Merge tag 'cpufreq-arm-updates-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm

Pull cpufreq ARM updates for 6.2 from Viresh Kumar:

"- Generalize of_perf_domain_get_sharing_cpumask phandle format (Hector
   Martin).

 - New cpufreq driver for Apple SoC CPU P-states (Hector Martin).

 - Lots of Qualcomm cpufreq driver updates, that include CPU clock
   provider support, generic cleanups or reorganization, fixed a
   potential memleak and the return value of cpufreq_driver->get()
   (Manivannan Sadhasivam, and Chen Hui).

 - Few updates to Qualcomm cpufreq driver's DT bindings, that include
   support for CPU clock provider, fixing missing cache related
   properties, and support for QDU1000/QRU1000 (Manivannan Sadhasivam,
   Rob Herring, and Melody Olvera).

 - Add support for ti,am625 SoC and enable build of ti-cpufreq for
   ARCH_K3 (Dave Gerlach, and Vibhore Vardhan).

 - tegra186: Use flexible array to simplify memory allocation (Christophe
   JAILLET)."

* tag 'cpufreq-arm-updates-6.2' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm:
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add QDU1000/QRU1000 cpufreq
  cpufreq: tegra186: Use flexible array to simplify memory allocation
  cpufreq: apple-soc: Add new driver to control Apple SoC CPU P-states
  cpufreq: qcom-hw: Add CPU clock provider support
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add cpufreq clock provider
  cpufreq: qcom-hw: Fix the frequency returned by cpufreq_driver->get()
  cpufreq: qcom-hw: Fix memory leak in qcom_cpufreq_hw_read_lut()
  arm64: dts: ti: k3-am625-sk: Add 1.4GHz OPP
  cpufreq: ti: Enable ti-cpufreq for ARCH_K3
  arm64: dts: ti: k3-am625: Introduce operating-points table
  cpufreq: dt-platdev: Blacklist ti,am625 SoC
  cpufreq: ti-cpufreq: Add support for AM625
  dt-bindings: cpufreq: qcom: Add missing cache related properties
  cpufreq: qcom-hw: Move soc_data to struct qcom_cpufreq
  cpufreq: qcom-hw: Use cached dev pointer in probe()
  cpufreq: qcom-hw: Allocate qcom_cpufreq_data during probe
  cpufreq: qcom-hw: Remove un-necessary cpumask_empty() check
  cpufreq: Generalize of_perf_domain_get_sharing_cpumask phandle format

8 files changed, 543 insertions, 93 deletions

diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 82e5de1f6f8c..0a0352d8fa45 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -41,6 +41,15 @@ config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
 	  To compile this driver as a module, choose M here: the
 	  module will be called sun50i-cpufreq-nvmem.
 
+config ARM_APPLE_SOC_CPUFREQ
+	tristate "Apple Silicon SoC CPUFreq support"
+	depends on ARCH_APPLE || (COMPILE_TEST && 64BIT)
+	select PM_OPP
+	default ARCH_APPLE
+	help
+	  This adds the CPUFreq driver for Apple Silicon machines
+	  (e.g. Apple M1).
+
 config ARM_ARMADA_37XX_CPUFREQ
 	tristate "Armada 37xx CPUFreq support"
 	depends on ARCH_MVEBU && CPUFREQ_DT
@@ -340,8 +349,8 @@ config ARM_TEGRA194_CPUFREQ
 
 config ARM_TI_CPUFREQ
 	bool "Texas Instruments CPUFreq support"
-	depends on ARCH_OMAP2PLUS
-	default ARCH_OMAP2PLUS
+	depends on ARCH_OMAP2PLUS || ARCH_K3
+	default y
 	help
 	  This driver enables valid OPPs on the running platform based on
 	  values contained within the SoC in use. Enable this in order to
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 49b98c62c5af..32a7029e25ed 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_X86_AMD_FREQ_SENSITIVITY)	+= amd_freq_sensitivity.o
 
