Merge tag 'cpufreq-arm-updates-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm

Merge ARM cpufreq updates for 6.7 from Viresh Kumar:

"- Add support for several Qualcomm SoC versions and other similar
   changes (Christian Marangi, Dmitry Baryshkov, Luca Weiss, Neil
   Armstrong, Richard Acayan, Robert Marko, Rohit Agarwal, Stephan
   Gerhold and Varadarajan Narayanan).

 - Cleanups to the tegra cpufreq driver (Sumit Gupta).

 - Use of_property_read_reg() to parse "reg" in pmac32 driver (Rob Herring).

 - Add support for TI's am62p5 Soc (Bryan Brattlof).

 - Make ARM_BRCMSTB_AVS_CPUFREQ depends on !ARM_SCMI_CPUFREQ (Florian
   Fainelli).

 - Update Kconfig to mention i.MX7 as well (Alexander Stein)."

* tag 'cpufreq-arm-updates-6.7' of git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm: (25 commits)
  dt-bindings: cpufreq: qcom-hw: document SM8650 CPUFREQ Hardware
  cpufreq: arm: Kconfig: Add i.MX7 to supported SoC for ARM_IMX_CPUFREQ_DT
  cpufreq: qcom-nvmem: add support for IPQ8064
  cpufreq: qcom-nvmem: also accept operating-points-v2-krait-cpu
  cpufreq: qcom-nvmem: drop pvs_ver for format a fuses
  dt-bindings: cpufreq: qcom-cpufreq-nvmem: Document krait-cpu
  cpufreq: qcom-nvmem: add support for IPQ6018
  dt-bindings: cpufreq: qcom-cpufreq-nvmem: document IPQ6018
  cpufreq: qcom-nvmem: Add MSM8909
  cpufreq: qcom-nvmem: Simplify driver data allocation
  dt-bindings: cpufreq: cpufreq-qcom-hw: Add SDX75 compatible
  cpufreq: ARM_BRCMSTB_AVS_CPUFREQ cannot be used with ARM_SCMI_CPUFREQ
  cpufreq: ti-cpufreq: Add opp support for am62p5 SoCs
  cpufreq: dt-platdev: add am62p5 to blocklist
  cpufreq: tegra194: remove redundant AND with cpu_online_mask
  cpufreq: tegra194: use refclk delta based loop instead of udelay
  cpufreq: tegra194: save CPU data to avoid repeated SMP calls
  dt-bindings: cpufreq: cpufreq-qcom-hw: add SDM670 compatible
  dt-bindings: cpufreq: qcom-nvmem: Document MSM8909
  cpufreq: dt: platdev: Add MSM8909 to blocklist
  ...

6 files changed, 291 insertions, 88 deletions

diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 123b4bbfcfee1..f911606897b8d 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -90,7 +90,7 @@ config ARM_VEXPRESS_SPC_CPUFREQ
 
 config ARM_BRCMSTB_AVS_CPUFREQ
 	tristate "Broadcom STB AVS CPUfreq driver"
-	depends on ARCH_BRCMSTB || COMPILE_TEST
+	depends on (ARCH_BRCMSTB && !ARM_SCMI_CPUFREQ) || COMPILE_TEST
 	default y
 	help
 	  Some Broadcom STB SoCs use a co-processor running proprietary firmware
@@ -124,8 +124,8 @@ config ARM_IMX_CPUFREQ_DT
 	tristate "Freescale i.MX8M cpufreq support"
 	depends on ARCH_MXC && CPUFREQ_DT
 	help
-	  This adds cpufreq driver support for Freescale i.MX8M series SoCs,
-	  based on cpufreq-dt.
+	  This adds cpufreq driver support for Freescale i.MX7/i.MX8M
+	  series SoCs, based on cpufreq-dt.
 
 	  If in doubt, say N.
 
