Merge back cpufreq material for 6.3-rc1.

20 files changed, 893 insertions, 305 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 6cfa6e3996cf..e3618dfdb36a 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7020,3 +7020,10 @@
 			  management firmware translates the requests into actual
 			  hardware states (core frequency, data fabric and memory
 			  clocks etc.)
+			active
+			  Use amd_pstate_epp driver instance as the scaling driver,
+			  driver provides a hint to the hardware if software wants
+			  to bias toward performance (0x0) or energy efficiency (0xff)
+			  to the CPPC firmware. then CPPC power algorithm will
+			  calculate the runtime workload and adjust the realtime cores
+			  frequency.
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 5376d53faaa8..5304adf2fc2f 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -262,6 +262,25 @@ lowest non-linear performance in `AMD CPPC Performance Capability
 <perf_cap_>`_.)
 This attribute is read-only.
 
+``energy_performance_available_preferences``
+
+A list of all the supported EPP preferences that could be used for
+``energy_performance_preference`` on this system.
+These profiles represent different hints that are provided
+to the low-level firmware about the user's desired energy vs efficiency
+tradeoff.  ``default`` represents the epp value is set by platform
+firmware. This attribute is read-only.
+
+``energy_performance_preference``
+
+The current energy performance preference can be read from this attribute.
+and user can change current preference according to energy or performance needs
+Please get all support profiles list from
+``energy_performance_available_preferences`` attribute, all the profiles are
+integer values defined between 0 to 255 when EPP feature is enabled by platform
+firmware, if EPP feature is disabled, driver will ignore the written value
+This attribute is read-write.
+
 Other performance and frequency values can be read back from
 ``/sys/devices/system/cpu/cpuX/acpi_cppc/``, see :ref:`cppc_sysfs`.
 
@@ -280,8 +299,30 @@ module which supports the new AMD P-States mechanism on most of the future AMD
 platforms. The AMD P-States mechanism is the more performance and energy
 efficiency frequency management method on AMD processors.
 
-Kernel Module Options for ``amd-pstate``
-=========================================
+
+AMD Pstate Driver Operation Modes
+=================================
+
+``amd_pstate`` CPPC has two operation modes: CPPC Autonomous(active) mode and
+CPPC non-autonomous(passive) mode.
+active mode and passive mode can be chosen by different kernel parameters.
+When in Autonomous mode, CPPC ignores requests done in the Desired Performance
+Target register and takes into account only the values set to the Minimum requested
+performance, Maximum requested performance, and Energy Performance Preference
+registers. When Autonomous is disabled, it only considers the Desired Performance Target.
+
+Active Mode
+------------
+
+``amd_pstate=active``
+
+This is the low-level firmware control mode which is implemented by ``amd_pstate_epp``
+driver with ``amd_pstate=active`` passed to the kernel in the command line.
+In this mode, ``amd_pstate_epp`` driver provides a hint to the hardware if software
+wants to bias toward performance (0x0) or energy efficiency (0xff) to the CPPC firmware.
+then CPPC power algorithm will calculate the runtime workload and adjust the realtime
+cores frequency according to the power supply and thermal, core voltage and some other
+hardware conditions.
 
 Passive Mode
 ------------
@@ -298,6 +339,35 @@ processor must provide at least nominal performance requested and go higher if c
 operating conditions allow.
 
 
+User Space Interface in ``sysfs``
+=================================
+
+Global Attributes
+-----------------
+
+``amd-pstate`` exposes several global attributes (files) in ``sysfs`` to
+control its functionality at the system level.  They are located in the
+``/sys/devices/system/cpu/amd-pstate/`` directory and affect all CPUs.
+
+``status``
+	Operation mode of the driver: "active", "passive" or "disable".
+
+	"active"
+		The driver is functional and in the ``active mode``
+
+	"passive"
+		The driver is functional and in the ``passive mode``
+
+	"disable"
+		The driver is unregistered and not functional now.
+
+        This attribute can be written to in order to change the driver's
+        operation mode or to unregister it.  The string written to it must be
+        one of the possible values of it and, if successful, writing one of
+        these values to the sysfs file will cause the driver to switch over
+        to the operation mode represented by that string - or to be
+        unregistered in the "disable" case.
+
 ``cpupower`` tool support for ``amd-pstate``
 ===============================================
 