 ##################################################################################
 # ARM SoC drivers
+obj-$(CONFIG_ARM_APPLE_SOC_CPUFREQ)	+= apple-soc-cpufreq.o
 obj-$(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
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
new file mode 100644
index 000000000000..d1801281cdd9
--- /dev/null
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -0,0 +1,352 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Apple SoC CPU cluster performance state driver
+ *
+ * Copyright The Asahi Linux Contributors
+ *
+ * Based on scpi-cpufreq.c
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/delay.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+
+#define APPLE_DVFS_CMD			0x20
+#define APPLE_DVFS_CMD_BUSY		BIT(31)
+#define APPLE_DVFS_CMD_SET		BIT(25)
+#define APPLE_DVFS_CMD_PS2		GENMASK(16, 12)
+#define APPLE_DVFS_CMD_PS1		GENMASK(4, 0)
+
+/* Same timebase as CPU counter (24MHz) */
+#define APPLE_DVFS_LAST_CHG_TIME	0x38
+
+/*
+ * Apple ran out of bits and had to shift this in T8112...
+ */
+#define APPLE_DVFS_STATUS			0x50
+#define APPLE_DVFS_STATUS_CUR_PS_T8103		GENMASK(7, 4)
+#define APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103	4
+#define APPLE_DVFS_STATUS_TGT_PS_T8103		GENMASK(3, 0)
+#define APPLE_DVFS_STATUS_CUR_PS_T8112		GENMASK(9, 5)
+#define APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8112	5
+#define APPLE_DVFS_STATUS_TGT_PS_T8112		GENMASK(4, 0)
+
+/*
+ * Div is +1, base clock is 12MHz on existing SoCs.
+ * For documentation purposes. We use the OPP table to
+ * get the frequency.
+ */
+#define APPLE_DVFS_PLL_STATUS		0xc0
+#define APPLE_DVFS_PLL_FACTOR		0xc8
+#define APPLE_DVFS_PLL_FACTOR_MULT	GENMASK(31, 16)
+#define APPLE_DVFS_PLL_FACTOR_DIV	GENMASK(15, 0)
+
+#define APPLE_DVFS_TRANSITION_TIMEOUT 100
+
+struct apple_soc_cpufreq_info {
+	u64 max_pstate;
+	u64 cur_pstate_mask;
+	u64 cur_pstate_shift;
+};
+
+struct apple_cpu_priv {
+	struct device *cpu_dev;
+	void __iomem *reg_base;
+	const struct apple_soc_cpufreq_info *info;
+};
+
+static struct cpufreq_driver apple_soc_cpufreq_driver;
+
+static const struct apple_soc_cpufreq_info soc_t8103_info = {
+	.max_pstate = 15,
+	.cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8103,
+	.cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8103,
+};
+
+static const struct apple_soc_cpufreq_info soc_t8112_info = {
+	.max_pstate = 31,
+	.cur_pstate_mask = APPLE_DVFS_STATUS_CUR_PS_T8112,
+	.cur_pstate_shift = APPLE_DVFS_STATUS_CUR_PS_SHIFT_T8112,
+};
+
+static const struct apple_soc_cpufreq_info soc_default_info = {
+	.max_pstate = 15,
+	.cur_pstate_mask = 0, /* fallback */
+};
+
+static const struct of_device_id apple_soc_cpufreq_of_match[] = {
+	{
+		.compatible = "apple,t8103-cluster-cpufreq",
+		.data = &soc_t8103_info,
+	},
+	{
+		.compatible = "apple,t8112-cluster-cpufreq",
+		.data = &soc_t8112_info,
+	},
+	{
+		.compatible = "apple,cluster-cpufreq",
+		.data = &soc_default_info,
+	},
+	{}
+};
+
+static unsigned int apple_soc_cpufreq_get_rate(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+	struct apple_cpu_priv *priv = policy->driver_data;
+	struct cpufreq_frequency_table *p;
+	unsigned int pstate;
+
+	if (priv->info->cur_pstate_mask) {
+		u64 reg = readq_relaxed(priv->reg_base + APPLE_DVFS_STATUS);
+
+		pstate = (reg & priv->info->cur_pstate_mask) >>  priv->info->cur_pstate_shift;
+	} else {
+		/*
+		 * For the fallback case we might not know the layout of DVFS_STATUS,
+		 * so just use the command register value (which ignores boost limitations).
+		 */
+		u64 reg = readq_relaxed(priv->reg_base + APPLE_DVFS_CMD);
+
+		pstate = FIELD_GET(APPLE_DVFS_CMD_PS1, reg);
+	}
+
+	cpufreq_for_each_valid_entry(p, policy->freq_table)
+		if (p->driver_data == pstate)
+			return p->frequency;
+
+	dev_err(priv->cpu_dev, "could not find frequency for pstate %d\n",
+		pstate);
+	return 0;
+}
+
+static int apple_soc_cpufreq_set_target(struct cpufreq_policy *policy,
+					unsigned int index)
+{
+	struct apple_cpu_priv *priv = policy->driver_data;
+	unsigned int pstate = policy->freq_table[index].driver_data;
+	u64 reg;
+
+	/* Fallback for newer SoCs */
+	if (index > priv->info->max_pstate)
+		index = priv->info->max_pstate;
+
+	if (readq_poll_timeout_atomic(priv->reg_base + APPLE_DVFS_CMD, reg,
+				      !(reg & APPLE_DVFS_CMD_BUSY), 2,
+				      APPLE_DVFS_TRANSITION_TIMEOUT)) {
+		return -EIO;
+	}
+
+	reg &= ~(APPLE_DVFS_CMD_PS1 | APPLE_DVFS_CMD_PS2);
+	reg |= FIELD_PREP(APPLE_DVFS_CMD_PS1, pstate);
+	reg |= FIELD_PREP(APPLE_DVFS_CMD_PS2, pstate);
+	reg |= APPLE_DVFS_CMD_SET;
+
+	writeq_relaxed(reg, priv->reg_base + APPLE_DVFS_CMD);
+
+	return 0;
+}
+
+static unsigned int apple_soc_cpufreq_fast_switch(struct cpufreq_policy *policy,
+						  unsigned int target_freq)
+{