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index fb2875ce1fdd5..11b3e34b76961 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -142,9 +142,11 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "nvidia,tegra234", },
 
 	{ .compatible = "qcom,apq8096", },
+	{ .compatible = "qcom,msm8909", },
 	{ .compatible = "qcom,msm8996", },
 	{ .compatible = "qcom,msm8998", },
 	{ .compatible = "qcom,qcm2290", },
+	{ .compatible = "qcom,qcm6490", },
 	{ .compatible = "qcom,qcs404", },
 	{ .compatible = "qcom,qdu1000", },
 	{ .compatible = "qcom,sa8155p" },
@@ -176,7 +178,9 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "ti,omap3", },
 	{ .compatible = "ti,am625", },
 	{ .compatible = "ti,am62a7", },
+	{ .compatible = "ti,am62p5", },
 
+	{ .compatible = "qcom,ipq6018", },
 	{ .compatible = "qcom,ipq8064", },
 	{ .compatible = "qcom,apq8064", },
 	{ .compatible = "qcom,msm8974", },
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c
index ec75e79659ace..df3567c1e93b7 100644
--- a/drivers/cpufreq/pmac32-cpufreq.c
+++ b/drivers/cpufreq/pmac32-cpufreq.c
@@ -24,6 +24,7 @@
 #include <linux/device.h>
 #include <linux/hardirq.h>
 #include <linux/of.h>
+#include <linux/of_address.h>
 
 #include <asm/machdep.h>
 #include <asm/irq.h>
@@ -378,10 +379,9 @@ static int pmac_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 static u32 read_gpio(struct device_node *np)
 {
-	const u32 *reg = of_get_property(np, "reg", NULL);
-	u32 offset;
+	u64 offset;
 
-	if (reg == NULL)
+	if (of_property_read_reg(np, 0, &offset, NULL) < 0)
 		return 0;
 	/* That works for all keylargos but shall be fixed properly
 	 * some day... The problem is that it seems we can't rely
@@ -389,7 +389,6 @@ static u32 read_gpio(struct device_node *np)
 	 * relative to the base of KeyLargo or to the base of the
 	 * GPIO space, and the device-tree doesn't help.
 	 */
-	offset = *reg;
 	if (offset < KEYLARGO_GPIO_LEVELS0)
 		offset += KEYLARGO_GPIO_LEVELS0;
 	return offset;
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index 84d7033e5efe8..15367ac08b2b8 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -30,6 +30,14 @@
 
 #include <dt-bindings/arm/qcom,ids.h>
 
+enum ipq806x_versions {
+	IPQ8062_VERSION = 0,
+	IPQ8064_VERSION,
+	IPQ8065_VERSION,
+};
+
+#define IPQ6000_VERSION	BIT(2)
+
 struct qcom_cpufreq_drv;
 
 struct qcom_cpufreq_match_data {
@@ -40,16 +48,38 @@ struct qcom_cpufreq_match_data {
 	const char **genpd_names;
 };
 
+struct qcom_cpufreq_drv_cpu {
+	int opp_token;
+};
+
 struct qcom_cpufreq_drv {
-	int *opp_tokens;
 	u32 versions;
 	const struct qcom_cpufreq_match_data *data;
+	struct qcom_cpufreq_drv_cpu cpus[];
 };
 
 static struct platform_device *cpufreq_dt_pdev, *cpufreq_pdev;
 
+static int qcom_cpufreq_simple_get_version(struct device *cpu_dev,
+					   struct nvmem_cell *speedbin_nvmem,
+					   char **pvs_name,
+					   struct qcom_cpufreq_drv *drv)
+{
+	u8 *speedbin;
+
+	*pvs_name = NULL;
+	speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
+
+	dev_dbg(cpu_dev, "speedbin: %d\n", *speedbin);
+	drv->versions = 1 << *speedbin;
+	kfree(speedbin);
+	return 0;
+}
+
 static void get_krait_bin_format_a(struct device *cpu_dev,
-					  int *speed, int *pvs, int *pvs_ver,
+					  int *speed, int *pvs,
 					  u8 *buf)
 {
 	u32 pte_efuse;
@@ -180,8 +210,7 @@ static int qcom_cpufreq_krait_name_version(struct device *cpu_dev,
 
 	switch (len) {
 	case 4:
-		get_krait_bin_format_a(cpu_dev, &speed, &pvs, &pvs_ver,
-				       speedbin);
+		get_krait_bin_format_a(cpu_dev, &speed, &pvs, speedbin);
 		break;
 	case 8:
 		get_krait_bin_format_b(cpu_dev, &speed, &pvs, &pvs_ver,
@@ -203,6 +232,114 @@ len_error:
 	return ret;
 }
 