diff --git a/arch/mips/include/asm/mach-loongson32/cpufreq.h b/arch/mips/include/asm/mach-loongson32/cpufreq.h
deleted file mode 100644
index e422a32883ae..000000000000
--- a/arch/mips/include/asm/mach-loongson32/cpufreq.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (c) 2014 Zhang, Keguang <keguang.zhang@gmail.com>
- *
- * Loongson 1 CPUFreq platform support.
- */
-
-#ifndef __ASM_MACH_LOONGSON32_CPUFREQ_H
-#define __ASM_MACH_LOONGSON32_CPUFREQ_H
-
-struct plat_ls1x_cpufreq {
-	const char	*clk_name;	/* CPU clk */
-	const char	*osc_clk_name;	/* OSC clk */
-	unsigned int	max_freq;	/* in kHz */
-	unsigned int	min_freq;	/* in kHz */
-};
-
-#endif /* __ASM_MACH_LOONGSON32_CPUFREQ_H */
diff --git a/arch/mips/include/asm/mach-loongson32/platform.h b/arch/mips/include/asm/mach-loongson32/platform.h
index eb83e2741887..86e1a6aab4e5 100644
--- a/arch/mips/include/asm/mach-loongson32/platform.h
+++ b/arch/mips/include/asm/mach-loongson32/platform.h
@@ -12,7 +12,6 @@
 #include <nand.h>
 
 extern struct platform_device ls1x_uart_pdev;
-extern struct platform_device ls1x_cpufreq_pdev;
 extern struct platform_device ls1x_eth0_pdev;
 extern struct platform_device ls1x_eth1_pdev;
 extern struct platform_device ls1x_ehci_pdev;
diff --git a/arch/mips/loongson32/common/platform.c b/arch/mips/loongson32/common/platform.c
index 311dc1580bbd..64d7979394e6 100644
--- a/arch/mips/loongson32/common/platform.c
+++ b/arch/mips/loongson32/common/platform.c
@@ -15,7 +15,6 @@
 
 #include <platform.h>
 #include <loongson1.h>
-#include <cpufreq.h>
 #include <dma.h>
 #include <nand.h>
 
@@ -62,21 +61,6 @@ void __init ls1x_serial_set_uartclk(struct platform_device *pdev)
 		p->uartclk = clk_get_rate(clk);
 }
 
-/* CPUFreq */
-static struct plat_ls1x_cpufreq ls1x_cpufreq_pdata = {
-	.clk_name	= "cpu_clk",
-	.osc_clk_name	= "osc_clk",
-	.max_freq	= 266 * 1000,
-	.min_freq	= 33 * 1000,
-};
-
-struct platform_device ls1x_cpufreq_pdev = {
-	.name		= "ls1x-cpufreq",
-	.dev		= {
-		.platform_data = &ls1x_cpufreq_pdata,
-	},
-};
-
 /* Synopsys Ethernet GMAC */
 static struct stmmac_mdio_bus_data ls1x_mdio_bus_data = {
 	.phy_mask	= 0,
diff --git a/arch/mips/loongson32/ls1b/board.c b/arch/mips/loongson32/ls1b/board.c
index 727e06718dab..fed8d432ef20 100644
--- a/arch/mips/loongson32/ls1b/board.c
+++ b/arch/mips/loongson32/ls1b/board.c
@@ -35,7 +35,6 @@ static const struct gpio_led_platform_data ls1x_led_pdata __initconst = {
 
 static struct platform_device *ls1b_platform_devices[] __initdata = {
 	&ls1x_uart_pdev,
-	&ls1x_cpufreq_pdev,
 	&ls1x_eth0_pdev,
 	&ls1x_eth1_pdev,
 	&ls1x_ehci_pdev,
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index 0f17b1c32718..02d83c807271 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1154,6 +1154,19 @@ int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 }
 
