cpufreq: add support for CPU DVFS based on SCMI message protocol

On some ARM based systems, a separate Cortex-M based System Control
Processor(SCP) provides the overall power, clock, reset and system
control including CPU DVFS. SCMI Message Protocol is used to
communicate with the SCP.

This patch adds a cpufreq driver for such systems using SCMI interface
to drive CPU DVFS.

Cc: linux-pm@vger.kernel.org
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>

MAINTAINERS

@@ -13385,7 +13385,7 @@ L:	linux-arm-kernel@lists.infradead.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/arm/arm,sc[mp]i.txt
 F:	drivers/clk/clk-sc[mp]i.c
-F:	drivers/cpufreq/scpi-cpufreq.c
+F:	drivers/cpufreq/sc[mp]i-cpufreq.c
 F:	drivers/firmware/arm_scpi.c
 F:	drivers/firmware/arm_scmi/
 F:	include/linux/sc[mp]i_protocol.h

drivers/cpufreq/Kconfig.arm

@@ -238,6 +238,17 @@ config ARM_SA1100_CPUFREQ
 config ARM_SA1110_CPUFREQ
 	bool
 
+config ARM_SCMI_CPUFREQ
+	tristate "SCMI based CPUfreq driver"
+	depends on ARM_SCMI_PROTOCOL || COMPILE_TEST
+	select PM_OPP
+	help
+	  This adds the CPUfreq driver support for ARM platforms using SCMI
+	  protocol for CPU power management.
+
+	  This driver uses SCMI Message Protocol driver to interact with the
+	  firmware providing the CPU DVFS functionality.
+
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR

drivers/cpufreq/Makefile

@@ -75,6 +75,7 @@ obj-$(CONFIG_ARM_S3C24XX_CPUFREQ_DEBUGFS) += s3c24xx-cpufreq-debugfs.o
 obj-$(CONFIG_ARM_S5PV210_CPUFREQ)	+= s5pv210-cpufreq.o
 obj-$(CONFIG_ARM_SA1100_CPUFREQ)	+= sa1100-cpufreq.o
 obj-$(CONFIG_ARM_SA1110_CPUFREQ)	+= sa1110-cpufreq.o
+obj-$(CONFIG_ARM_SCMI_CPUFREQ)		+= scmi-cpufreq.o
 obj-$(CONFIG_ARM_SCPI_CPUFREQ)		+= scpi-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
 obj-$(CONFIG_ARM_STI_CPUFREQ)		+= sti-cpufreq.o

