mw_get(ph);
+	struct scmi_data *priv = policy->driver_data;
+
+	/*
+	 * This callback will be called for each policy, but we don't need to
+	 * register with EM every time. Despite not being part of the same
+	 * policy, some CPUs may still share their perf-domains, and a CPU from
+	 * another policy may already have registered with EM on behalf of CPUs
+	 * of this policy.
+	 */
+	if (!priv->nr_opp)
+		return;
+
+	em_dev_register_perf_domain(get_cpu_device(policy->cpu), priv->nr_opp,
+				    &em_cb, priv->opp_shared_cpus,
+				    power_scale_mw);
+}
+
 static struct cpufreq_driver scmi_cpufreq_driver = {
 	.name	= "scmi",
 	.flags	= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
@@ -261,6 +279,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = {
 	.get	= scmi_cpufreq_get_rate,
 	.init	= scmi_cpufreq_init,
 	.exit	= scmi_cpufreq_exit,
+	.register_em	= scmi_cpufreq_register_em,
 };
 
 static int scmi_cpufreq_probe(struct scmi_device *sdev)
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index d6a698a1b5d1..bda3e7d42964 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -163,8 +163,6 @@ static int scpi_cpufreq_init(struct cpufreq_policy *policy)
 
 	policy->fast_switch_possible = false;
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	return 0;
 
 out_free_cpufreq_table:
@@ -200,6 +198,7 @@ static struct cpufreq_driver scpi_cpufreq_driver = {
 	.init	= scpi_cpufreq_init,
 	.exit	= scpi_cpufreq_exit,
 	.target_index	= scpi_cpufreq_set_target,
+	.register_em	= cpufreq_register_em_with_opp,
 };
 
 static int scpi_cpufreq_probe(struct platform_device *pdev)
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index 51dfa9ae6cf5..284b6bd040b1 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -15,7 +15,6 @@
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/cpumask.h>
-#include <linux/cpu_cooling.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
@@ -47,7 +46,6 @@ static bool bL_switching_enabled;
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
 #define VIRT_FREQ(cluster, freq)    ((cluster == A7_CLUSTER) ? freq >> 1 : freq)
 
-static struct thermal_cooling_device *cdev[MAX_CLUSTERS];
 static struct clk *clk[MAX_CLUSTERS];
 static struct cpufreq_frequency_table *freq_table[MAX_CLUSTERS + 1];
 static atomic_t cluster_usage[MAX_CLUSTERS + 1];
@@ -442,8 +440,6 @@ static int ve_spc_cpufreq_init(struct cpufreq_policy *policy)
 	policy->freq_table = freq_table[cur_cluster];
 	policy->cpuinfo.transition_latency = 1000000; /* 1 ms */
 
-	dev_pm_opp_of_register_em(cpu_dev, policy->cpus);
-
 	if (is_bL_switching_enabled())
 		per_cpu(cpu_last_req_freq, policy->cpu) =
 						clk_get_cpu_rate(policy->cpu);
@@ -457,11 +453,6 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
 	struct device *cpu_dev;
 	int cur_cluster = cpu_to_cluster(policy->cpu);
 
-	if (cur_cluster < MAX_CLUSTERS) {
-		cpufreq_cooling_unregister(cdev[cur_cluster]);
-		cdev[cur_cluster] = NULL;
-	}
-
 	cpu_dev = get_cpu_device(policy->cpu);
 	if (!cpu_dev) {
 		pr_err("%s: failed to get cpu%d device\n", __func__,
@@ -473,17 +464,6 @@ static int ve_spc_cpufreq_exit(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void ve_spc_cpufreq_ready(struct cpufreq_policy *policy)
-{
-	int cur_cluster = cpu_to_cluster(policy->cpu);
-
-	/* Do not register a cpu_cooling device if we are in IKS mode */
-	if (cur_cluster >= MAX_CLUSTERS)
-		return;
-
-	cdev[cur_cluster] = of_cpufreq_cooling_register(policy);
-}
-
 static struct cpufreq_driver ve_spc_cpufreq_driver = {
 	.name			= "vexpress-spc",
 	.flags			= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
@@ -493,7 +473,7 @@ static struct cpufreq_driver ve_spc_cpufreq_driver = {
 	.get			= ve_spc_cpufreq_get_rate,
 	.init			= ve_spc_cpufreq_init,
 	.exit			= ve_spc_cpufreq_exit,
-	.ready			= ve_spc_cpufreq_ready,
+	.register_em		= cpufreq_register_em_with_opp,
 	.attr			= cpufreq_generic_attr,
 };
 
@@ -553,6 +533,9 @@ static int ve_spc_cpufreq_probe(struct platform_device *pdev)
 	for (i = 0; i < MAX_CLUSTERS; i++)
 		mutex_init(&cluster_lock[i]);
 
+	if (!is_bL_switching_enabled())
+		ve_spc_cpufreq_driver.flags |= CPUFREQ_IS_COOLING_DEV;
+
 	ret = cpufreq_register_driver(&ve_spc_cpufreq_driver);
 	if (ret) {
 		pr_info("%s: Failed registering platform driver: %s, err: %d\n",
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 9fd719475fcd..c65a1d7385f8 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -9,10 +9,12 @@
 #define _LINUX_CPUFREQ_H
 
 #include <linux/clk.h>
+#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/completion.h>
 #include <linux/kobject.h>
 #include <linux/notifier.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_qos.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
@@ -373,6 +375,12 @@ struct cpufreq_driver {
 	/* platform specific boost support code */
 	bool		boost_enabled;
 	int		(*set_boost)(struct cpufreq_policy *policy, int state);
+
+	/*
+	 * Set by drivers that want to register with the energy model after the
+	 * policy is properly initialized, but before the governor is started.
+	 */
+	void		(*register_em)(struct cpufreq_policy *policy);
 };
 
 /* flags */
@@ -1046,4 +1054,10 @@ unsigned int cpufreq_generic_get(unsigned int cpu);
 void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
+
+static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy)
+{
+	dev_pm_opp_of_register_em(get_cpu_device(policy->cpu),
+				  policy->related_cpus);
+}
 #endif /* _LINUX_CPUFREQ_H */