 /**
+ * cppc_get_epp_perf - Get the epp register value.
+ * @cpunum: CPU from which to get epp preference value.
+ * @epp_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_epp_perf(int cpunum, u64 *epp_perf)
+{
+	return cppc_get_perf(cpunum, ENERGY_PERF, epp_perf);
+}
+EXPORT_SYMBOL_GPL(cppc_get_epp_perf);
+
+/**
  * cppc_get_perf_caps - Get a CPU's performance capabilities.
  * @cpunum: CPU from which to get capabilities info.
  * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
@@ -1365,6 +1378,60 @@ out_err:
 }
 EXPORT_SYMBOL_GPL(cppc_get_perf_ctrs);
 
+/*
+ * Set Energy Performance Preference Register value through
+ * Performance Controls Interface
+ */
+int cppc_set_epp_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls, bool enable)
+{
+	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+	struct cpc_register_resource *epp_set_reg;
+	struct cpc_register_resource *auto_sel_reg;
+	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
+	struct cppc_pcc_data *pcc_ss_data = NULL;
+	int ret;
+
+	if (!cpc_desc) {
+		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
+		return -ENODEV;
+	}
+
+	auto_sel_reg = &cpc_desc->cpc_regs[AUTO_SEL_ENABLE];
+	epp_set_reg = &cpc_desc->cpc_regs[ENERGY_PERF];
+
+	if (CPC_IN_PCC(epp_set_reg) || CPC_IN_PCC(auto_sel_reg)) {
+		if (pcc_ss_id < 0) {
+			pr_debug("Invalid pcc_ss_id for CPU:%d\n", cpu);
+			return -ENODEV;
+		}
+
+		if (CPC_SUPPORTED(auto_sel_reg)) {
+			ret = cpc_write(cpu, auto_sel_reg, enable);
+			if (ret)
+				return ret;
+		}
+
+		if (CPC_SUPPORTED(epp_set_reg)) {
+			ret = cpc_write(cpu, epp_set_reg, perf_ctrls->energy_perf);
+			if (ret)
+				return ret;
+		}
+
+		pcc_ss_data = pcc_data[pcc_ss_id];
+
+		down_write(&pcc_ss_data->pcc_lock);
+		/* after writing CPC, transfer the ownership of PCC to platform */
+		ret = send_pcc_cmd(pcc_ss_id, CMD_WRITE);
+		up_write(&pcc_ss_data->pcc_lock);
+	} else {
+		ret = -ENOTSUPP;
+		pr_debug("_CPC in PCC is not supported\n");
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cppc_set_epp_perf);
+
 /**
  * cppc_set_enable - Set to enable CPPC on the processor by writing the
  * Continuous Performance Control package EnableRegister field.
diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 2a84fc63371e..76aa1336e2be 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -3,7 +3,6 @@ menu "CPU Frequency scaling"
 
 config CPU_FREQ
 	bool "CPU Frequency scaling"
-	select SRCU
 	help
 	  CPU Frequency scaling allows you to change the clock speed of 
 	  CPUs on the fly. This is a nice method to save power, because 
@@ -271,15 +270,6 @@ config LOONGSON2_CPUFREQ
 	  Loongson2F and its successors support this feature.
 
 	  If in doubt, say N.
-
-config LOONGSON1_CPUFREQ
-	tristate "Loongson1 CPUFreq Driver"
-	depends on LOONGSON1_LS1B
-	help
-	  This option adds a CPUFreq driver for loongson1 processors which
-	  support software configurable cpu frequency.
-
-	  If in doubt, say N.
 endif
 