+	if (apple_soc_cpufreq_set_target(policy, policy->cached_resolved_idx) < 0)
+		return 0;
+
+	return policy->freq_table[policy->cached_resolved_idx].frequency;
+}
+
+static int apple_soc_cpufreq_find_cluster(struct cpufreq_policy *policy,
+					  void __iomem **reg_base,
+					  const struct apple_soc_cpufreq_info **info)
+{
+	struct of_phandle_args args;
+	const struct of_device_id *match;
+	int ret = 0;
+
+	ret = of_perf_domain_get_sharing_cpumask(policy->cpu, "performance-domains",
+						 "#performance-domain-cells",
+						 policy->cpus, &args);
+	if (ret < 0)
+		return ret;
+
+	match = of_match_node(apple_soc_cpufreq_of_match, args.np);
+	of_node_put(args.np);
+	if (!match)
+		return -ENODEV;
+
+	*info = match->data;
+
+	*reg_base = of_iomap(args.np, 0);
+	if (IS_ERR(*reg_base))
+		return PTR_ERR(*reg_base);
+
+	return 0;
+}
+
+static struct freq_attr *apple_soc_cpufreq_hw_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL, /* Filled in below if boost is enabled */
+	NULL,
+};
+
+static int apple_soc_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int ret, i;
+	unsigned int transition_latency;
+	void __iomem *reg_base;
+	struct device *cpu_dev;
+	struct apple_cpu_priv *priv;
+	const struct apple_soc_cpufreq_info *info;
+	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 = dev_pm_opp_of_add_table(cpu_dev);
+	if (ret < 0) {
+		dev_err(cpu_dev, "%s: failed to add OPP table: %d\n", __func__, ret);
+		return ret;
+	}
+
+	ret = apple_soc_cpufreq_find_cluster(policy, &reg_base, &info);
+	if (ret) {
+		dev_err(cpu_dev, "%s: failed to get cluster info: %d\n", __func__, ret);
+		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);
+		goto out_iounmap;
+	}
+
+	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;
+	}
+
+	/* Get OPP levels (p-state indexes) and stash them in driver_data */
+	for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		unsigned long rate = freq_table[i].frequency * 1000 + 999;
+		struct dev_pm_opp *opp = dev_pm_opp_find_freq_floor(cpu_dev, &rate);
+
+		if (IS_ERR(opp)) {
+			ret = PTR_ERR(opp);
+			goto out_free_cpufreq_table;
+		}
+		freq_table[i].driver_data = dev_pm_opp_get_level(opp);
+		dev_pm_opp_put(opp);
+	}
+
+	priv->cpu_dev = cpu_dev;
+	priv->reg_base = reg_base;
+	priv->info = info;
+	policy->driver_data = priv;
+	policy->freq_table = freq_table;
+
+	transition_latency = dev_pm_opp_get_max_transition_latency(cpu_dev);
+	if (!transition_latency)
+		transition_latency = CPUFREQ_ETERNAL;
+
+	policy->cpuinfo.transition_latency = transition_latency;
+	policy->dvfs_possible_from_any_cpu = true;
+	policy->fast_switch_possible = true;
+
+	if (policy_has_boost_freq(policy)) {
+		ret = cpufreq_enable_boost_support();
+		if (ret) {
+			dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
+		} else {
+			apple_soc_cpufreq_hw_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+			apple_soc_cpufreq_driver.boost_enabled = true;
+		}
+	}
+
+	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_remove_all_dynamic(cpu_dev);
+out_iounmap:
+	iounmap(reg_base);
+	return ret;
+}
+
+static int apple_soc_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct apple_cpu_priv *priv = policy->driver_data;
+
+	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
+	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+	iounmap(priv->reg_base);
+	kfree(priv);
+
+	return 0;
+}
+
+static struct cpufreq_driver apple_soc_cpufreq_driver = {
+	.name		= "apple-cpufreq",
+	.flags		= CPUFREQ_HAVE_GOVERNOR_PER_POLICY |
+			  CPUFREQ_NEED_INITIAL_FREQ_CHECK | CPUFREQ_IS_COOLING_DEV,
+	.verify		= cpufreq_generic_frequency_table_verify,
+	.attr		= cpufreq_generic_attr,
+	.get		= apple_soc_cpufreq_get_rate,
+	.init		= apple_soc_cpufreq_init,
+	.exit		= apple_soc_cpufreq_exit,
+	.target_index	= apple_soc_cpufreq_set_target,
+	.fast_switch	= apple_soc_cpufreq_fast_switch,
+	.register_em	= cpufreq_register_em_with_opp,
+	.attr		= apple_soc_cpufreq_hw_attr,
+};
+
+static int __init apple_soc_cpufreq_module_init(void)
+{
+	if (!of_machine_is_compatible("apple,arm-platform"))
+		return -ENODEV;
+
+	return cpufreq_register_driver(&apple_soc_cpufreq_driver);
+}
+module_init(apple_soc_cpufreq_module_init);
+
+static void __exit apple_soc_cpufreq_module_exit(void)
+{
+	cpufreq_unregister_driver(&apple_soc_cpufreq_driver);
+}
+module_exit(apple_soc_cpufreq_module_exit);
+
+MODULE_DEVICE_TABLE(of, apple_soc_cpufreq_of_match);
+MODULE_AUTHOR("Hector Martin <marcan@marcan.st>");
+MODULE_DESCRIPTION("Apple SoC CPU cluster DVFS driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 6ac3800db450..8ab672883043 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -103,6 +103,8 @@ static const struct of_device_id allowlist[] __initconst = {
 static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "allwinner,sun50i-h6", },
 