+static int qcom_cpufreq_ipq8064_name_version(struct device *cpu_dev,
+					     struct nvmem_cell *speedbin_nvmem,
+					     char **pvs_name,
+					     struct qcom_cpufreq_drv *drv)
+{
+	int speed = 0, pvs = 0;
+	int msm_id, ret = 0;
+	u8 *speedbin;
+	size_t len;
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
+
+	if (len != 4) {
+		dev_err(cpu_dev, "Unable to read nvmem data. Defaulting to 0!\n");
+		ret = -ENODEV;
+		goto exit;
+	}
+
+	get_krait_bin_format_a(cpu_dev, &speed, &pvs, speedbin);
+
+	ret = qcom_smem_get_soc_id(&msm_id);
+	if (ret)
+		goto exit;
+
+	switch (msm_id) {
+	case QCOM_ID_IPQ8062:
+		drv->versions = BIT(IPQ8062_VERSION);
+		break;
+	case QCOM_ID_IPQ8064:
+	case QCOM_ID_IPQ8066:
+	case QCOM_ID_IPQ8068:
+		drv->versions = BIT(IPQ8064_VERSION);
+		break;
+	case QCOM_ID_IPQ8065:
+	case QCOM_ID_IPQ8069:
+		drv->versions = BIT(IPQ8065_VERSION);
+		break;
+	default:
+		dev_err(cpu_dev,
+			"SoC ID %u is not part of IPQ8064 family, limiting to 1.0GHz!\n",
+			msm_id);
+		drv->versions = BIT(IPQ8062_VERSION);
+		break;
+	}
+
+	/* IPQ8064 speed is never fused. Only pvs values are fused. */
+	snprintf(*pvs_name, sizeof("speed0-pvsXX"), "speed0-pvs%d", pvs);
+
+exit:
+	kfree(speedbin);
+	return ret;
+}
+
+static int qcom_cpufreq_ipq6018_name_version(struct device *cpu_dev,
+					     struct nvmem_cell *speedbin_nvmem,
+					     char **pvs_name,
+					     struct qcom_cpufreq_drv *drv)
+{
+	u32 msm_id;
+	int ret;
+	u8 *speedbin;
+	*pvs_name = NULL;
+
+	ret = qcom_smem_get_soc_id(&msm_id);
+	if (ret)
+		return ret;
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, NULL);
+	if (IS_ERR(speedbin))
+		return PTR_ERR(speedbin);
+
+	switch (msm_id) {
+	case QCOM_ID_IPQ6005:
+	case QCOM_ID_IPQ6010:
+	case QCOM_ID_IPQ6018:
+	case QCOM_ID_IPQ6028:
+		/* Fuse Value    Freq    BIT to set
+		 * ---------------------------------
+		 *   2’b0     No Limit     BIT(0)
+		 *   2’b1     1.5 GHz      BIT(1)
+		 */
+		drv->versions = 1 << (unsigned int)(*speedbin);
+		break;
+	case QCOM_ID_IPQ6000:
+		/*
+		 * IPQ6018 family only has one bit to advertise the CPU
+		 * speed-bin, but that is not enough for IPQ6000 which
+		 * is only rated up to 1.2GHz.
+		 * So for IPQ6000 manually set BIT(2) based on SMEM ID.
+		 */
+		drv->versions = IPQ6000_VERSION;
+		break;
+	default:
+		dev_err(cpu_dev,
+			"SoC ID %u is not part of IPQ6018 family, limiting to 1.2GHz!\n",
+			msm_id);
+		drv->versions = IPQ6000_VERSION;
+		break;
+	}
+
+	kfree(speedbin);
+	return 0;
+}
+
+static const char *generic_genpd_names[] = { "perf", NULL };
+
 static const struct qcom_cpufreq_match_data match_data_kryo = {
 	.get_version = qcom_cpufreq_kryo_name_version,
 };
@@ -211,12 +348,25 @@ static const struct qcom_cpufreq_match_data match_data_krait = {
 	.get_version = qcom_cpufreq_krait_name_version,
 };
 