 if SPARC64
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 32a7029e25ed..4a806cc5265b 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -111,7 +111,6 @@ obj-$(CONFIG_POWERNV_CPUFREQ)		+= powernv-cpufreq.o
 obj-$(CONFIG_BMIPS_CPUFREQ)		+= bmips-cpufreq.o
 obj-$(CONFIG_IA64_ACPI_CPUFREQ)		+= ia64-acpi-cpufreq.o
 obj-$(CONFIG_LOONGSON2_CPUFREQ)		+= loongson2_cpufreq.o
-obj-$(CONFIG_LOONGSON1_CPUFREQ)		+= loongson1-cpufreq.o
 obj-$(CONFIG_SH_CPU_FREQ)		+= sh-cpufreq.o
 obj-$(CONFIG_SPARC_US2E_CPUFREQ)	+= sparc-us2e-cpufreq.o
 obj-$(CONFIG_SPARC_US3_CPUFREQ)		+= sparc-us3-cpufreq.o
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index c17bd845f5fc..b8862afef4e4 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -59,8 +59,171 @@
  * we disable it by default to go acpi-cpufreq on these processors and add a
  * module parameter to be able to enable it manually for debugging.
  */
+static struct cpufreq_driver *current_pstate_driver;
 static struct cpufreq_driver amd_pstate_driver;
-static int cppc_load __initdata;
+static struct cpufreq_driver amd_pstate_epp_driver;
+static int cppc_state = AMD_PSTATE_DISABLE;
+struct kobject *amd_pstate_kobj;
+
+/*
+ * AMD Energy Preference Performance (EPP)
+ * The EPP is used in the CCLK DPM controller to drive
+ * the frequency that a core is going to operate during
+ * short periods of activity. EPP values will be utilized for
+ * different OS profiles (balanced, performance, power savings)
+ * display strings corresponding to EPP index in the
+ * energy_perf_strings[]
+ *	index		String
+ *-------------------------------------
+ *	0		default
+ *	1		performance
+ *	2		balance_performance
+ *	3		balance_power
+ *	4		power
+ */
+enum energy_perf_value_index {
+	EPP_INDEX_DEFAULT = 0,
+	EPP_INDEX_PERFORMANCE,
+	EPP_INDEX_BALANCE_PERFORMANCE,
+	EPP_INDEX_BALANCE_POWERSAVE,
+	EPP_INDEX_POWERSAVE,
+};
+
+static const char * const energy_perf_strings[] = {
+	[EPP_INDEX_DEFAULT] = "default",
+	[EPP_INDEX_PERFORMANCE] = "performance",
+	[EPP_INDEX_BALANCE_PERFORMANCE] = "balance_performance",
+	[EPP_INDEX_BALANCE_POWERSAVE] = "balance_power",
+	[EPP_INDEX_POWERSAVE] = "power",
+	NULL
+};
+
+static unsigned int epp_values[] = {
+	[EPP_INDEX_DEFAULT] = 0,
+	[EPP_INDEX_PERFORMANCE] = AMD_CPPC_EPP_PERFORMANCE,
+	[EPP_INDEX_BALANCE_PERFORMANCE] = AMD_CPPC_EPP_BALANCE_PERFORMANCE,
+	[EPP_INDEX_BALANCE_POWERSAVE] = AMD_CPPC_EPP_BALANCE_POWERSAVE,
+	[EPP_INDEX_POWERSAVE] = AMD_CPPC_EPP_POWERSAVE,
+ };
+
+static inline int get_mode_idx_from_str(const char *str, size_t size)
+{
+	int i;
+
+	for (i=0; i < AMD_PSTATE_MAX; i++) {
+		if (!strncmp(str, amd_pstate_mode_string[i], size))
+			return i;
+	}
+	return -EINVAL;
+}
+
+static DEFINE_MUTEX(amd_pstate_limits_lock);
+static DEFINE_MUTEX(amd_pstate_driver_lock);
+
+static s16 amd_pstate_get_epp(struct amd_cpudata *cpudata, u64 cppc_req_cached)
+{
+	u64 epp;
+	int ret;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		if (!cppc_req_cached) {
+			epp = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
+					&cppc_req_cached);
+			if (epp)
+				return epp;
+		}
+		epp = (cppc_req_cached >> 24) & 0xFF;
+	} else {
+		ret = cppc_get_epp_perf(cpudata->cpu, &epp);
+		if (ret < 0) {
+			pr_debug("Could not retrieve energy perf value (%d)\n", ret);
+			return -EIO;
+		}
+	}
+
+	return (s16)(epp & 0xff);
+}
+
+static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata)
+{
+	s16 epp;
+	int index = -EINVAL;
+
+	epp = amd_pstate_get_epp(cpudata, 0);
+	if (epp < 0)
+		return epp;
+
+	switch (epp) {
+	case AMD_CPPC_EPP_PERFORMANCE:
+		index = EPP_INDEX_PERFORMANCE;
+		break;
+	case AMD_CPPC_EPP_BALANCE_PERFORMANCE:
+		index = EPP_INDEX_BALANCE_PERFORMANCE;
+		break;
+	case AMD_CPPC_EPP_BALANCE_POWERSAVE:
+		index = EPP_INDEX_BALANCE_POWERSAVE;
+		break;
+	case AMD_CPPC_EPP_POWERSAVE:
+		index = EPP_INDEX_POWERSAVE;
+		break;
+	default:
+		break;
+	}
+
+	return index;
+}
+
+static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp)
+{
+	int ret;
+	struct cppc_perf_ctrls perf_ctrls;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		u64 value = READ_ONCE(cpudata->cppc_req_cached);
+
+		value &= ~GENMASK_ULL(31, 24);
+		value |= (u64)epp << 24;
+		WRITE_ONCE(cpudata->cppc_req_cached, value);
+
+		ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
+		if (!ret)
+			cpudata->epp_cached = epp;
+	} else {
+		perf_ctrls.energy_perf = epp;
+		ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
+		if (ret) {
+			pr_debug("failed to set energy perf value (%d)\n", ret);
+			return ret;
+		}
+		cpudata->epp_cached = epp;
+	}
+
+	return ret;
+}
+
+static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
+		int pref_index)
+{
+	int epp = -EINVAL;
+	int ret;
+
+	if (!pref_index) {
+		pr_debug("EPP pref_index is invalid\n");
+		return -EINVAL;
+	}
+
+	if (epp == -EINVAL)
+		epp = epp_values[pref_index];
+
+	if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		pr_debug("EPP cannot be set under performance policy\n");
+		return -EBUSY;
+	}
+
+	ret = amd_pstate_set_epp(cpudata, epp);
+
+	return ret;
+}
 