+	{ .compatible = "apple,arm-platform", },
+
 	{ .compatible = "arm,vexpress", },
 
 	{ .compatible = "calxeda,highbank", },
@@ -160,6 +162,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "ti,am43", },
 	{ .compatible = "ti,dra7", },
 	{ .compatible = "ti,omap3", },
+	{ .compatible = "ti,am625", },
 
 	{ .compatible = "qcom,ipq8064", },
 	{ .compatible = "qcom,apq8064", },
diff --git a/drivers/cpufreq/mediatek-cpufreq-hw.c b/drivers/cpufreq/mediatek-cpufreq-hw.c
index f0e0a35c7f21..f80339779084 100644
--- a/drivers/cpufreq/mediatek-cpufreq-hw.c
+++ b/drivers/cpufreq/mediatek-cpufreq-hw.c
@@ -160,6 +160,7 @@ static int mtk_cpu_resources_init(struct platform_device *pdev,
 	struct mtk_cpufreq_data *data;
 	struct device *dev = &pdev->dev;
 	struct resource *res;
+	struct of_phandle_args args;
 	void __iomem *base;
 	int ret, i;
 	int index;
@@ -168,11 +169,14 @@ static int mtk_cpu_resources_init(struct platform_device *pdev,
 	if (!data)
 		return -ENOMEM;
 