+static const struct qcom_cpufreq_match_data match_data_msm8909 = {
+	.get_version = qcom_cpufreq_simple_get_version,
+	.genpd_names = generic_genpd_names,
+};
+
 static const char *qcs404_genpd_names[] = { "cpr", NULL };
 
 static const struct qcom_cpufreq_match_data match_data_qcs404 = {
 	.genpd_names = qcs404_genpd_names,
 };
 
+static const struct qcom_cpufreq_match_data match_data_ipq6018 = {
+	.get_version = qcom_cpufreq_ipq6018_name_version,
+};
+
+static const struct qcom_cpufreq_match_data match_data_ipq8064 = {
+	.get_version = qcom_cpufreq_ipq8064_name_version,
+};
+
 static int qcom_cpufreq_probe(struct platform_device *pdev)
 {
 	struct qcom_cpufreq_drv *drv;
@@ -237,48 +387,39 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 	if (!np)
 		return -ENOENT;
 
-	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
+	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu") ||
+	      of_device_is_compatible(np, "operating-points-v2-krait-cpu");
 	if (!ret) {
 		of_node_put(np);
 		return -ENOENT;
 	}
 
-	drv = kzalloc(sizeof(*drv), GFP_KERNEL);
+	drv = devm_kzalloc(&pdev->dev, struct_size(drv, cpus, num_possible_cpus()),
+		           GFP_KERNEL);
 	if (!drv)
 		return -ENOMEM;
 
 	match = pdev->dev.platform_data;
 	drv->data = match->data;
-	if (!drv->data) {
-		ret = -ENODEV;
-		goto free_drv;
-	}
+	if (!drv->data)
+		return -ENODEV;
 
 	if (drv->data->get_version) {
 		speedbin_nvmem = of_nvmem_cell_get(np, NULL);
-		if (IS_ERR(speedbin_nvmem)) {
-			ret = dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
-					    "Could not get nvmem cell\n");
-			goto free_drv;
-		}
+		if (IS_ERR(speedbin_nvmem))
+			return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
+					     "Could not get nvmem cell\n");
 
 		ret = drv->data->get_version(cpu_dev,
 							speedbin_nvmem, &pvs_name, drv);
 		if (ret) {
 			nvmem_cell_put(speedbin_nvmem);
-			goto free_drv;
+			return ret;
 		}
 		nvmem_cell_put(speedbin_nvmem);
 	}
 	of_node_put(np);
 
-	drv->opp_tokens = kcalloc(num_possible_cpus(), sizeof(*drv->opp_tokens),
-				  GFP_KERNEL);
-	if (!drv->opp_tokens) {
-		ret = -ENOMEM;
-		goto free_drv;
-	}
-
 	for_each_possible_cpu(cpu) {
 		struct dev_pm_opp_config config = {
 			.supported_hw = NULL,
@@ -304,9 +445,9 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 		}
 
 		if (config.supported_hw || config.genpd_names) {
-			drv->opp_tokens[cpu] = dev_pm_opp_set_config(cpu_dev, &config);
-			if (drv->opp_tokens[cpu] < 0) {
-				ret = drv->opp_tokens[cpu];
+			drv->cpus[cpu].opp_token = dev_pm_opp_set_config(cpu_dev, &config);
+			if (drv->cpus[cpu].opp_token < 0) {
+				ret = drv->cpus[cpu].opp_token;
 				dev_err(cpu_dev, "Failed to set OPP config\n");
 				goto free_opp;
 			}
@@ -325,11 +466,7 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
 
 free_opp:
 	for_each_possible_cpu(cpu)
-		dev_pm_opp_clear_config(drv->opp_tokens[cpu]);
-	kfree(drv->opp_tokens);
-free_drv:
-	kfree(drv);
-
+		dev_pm_opp_clear_config(drv->cpus[cpu].opp_token);
 	return ret;
 }
 