drivers/cpufreq/scmi-cpufreq.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * System Control and Power Interface (SCMI) based CPUFreq Interface driver
+ *
+ * Copyright (C) 2018 ARM Ltd.
+ * Sudeep Holla <sudeep.holla@arm.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/cpu_cooling.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/scmi_protocol.h>
+#include <linux/types.h>
+
+struct scmi_data {
+	int domain_id;
+	struct device *cpu_dev;
+	struct thermal_cooling_device *cdev;
+};
+
+static const struct scmi_handle *handle;
+
+static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+	struct scmi_perf_ops *perf_ops = handle->perf_ops;
+	struct scmi_data *priv = policy->driver_data;
+	unsigned long rate;
+	int ret;
+
+	ret = perf_ops->freq_get(handle, priv->domain_id, &rate, false);
+	if (ret)
+		return 0;
+	return rate / 1000;
+}
+
+/*
+ * perf_ops->freq_set is not a synchronous, the actual OPP change will
+ * happen asynchronously and can get notified if the events are
+ * subscribed for by the SCMI firmware
+ */
+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 * 1000;
+
+	ret = perf_ops->freq_set(handle, priv->domain_id, freq, false);
+	if (!ret)
+		arch_set_freq_scale(policy->related_cpus, freq,
+				    policy->cpuinfo.max_freq);
+	return ret;
+}
+
+static int
+scmi_get_sharing_cpus(struct device *cpu_dev, struct cpumask *cpumask)
+{
+	int cpu, domain, tdomain;
+	struct device *tcpu_dev;
+
+	domain = handle->perf_ops->device_domain_id(cpu_dev);
+	if (domain < 0)
+		return domain;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu == cpu_dev->id)
+			continue;
+
+		tcpu_dev = get_cpu_device(cpu);
+		if (!tcpu_dev)
+			continue;
+
+		tdomain = handle->perf_ops->device_domain_id(tcpu_dev);
+		if (tdomain == domain)
+			cpumask_set_cpu(cpu, cpumask);
+	}
+
+	return 0;
+}
+
+static int scmi_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int ret;
+	unsigned int latency;
+	struct device *cpu_dev;
+	struct scmi_data *priv;
+	struct cpufreq_frequency_table *freq_table;
+
+	cpu_dev = get_cpu_device(policy->cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", policy->cpu);
+		return -ENODEV;
+	}
+
+	ret = handle->perf_ops->add_opps_to_device(handle, cpu_dev);
+	if (ret) {
+		dev_warn(cpu_dev, "failed to add opps to the device\n");
+		return ret;
+	}
+
+	ret = scmi_get_sharing_cpus(cpu_dev, policy->cpus);
+	if (ret) {
+		dev_warn(cpu_dev, "failed to get sharing cpumask\n");
+		return ret;
+	}
+
+	ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
+	if (ret) {
+		dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+			__func__, ret);
+		return ret;
+	}
+
+	ret = dev_pm_opp_get_opp_count(cpu_dev);
+	if (ret <= 0) {
+		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
+		ret = -EPROBE_DEFER;
+		goto out_free_opp;
+	}
+
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (!priv) {
+		ret = -ENOMEM;
+		goto out_free_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;
+	}
+
+	priv->cpu_dev = cpu_dev;
+	priv->domain_id = handle->perf_ops->device_domain_id(cpu_dev);
+
+	policy->driver_data = priv;
+
+	ret = cpufreq_table_validate_and_show(policy, freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
+			ret);
+		goto out_free_cpufreq_table;
+	}
+
+	/* SCMI allows DVFS request for any domain from any CPU */
+	policy->dvfs_possible_from_any_cpu = true;
+
+	latency = handle->perf_ops->get_transition_latency(handle, cpu_dev);
+	if (!latency)
+		latency = CPUFREQ_ETERNAL;
+
+	policy->cpuinfo.transition_latency = latency;
+
+	return 0;
+
+out_free_cpufreq_table:
+	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_free_priv:
+	kfree(priv);
+out_free_opp:
+	dev_pm_opp_cpumask_remove_table(policy->cpus);
+
+	return ret;
+}
+
+static int scmi_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct scmi_data *priv = policy->driver_data;
+
+	cpufreq_cooling_unregister(priv->cdev);
+	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
+	kfree(priv);
+	dev_pm_opp_cpumask_remove_table(policy->related_cpus);
+
+	return 0;
+}
+
+static void scmi_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	struct scmi_data *priv = policy->driver_data;
+
+	priv->cdev = of_cpufreq_cooling_register(policy);
+}
+
+static struct cpufreq_driver scmi_cpufreq_driver = {
+	.name	= "scmi",
+	.flags	= CPUFREQ_STICKY | CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+		  CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify	= cpufreq_generic_frequency_table_verify,
+	.attr	= cpufreq_generic_attr,
+	.target_index	= scmi_cpufreq_set_target,
+	.get	= scmi_cpufreq_get_rate,
+	.init	= scmi_cpufreq_init,
+	.exit	= scmi_cpufreq_exit,
+	.ready	= scmi_cpufreq_ready,
+};
+
+static int scmi_cpufreq_probe(struct scmi_device *sdev)
+{
+	int ret;
+
+	handle = sdev->handle;
+
+	if (!handle || !handle->perf_ops)
+		return -ENODEV;
+
+	ret = cpufreq_register_driver(&scmi_cpufreq_driver);
+	if (ret) {
+		dev_err(&sdev->dev, "%s: registering cpufreq failed, err: %d\n",
+			__func__, ret);
+	}
+
+	return ret;
+}
+
+static void scmi_cpufreq_remove(struct scmi_device *sdev)
+{
+	cpufreq_unregister_driver(&scmi_cpufreq_driver);
+}
+
+static const struct scmi_device_id scmi_id_table[] = {
+	{ SCMI_PROTOCOL_PERF },
+	{ },
+};
+MODULE_DEVICE_TABLE(scmi, scmi_id_table);
+
+static struct scmi_driver scmi_cpufreq_drv = {
+	.name		= "scmi-cpufreq",
+	.probe		= scmi_cpufreq_probe,
+	.remove		= scmi_cpufreq_remove,
+	.id_table	= scmi_id_table,
+};
+module_scmi_driver(scmi_cpufreq_drv);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCMI CPUFreq interface driver");
+MODULE_LICENSE("GPL v2");