-	index = of_perf_domain_get_sharing_cpumask(policy->cpu, "performance-domains",
-						   "#performance-domain-cells",
-						   policy->cpus);
-	if (index < 0)
-		return index;
+	ret = of_perf_domain_get_sharing_cpumask(policy->cpu, "performance-domains",
+						 "#performance-domain-cells",
+						 policy->cpus, &args);
+	if (ret < 0)
+		return ret;
+
+	index = args.args[0];
+	of_node_put(args.np);
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, index);
 	if (!res) {
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 833589bc95e4..340fed35e45d 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -4,6 +4,7 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/clk-provider.h>
 #include <linux/cpufreq.h>
 #include <linux/init.h>
 #include <linux/interconnect.h>
@@ -43,7 +44,6 @@ struct qcom_cpufreq_soc_data {
 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
@@ -55,12 +55,18 @@ struct qcom_cpufreq_data {
 	bool cancel_throttle;
 	struct delayed_work throttle_work;
 	struct cpufreq_policy *policy;
+	struct clk_hw cpu_clk;
 
 	bool per_core_dcvs;
 
 	struct freq_qos_request throttle_freq_req;
 };
 
+static struct {
+	struct qcom_cpufreq_data *data;
+	const struct qcom_cpufreq_soc_data *soc_data;
+} qcom_cpufreq;
+
 static unsigned long cpu_hw_rate, xo_rate;
 static bool icc_scaling_enabled;
 
@@ -109,7 +115,7 @@ static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
 					unsigned int index)
 {
 	struct qcom_cpufreq_data *data = policy->driver_data;
-	const struct qcom_cpufreq_soc_data *soc_data = data->soc_data;
+	const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data;
 	unsigned long freq = policy->freq_table[index].frequency;
 	unsigned int i;
 
@@ -125,9 +131,37 @@ static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
 	return 0;
 }
 
+static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
+{
+	unsigned int lval;
+
+	if (qcom_cpufreq.soc_data->reg_current_vote)
+		lval = readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_current_vote) & 0x3ff;
+	else
+		lval = readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_domain_state) & 0xff;
+
+	return lval * xo_rate;
+}
+
+/* Get the current frequency of the CPU (after throttling) */
 static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
 {
 	struct qcom_cpufreq_data *data;
+	struct cpufreq_policy *policy;
+
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (!policy)
+		return 0;
+
+	data = policy->driver_data;
+
+	return qcom_lmh_get_throttle_freq(data) / HZ_PER_KHZ;
+}
+
+/* Get the frequency requested by the cpufreq core for the CPU */
+static unsigned int qcom_cpufreq_get_freq(unsigned int cpu)
+{
+	struct qcom_cpufreq_data *data;
 	const struct qcom_cpufreq_soc_data *soc_data;
 	struct cpufreq_policy *policy;
 	unsigned int index;
@@ -137,7 +171,7 @@ static unsigned int qcom_cpufreq_hw_get(unsigned int cpu)
 		return 0;
 
 	data = policy->driver_data;
-	soc_data = data->soc_data;
+	soc_data = qcom_cpufreq.soc_data;
 
 	index = readl_relaxed(data->base + soc_data->reg_perf_state);
 	index = min(index, LUT_MAX_ENTRIES - 1);
@@ -149,7 +183,7 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 						unsigned int target_freq)
 {
 	struct qcom_cpufreq_data *data = policy->driver_data;
-	const struct qcom_cpufreq_soc_data *soc_data = data->soc_data;
+	const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data;
 	unsigned int index;
 	unsigned int i;
 
@@ -173,7 +207,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 	unsigned long rate;
 	int ret;
 	struct qcom_cpufreq_data *drv_data = policy->driver_data;
-	const struct qcom_cpufreq_soc_data *soc_data = drv_data->soc_data;
+	const struct qcom_cpufreq_soc_data *soc_data = qcom_cpufreq.soc_data;
 
 	table = kcalloc(LUT_MAX_ENTRIES + 1, sizeof(*table), GFP_KERNEL);
 	if (!table)
@@ -193,6 +227,7 @@ static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
 		}
 	} else if (ret != -ENODEV) {
 		dev_err(cpu_dev, "Invalid opp table in device tree\n");
+		kfree(table);
 		return ret;
 	} else {
 		policy->fast_switch_possible = true;
@@ -286,18 +321,6 @@ static void qcom_get_related_cpus(int index, struct cpumask *m)
 	}
 }
 