@@ -341,10 +478,7 @@ static void qcom_cpufreq_remove(struct platform_device *pdev)
 	platform_device_unregister(cpufreq_dt_pdev);
 
 	for_each_possible_cpu(cpu)
-		dev_pm_opp_clear_config(drv->opp_tokens[cpu]);
-
-	kfree(drv->opp_tokens);
-	kfree(drv);
+		dev_pm_opp_clear_config(drv->cpus[cpu].opp_token);
 }
 
 static struct platform_driver qcom_cpufreq_driver = {
@@ -357,9 +491,11 @@ static struct platform_driver qcom_cpufreq_driver = {
 
 static const struct of_device_id qcom_cpufreq_match_list[] __initconst = {
 	{ .compatible = "qcom,apq8096", .data = &match_data_kryo },
+	{ .compatible = "qcom,msm8909", .data = &match_data_msm8909 },
 	{ .compatible = "qcom,msm8996", .data = &match_data_kryo },
 	{ .compatible = "qcom,qcs404", .data = &match_data_qcs404 },
-	{ .compatible = "qcom,ipq8064", .data = &match_data_krait },
+	{ .compatible = "qcom,ipq6018", .data = &match_data_ipq6018 },
+	{ .compatible = "qcom,ipq8064", .data = &match_data_ipq8064 },
 	{ .compatible = "qcom,apq8064", .data = &match_data_krait },
 	{ .compatible = "qcom,msm8974", .data = &match_data_krait },
 	{ .compatible = "qcom,msm8960", .data = &match_data_krait },
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index 88ef5e57ccd05..59865ea455a8e 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -5,7 +5,6 @@
 
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
-#include <linux/delay.h>
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -21,10 +20,11 @@
 
 #define KHZ                     1000
 #define REF_CLK_MHZ             408 /* 408 MHz */
-#define US_DELAY                500
 #define CPUFREQ_TBL_STEP_HZ     (50 * KHZ * KHZ)
 #define MAX_CNT                 ~0U
 
+#define MAX_DELTA_KHZ          115200
+
 #define NDIV_MASK              0x1FF
 
 #define CORE_OFFSET(cpu)			(cpu * 8)
@@ -39,6 +39,12 @@
 /* cpufreq transisition latency */
 #define TEGRA_CPUFREQ_TRANSITION_LATENCY (300 * 1000) /* unit in nanoseconds */
 
+struct tegra_cpu_data {
+	u32 cpuid;
+	u32 clusterid;
+	void __iomem *freq_core_reg;
+};
+
 struct tegra_cpu_ctr {
 	u32 cpu;
 	u32 coreclk_cnt, last_coreclk_cnt;
@@ -62,6 +68,7 @@ struct tegra_cpufreq_soc {
 	int maxcpus_per_cluster;
 	unsigned int num_clusters;
 	phys_addr_t actmon_cntr_base;
+	u32 refclk_delta_min;
 };
 
 struct tegra194_cpufreq_data {
@@ -69,6 +76,7 @@ struct tegra194_cpufreq_data {
 	struct cpufreq_frequency_table **bpmp_luts;
 	const struct tegra_cpufreq_soc *soc;
 	bool icc_dram_bw_scaling;
+	struct tegra_cpu_data *cpu_data;
 };
 
 static struct workqueue_struct *read_counters_wq;
@@ -116,14 +124,8 @@ static void tegra234_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid)
 static int tegra234_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
-	void __iomem *freq_core_reg;
-	u64 mpidr_id;
 
-	/* use physical id to get address of per core frequency register */
-	mpidr_id = (clusterid * data->soc->maxcpus_per_cluster) + cpuid;
-	freq_core_reg = SCRATCH_FREQ_CORE_REG(data, mpidr_id);
-
-	*ndiv = readl(freq_core_reg) & NDIV_MASK;
+	*ndiv = readl(data->cpu_data[cpu].freq_core_reg) & NDIV_MASK;
 
 	return 0;
 }
@@ -131,19 +133,10 @@ static int tegra234_get_cpu_ndiv(u32 cpu, u32 cpuid, u32 clusterid, u64 *ndiv)
 static void tegra234_set_cpu_ndiv(struct cpufreq_policy *policy, u64 ndiv)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
-	void __iomem *freq_core_reg;
-	u32 cpu, cpuid, clusterid;
-	u64 mpidr_id;
-
-	for_each_cpu_and(cpu, policy->cpus, cpu_online_mask) {
-		data->soc->ops->get_cpu_cluster_id(cpu, &cpuid, &clusterid);
-
-		/* use physical id to get address of per core frequency register */
-		mpidr_id = (clusterid * data->soc->maxcpus_per_cluster) + cpuid;
-		freq_core_reg = SCRATCH_FREQ_CORE_REG(data, mpidr_id);
+	u32 cpu;
 