-static unsigned long qcom_lmh_get_throttle_freq(struct qcom_cpufreq_data *data)
-{
-	unsigned int lval;
-
-	if (data->soc_data->reg_current_vote)
-		lval = readl_relaxed(data->base + data->soc_data->reg_current_vote) & 0x3ff;
-	else
-		lval = readl_relaxed(data->base + data->soc_data->reg_domain_state) & 0xff;
-
-	return lval * xo_rate;
-}
-
 static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 {
 	struct cpufreq_policy *policy = data->policy;
@@ -341,7 +364,7 @@ static void qcom_lmh_dcvs_notify(struct qcom_cpufreq_data *data)
 	 * 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))
+	if (throttled_freq >= qcom_cpufreq_get_freq(cpu))
 		enable_irq(data->throttle_irq);
 	else
 		mod_delayed_work(system_highpri_wq, &data->throttle_work,
@@ -367,9 +390,9 @@ static irqreturn_t qcom_lmh_dcvs_handle_irq(int irq, void *data)
 	disable_irq_nosync(c_data->throttle_irq);
 	schedule_delayed_work(&c_data->throttle_work, 0);
 
-	if (c_data->soc_data->reg_intr_clr)
+	if (qcom_cpufreq.soc_data->reg_intr_clr)
 		writel_relaxed(GT_IRQ_STATUS,
-			       c_data->base + c_data->soc_data->reg_intr_clr);
+			       c_data->base + qcom_cpufreq.soc_data->reg_intr_clr);
 
 	return IRQ_HANDLED;
 }
@@ -503,8 +526,6 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	struct of_phandle_args args;
 	struct device_node *cpu_np;
 	struct device *cpu_dev;
-	struct resource *res;
-	void __iomem *base;
 	struct qcom_cpufreq_data *data;
 	int ret, index;
 
@@ -526,51 +547,18 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 		return ret;
 
 	index = args.args[0];
-
-	res = platform_get_resource(pdev, IORESOURCE_MEM, index);
-	if (!res) {
-		dev_err(dev, "failed to get mem resource %d\n", index);
-		return -ENODEV;
-	}
-
-	if (!request_mem_region(res->start, resource_size(res), res->name)) {
-		dev_err(dev, "failed to request resource %pR\n", res);
-		return -EBUSY;
-	}
-
-	base = ioremap(res->start, resource_size(res));
-	if (!base) {
-		dev_err(dev, "failed to map resource %pR\n", res);
-		ret = -ENOMEM;
-		goto release_region;
-	}
-
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
-	if (!data) {
-		ret = -ENOMEM;
-		goto unmap_base;
-	}
-
-	data->soc_data = of_device_get_match_data(&pdev->dev);
-	data->base = base;
-	data->res = res;
+	data = &qcom_cpufreq.data[index];
 
 	/* HW should be in enabled state to proceed */
-	if (!(readl_relaxed(base + data->soc_data->reg_enable) & 0x1)) {
+	if (!(readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_enable) & 0x1)) {
 		dev_err(dev, "Domain-%d cpufreq hardware not enabled\n", index);
-		ret = -ENODEV;
-		goto error;
+		return -ENODEV;
 	}
 
-	if (readl_relaxed(base + data->soc_data->reg_dcvs_ctrl) & 0x1)
+	if (readl_relaxed(data->base + qcom_cpufreq.soc_data->reg_dcvs_ctrl) & 0x1)
 		data->per_core_dcvs = true;
 
 	qcom_get_related_cpus(index, policy->cpus);
-	if (cpumask_empty(policy->cpus)) {
-		dev_err(dev, "Domain-%d failed to get related CPUs\n", index);
-		ret = -ENOENT;
-		goto error;
-	}
 
 	policy->driver_data = data;
 	policy->dvfs_possible_from_any_cpu = true;
@@ -578,14 +566,13 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 	ret = qcom_cpufreq_hw_read_lut(cpu_dev, policy);
 	if (ret) {
 		dev_err(dev, "Domain-%d failed to read LUT\n", index);
-		goto error;
+		return ret;
 	}
 
 	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;
+		return -ENODEV;
 	}
 
 	if (policy_has_boost_freq(policy)) {
@@ -594,18 +581,7 @@ static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy)
 			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);
-unmap_base:
-	iounmap(base);
-release_region:
-	release_mem_region(res->start, resource_size(res));
-	return ret;
+	return qcom_cpufreq_hw_lmh_init(policy, index);
 }
 
 static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy)
@@ -658,20 +634,33 @@ static struct cpufreq_driver cpufreq_qcom_hw_driver = {
 	.ready		= qcom_cpufreq_ready,
 };
 