-		writel(ndiv, freq_core_reg);
-	}
+	for_each_cpu(cpu, policy->cpus)
+		writel(ndiv, data->cpu_data[cpu].freq_core_reg);
 }
 
 /*
@@ -157,19 +150,35 @@ static void tegra234_read_counters(struct tegra_cpu_ctr *c)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
 	void __iomem *actmon_reg;
-	u32 cpuid, clusterid;
+	u32 delta_refcnt;
+	int cnt = 0;
 	u64 val;
 
-	data->soc->ops->get_cpu_cluster_id(c->cpu, &cpuid, &clusterid);
-	actmon_reg = CORE_ACTMON_CNTR_REG(data, clusterid, cpuid);
+	actmon_reg = CORE_ACTMON_CNTR_REG(data, data->cpu_data[c->cpu].clusterid,
+					  data->cpu_data[c->cpu].cpuid);
 
 	val = readq(actmon_reg);
 	c->last_refclk_cnt = upper_32_bits(val);
 	c->last_coreclk_cnt = lower_32_bits(val);
-	udelay(US_DELAY);
-	val = readq(actmon_reg);
-	c->refclk_cnt = upper_32_bits(val);
-	c->coreclk_cnt = lower_32_bits(val);
+
+	/*
+	 * The sampling window is based on the minimum number of reference
+	 * clock cycles which is known to give a stable value of CPU frequency.
+	 */
+	do {
+		val = readq(actmon_reg);
+		c->refclk_cnt = upper_32_bits(val);
+		c->coreclk_cnt = lower_32_bits(val);
+		if (c->refclk_cnt < c->last_refclk_cnt)
+			delta_refcnt = c->refclk_cnt + (MAX_CNT - c->last_refclk_cnt);
+		else
+			delta_refcnt = c->refclk_cnt - c->last_refclk_cnt;
+		if (++cnt >= 0xFFFF) {
+			pr_warn("cpufreq: problem with refclk on cpu:%d, delta_refcnt:%u, cnt:%d\n",
+				c->cpu, delta_refcnt, cnt);
+			break;
+		}
+	} while (delta_refcnt < data->soc->refclk_delta_min);
 }
 
 static struct tegra_cpufreq_ops tegra234_cpufreq_ops = {
@@ -184,6 +193,7 @@ static const struct tegra_cpufreq_soc tegra234_cpufreq_soc = {
 	.actmon_cntr_base = 0x9000,
 	.maxcpus_per_cluster = 4,
 	.num_clusters = 3,
+	.refclk_delta_min = 16000,
 };
 
 static const struct tegra_cpufreq_soc tegra239_cpufreq_soc = {
@@ -191,6 +201,7 @@ static const struct tegra_cpufreq_soc tegra239_cpufreq_soc = {
 	.actmon_cntr_base = 0x4000,
 	.maxcpus_per_cluster = 8,
 	.num_clusters = 1,
+	.refclk_delta_min = 16000,
 };
 
 static void tegra194_get_cpu_cluster_id(u32 cpu, u32 *cpuid, u32 *clusterid)
@@ -231,15 +242,33 @@ static inline u32 map_ndiv_to_freq(struct mrq_cpu_ndiv_limits_response
 
 static void tegra194_read_counters(struct tegra_cpu_ctr *c)
 {
+	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
+	u32 delta_refcnt;
+	int cnt = 0;
 	u64 val;
 