+static unsigned long qcom_cpufreq_hw_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
+{
+	struct qcom_cpufreq_data *data = container_of(hw, struct qcom_cpufreq_data, cpu_clk);
+
+	return qcom_lmh_get_throttle_freq(data);
+}
+
+static const struct clk_ops qcom_cpufreq_hw_clk_ops = {
+	.recalc_rate = qcom_cpufreq_hw_recalc_rate,
+};
+
 static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
 {
+	struct clk_hw_onecell_data *clk_data;
+	struct device *dev = &pdev->dev;
 	struct device *cpu_dev;
 	struct clk *clk;
-	int ret;
+	int ret, i, num_domains;
 
-	clk = clk_get(&pdev->dev, "xo");
+	clk = clk_get(dev, "xo");
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
 	xo_rate = clk_get_rate(clk);
 	clk_put(clk);
 
-	clk = clk_get(&pdev->dev, "alternate");
+	clk = clk_get(dev, "alternate");
 	if (IS_ERR(clk))
 		return PTR_ERR(clk);
 
@@ -689,11 +678,70 @@ static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	/* Allocate qcom_cpufreq_data based on the available frequency domains in DT */
+	num_domains = of_property_count_elems_of_size(dev->of_node, "reg", sizeof(u32) * 4);
+	if (num_domains <= 0)
+		return num_domains;
+
+	qcom_cpufreq.data = devm_kzalloc(dev, sizeof(struct qcom_cpufreq_data) * num_domains,
+					 GFP_KERNEL);
+	if (!qcom_cpufreq.data)
+		return -ENOMEM;
+
+	qcom_cpufreq.soc_data = of_device_get_match_data(dev);
+
+	clk_data = devm_kzalloc(dev, struct_size(clk_data, hws, num_domains), GFP_KERNEL);
+	if (!clk_data)
+		return -ENOMEM;
+
+	clk_data->num = num_domains;
+
+	for (i = 0; i < num_domains; i++) {
+		struct qcom_cpufreq_data *data = &qcom_cpufreq.data[i];
+		struct clk_init_data clk_init = {};
+		struct resource *res;
+		void __iomem *base;
+
+		base = devm_platform_get_and_ioremap_resource(pdev, i, &res);
+		if (IS_ERR(base)) {
+			dev_err(dev, "Failed to map resource %pR\n", res);
+			return PTR_ERR(base);
+		}
+
+		data->base = base;
+		data->res = res;
+
+		/* Register CPU clock for each frequency domain */
+		clk_init.name = kasprintf(GFP_KERNEL, "qcom_cpufreq%d", i);
+		if (!clk_init.name)
+			return -ENOMEM;
+
+		clk_init.flags = CLK_GET_RATE_NOCACHE;
+		clk_init.ops = &qcom_cpufreq_hw_clk_ops;
+		data->cpu_clk.init = &clk_init;
+
+		ret = devm_clk_hw_register(dev, &data->cpu_clk);
+		if (ret < 0) {
+			dev_err(dev, "Failed to register clock %d: %d\n", i, ret);
+			kfree(clk_init.name);
+			return ret;
+		}
+
+		clk_data->hws[i] = &data->cpu_clk;
+		kfree(clk_init.name);
+	}
+
+	ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_onecell_get, clk_data);
+	if (ret < 0) {
+		dev_err(dev, "Failed to add clock provider\n");
+		return ret;
+	}
+
 	ret = cpufreq_register_driver(&cpufreq_qcom_hw_driver);
 	if (ret)
-		dev_err(&pdev->dev, "CPUFreq HW driver failed to register\n");
+		dev_err(dev, "CPUFreq HW driver failed to register\n");
 	else
-		dev_dbg(&pdev->dev, "QCOM CPUFreq HW driver initialized\n");
+		dev_dbg(dev, "QCOM CPUFreq HW driver initialized\n");
 
 	return ret;
 }
diff --git a/drivers/cpufreq/tegra186-cpufreq.c b/drivers/cpufreq/tegra186-cpufreq.c
index 6c88827f4e62..f98f53bf1011 100644
--- a/drivers/cpufreq/tegra186-cpufreq.c
+++ b/drivers/cpufreq/tegra186-cpufreq.c
@@ -65,8 +65,8 @@ struct tegra186_cpufreq_cluster {
 
 struct tegra186_cpufreq_data {
 	void __iomem *regs;
-	struct tegra186_cpufreq_cluster *clusters;
 	const struct tegra186_cpufreq_cpu *cpus;
+	struct tegra186_cpufreq_cluster clusters[];
 };
 
 static int tegra186_cpufreq_init(struct cpufreq_policy *policy)
@@ -221,15 +221,12 @@ static int tegra186_cpufreq_probe(struct platform_device *pdev)
 	struct tegra_bpmp *bpmp;
 	unsigned int i = 0, err;
 