 	val = read_freq_feedback();
 	c->last_refclk_cnt = lower_32_bits(val);
 	c->last_coreclk_cnt = upper_32_bits(val);
-	udelay(US_DELAY);
-	val = read_freq_feedback();
-	c->refclk_cnt = lower_32_bits(val);
-	c->coreclk_cnt = upper_32_bits(val);
+
+	/*
+	 * The sampling window is based on the minimum number of reference
+	 * clock cycles which is known to give a stable value of CPU frequency.
+	 */
+	do {
+		val = read_freq_feedback();
+		c->refclk_cnt = lower_32_bits(val);
+		c->coreclk_cnt = upper_32_bits(val);
+		if (c->refclk_cnt < c->last_refclk_cnt)
+			delta_refcnt = c->refclk_cnt + (MAX_CNT - c->last_refclk_cnt);
+		else
+			delta_refcnt = c->refclk_cnt - c->last_refclk_cnt;
+		if (++cnt >= 0xFFFF) {
+			pr_warn("cpufreq: problem with refclk on cpu:%d, delta_refcnt:%u, cnt:%d\n",
+				c->cpu, delta_refcnt, cnt);
+			break;
+		}
+	} while (delta_refcnt < data->soc->refclk_delta_min);
 }
 
 static void tegra_read_counters(struct work_struct *work)
@@ -297,9 +326,8 @@ static unsigned int tegra194_calculate_speed(u32 cpu)
 	u32 rate_mhz;
 
 	/*
-	 * udelay() is required to reconstruct cpu frequency over an
-	 * observation window. Using workqueue to call udelay() with
-	 * interrupts enabled.
+	 * Reconstruct cpu frequency over an observation/sampling window.
+	 * Using workqueue to keep interrupts enabled during the interval.
 	 */
 	read_counters_work.c.cpu = cpu;
 	INIT_WORK_ONSTACK(&read_counters_work.work, tegra_read_counters);
@@ -357,19 +385,17 @@ static void tegra194_set_cpu_ndiv(struct cpufreq_policy *policy, u64 ndiv)
 static unsigned int tegra194_get_speed(u32 cpu)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
+	u32 clusterid = data->cpu_data[cpu].clusterid;
 	struct cpufreq_frequency_table *pos;
-	u32 cpuid, clusterid;
 	unsigned int rate;
 	u64 ndiv;
 	int ret;
 
-	data->soc->ops->get_cpu_cluster_id(cpu, &cpuid, &clusterid);
-
 	/* reconstruct actual cpu freq using counters */
 	rate = tegra194_calculate_speed(cpu);
 
 	/* get last written ndiv value */
-	ret = data->soc->ops->get_cpu_ndiv(cpu, cpuid, clusterid, &ndiv);
+	ret = data->soc->ops->get_cpu_ndiv(cpu, data->cpu_data[cpu].cpuid, clusterid, &ndiv);
 	if (WARN_ON_ONCE(ret))
 		return rate;
 
@@ -383,9 +409,9 @@ static unsigned int tegra194_get_speed(u32 cpu)
 		if (pos->driver_data != ndiv)
 			continue;
 
-		if (abs(pos->frequency - rate) > 115200) {
-			pr_warn("cpufreq: cpu%d,cur:%u,set:%u,set ndiv:%llu\n",
-				cpu, rate, pos->frequency, ndiv);
+		if (abs(pos->frequency - rate) > MAX_DELTA_KHZ) {
+			pr_warn("cpufreq: cpu%d,cur:%u,set:%u,delta:%d,set ndiv:%llu\n",
+				cpu, rate, pos->frequency, abs(rate - pos->frequency), ndiv);
 		} else {
 			rate = pos->frequency;
 		}
@@ -450,6 +476,8 @@ static int tegra_cpufreq_init_cpufreq_table(struct cpufreq_policy *policy,
 		if (IS_ERR(opp))
 			continue;
 
+		dev_pm_opp_put(opp);
+
 		ret = dev_pm_opp_enable(cpu_dev, pos->frequency * KHZ);
 		if (ret < 0)
 			return ret;
@@ -473,13 +501,12 @@ static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
 	int maxcpus_per_cluster = data->soc->maxcpus_per_cluster;
+	u32 clusterid = data->cpu_data[policy->cpu].clusterid;
 	struct cpufreq_frequency_table *freq_table;
 	struct cpufreq_frequency_table *bpmp_lut;
 	u32 start_cpu, cpu;
-	u32 clusterid;
 	int ret;
 
-	data->soc->ops->get_cpu_cluster_id(policy->cpu, NULL, &clusterid);
 	if (clusterid >= data->soc->num_clusters || !data->bpmp_luts[clusterid])
 		return -EINVAL;
 
@@ -578,6 +605,7 @@ static const struct tegra_cpufreq_soc tegra194_cpufreq_soc = {
 	.ops = &tegra194_cpufreq_ops,
 	.maxcpus_per_cluster = 2,
 	.num_clusters = 4,
+	.refclk_delta_min = 16000,
 };
 
 static void tegra194_cpufreq_free_resources(void)
@@ -657,6 +685,28 @@ tegra_cpufreq_bpmp_read_lut(struct platform_device *pdev, struct tegra_bpmp *bpm
 	return freq_table;
 }
 
+static int tegra194_cpufreq_store_physids(unsigned int cpu, struct tegra194_cpufreq_data *data)
+{
+	int num_cpus = data->soc->maxcpus_per_cluster * data->soc->num_clusters;
+	u32 cpuid, clusterid;
+	u64 mpidr_id;
+
+	if (cpu > (num_cpus - 1)) {
+		pr_err("cpufreq: wrong num of cpus or clusters in soc data\n");
+		return -EINVAL;
+	}
+
+	data->soc->ops->get_cpu_cluster_id(cpu, &cpuid, &clusterid);
+
+	mpidr_id = (clusterid * data->soc->maxcpus_per_cluster) + cpuid;
+
+	data->cpu_data[cpu].cpuid = cpuid;
+	data->cpu_data[cpu].clusterid = clusterid;
+	data->cpu_data[cpu].freq_core_reg = SCRATCH_FREQ_CORE_REG(data, mpidr_id);
+
+	return 0;
+}
+
 static int tegra194_cpufreq_probe(struct platform_device *pdev)
 {
 	const struct tegra_cpufreq_soc *soc;
@@ -664,6 +714,7 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 	struct tegra_bpmp *bpmp;
 	struct device *cpu_dev;
 	int err, i;
+	u32 cpu;
 
 	data = devm_kzalloc(&pdev->dev, sizeof(*data), GFP_KERNEL);
 	if (!data)
@@ -671,7 +722,7 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 
 	soc = of_device_get_match_data(&pdev->dev);
 
-	if (soc->ops && soc->maxcpus_per_cluster && soc->num_clusters) {
+	if (soc->ops && soc->maxcpus_per_cluster && soc->num_clusters && soc->refclk_delta_min) {
 		data->soc = soc;
 	} else {
 		dev_err(&pdev->dev, "soc data missing\n");
@@ -690,6 +741,12 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 			return PTR_ERR(data->regs);
 	}
 
+	data->cpu_data = devm_kcalloc(&pdev->dev, data->soc->num_clusters *
+				      data->soc->maxcpus_per_cluster,
+				      sizeof(*data->cpu_data), GFP_KERNEL);
+	if (!data->cpu_data)
+		return -ENOMEM;
+
 	platform_set_drvdata(pdev, data);
 
 	bpmp = tegra_bpmp_get(&pdev->dev);
@@ -711,6 +768,12 @@ static int tegra194_cpufreq_probe(struct platform_device *pdev)
 		}
 	}
 
+	for_each_possible_cpu(cpu) {
+		err = tegra194_cpufreq_store_physids(cpu, data);
+		if (err)
+			goto err_free_res;
+	}
+
 	tegra194_cpufreq_driver.driver_data = data;
 
 	/* Check for optional OPPv2 and interconnect paths on CPU0 to enable ICC scaling */
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index 3c37d78996607..46c41e2ca727b 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -338,6 +338,7 @@ static const struct of_device_id ti_cpufreq_of_match[] = {
 	{ .compatible = "ti,omap36xx", .data = &omap36xx_soc_data, },
 	{ .compatible = "ti,am625", .data = &am625_soc_data, },
 	{ .compatible = "ti,am62a7", .data = &am625_soc_data, },
+	{ .compatible = "ti,am62p5", .data = &am625_soc_data, },
 	/* legacy */
 	{ .compatible = "ti,omap3430", .data = &omap34xx_soc_data, },
 	{ .compatible = "ti,omap3630", .data = &omap36xx_soc_data, },