-	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
+	data = devm_kzalloc(&pdev->dev,
+			    struct_size(data, clusters, TEGRA186_NUM_CLUSTERS),
+			    GFP_KERNEL);
 	if (!data)
 		return -ENOMEM;
 
-	data->clusters = devm_kcalloc(&pdev->dev, TEGRA186_NUM_CLUSTERS,
-				      sizeof(*data->clusters), GFP_KERNEL);
-	if (!data->clusters)
-		return -ENOMEM;
-
 	data->cpus = tegra186_cpus;
 
 	bpmp = tegra_bpmp_get(&pdev->dev);
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index f64180dd2005..be4209d97cb3 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -39,6 +39,14 @@
 #define OMAP34xx_ProdID_SKUID			0x4830A20C
 #define OMAP3_SYSCON_BASE	(0x48000000 + 0x2000 + 0x270)
 
+#define AM625_EFUSE_K_MPU_OPP			11
+#define AM625_EFUSE_S_MPU_OPP			19
+#define AM625_EFUSE_T_MPU_OPP			20
+
+#define AM625_SUPPORT_K_MPU_OPP			BIT(0)
+#define AM625_SUPPORT_S_MPU_OPP			BIT(1)
+#define AM625_SUPPORT_T_MPU_OPP			BIT(2)
+
 #define VERSION_COUNT				2
 
 struct ti_cpufreq_data;
@@ -104,6 +112,25 @@ static unsigned long omap3_efuse_xlate(struct ti_cpufreq_data *opp_data,
 	return BIT(efuse);
 }
 
+static unsigned long am625_efuse_xlate(struct ti_cpufreq_data *opp_data,
+				       unsigned long efuse)
+{
+	unsigned long calculated_efuse = AM625_SUPPORT_K_MPU_OPP;
+
+	switch (efuse) {
+	case AM625_EFUSE_T_MPU_OPP:
+		calculated_efuse |= AM625_SUPPORT_T_MPU_OPP;
+		fallthrough;
+	case AM625_EFUSE_S_MPU_OPP:
+		calculated_efuse |= AM625_SUPPORT_S_MPU_OPP;
+		fallthrough;
+	case AM625_EFUSE_K_MPU_OPP:
+		calculated_efuse |= AM625_SUPPORT_K_MPU_OPP;
+	}
+
+	return calculated_efuse;
+}
+
 static struct ti_cpufreq_soc_data am3x_soc_data = {
 	.efuse_xlate = amx3_efuse_xlate,
 	.efuse_fallback = AM33XX_800M_ARM_MPU_MAX_FREQ,
@@ -198,6 +225,14 @@ static struct ti_cpufreq_soc_data am3517_soc_data = {
 	.multi_regulator = false,
 };
 
+static struct ti_cpufreq_soc_data am625_soc_data = {
+	.efuse_xlate = am625_efuse_xlate,
+	.efuse_offset = 0x0018,
+	.efuse_mask = 0x07c0,
+	.efuse_shift = 0x6,
+	.rev_offset = 0x0014,
+	.multi_regulator = false,
+};
 
 /**
  * ti_cpufreq_get_efuse() - Parse and return efuse value present on SoC
@@ -301,6 +336,7 @@ static const struct of_device_id ti_cpufreq_of_match[] = {
 	{ .compatible = "ti,dra7", .data = &dra7_soc_data },
 	{ .compatible = "ti,omap34xx", .data = &omap34xx_soc_data, },
 	{ .compatible = "ti,omap36xx", .data = &omap36xx_soc_data, },
+	{ .compatible = "ti,am625", .data = &am625_soc_data, },
 	/* legacy */
 	{ .compatible = "ti,omap3430", .data = &omap34xx_soc_data, },
 	{ .compatible = "ti,omap3630", .data = &omap36xx_soc_data, },