 static inline int pstate_enable(bool enable)
 {
@@ -70,11 +233,21 @@ static inline int pstate_enable(bool enable)
 static int cppc_enable(bool enable)
 {
 	int cpu, ret = 0;
+	struct cppc_perf_ctrls perf_ctrls;
 
 	for_each_present_cpu(cpu) {
 		ret = cppc_set_enable(cpu, enable);
 		if (ret)
 			return ret;
+
+		/* Enable autonomous mode for EPP */
+		if (cppc_state == AMD_PSTATE_ACTIVE) {
+			/* Set desired perf as zero to allow EPP firmware control */
+			perf_ctrls.desired_perf = 0;
+			ret = cppc_set_perf(cpu, &perf_ctrls);
+			if (ret)
+				return ret;
+		}
 	}
 
 	return ret;
@@ -418,7 +591,7 @@ static void amd_pstate_boost_init(struct amd_cpudata *cpudata)
 		return;
 
 	cpudata->boost_supported = true;
-	amd_pstate_driver.boost_enabled = true;
+	current_pstate_driver->boost_enabled = true;
 }
 
 static void amd_perf_ctl_reset(unsigned int cpu)
@@ -501,6 +674,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	policy->driver_data = cpudata;
 
 	amd_pstate_boost_init(cpudata);
+	if (!current_pstate_driver->adjust_perf)
+		current_pstate_driver->adjust_perf = amd_pstate_adjust_perf;
 
 	return 0;
 
@@ -561,7 +736,7 @@ static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
 	if (max_freq < 0)
 		return max_freq;
 
-	return sprintf(&buf[0], "%u\n", max_freq);
+	return sysfs_emit(buf, "%u\n", max_freq);
 }
 
 static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *policy,
@@ -574,7 +749,7 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli
 	if (freq < 0)
 		return freq;
 
-	return sprintf(&buf[0], "%u\n", freq);
+	return sysfs_emit(buf, "%u\n", freq);
 }
 
 /*
@@ -589,13 +764,151 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
 
 	perf = READ_ONCE(cpudata->highest_perf);
 
-	return sprintf(&buf[0], "%u\n", perf);
+	return sysfs_emit(buf, "%u\n", perf);
+}
+
+static ssize_t show_energy_performance_available_preferences(
+				struct cpufreq_policy *policy, char *buf)
+{
+	int i = 0;
+	int offset = 0;
+
+	while (energy_perf_strings[i] != NULL)
+		offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]);
+
+	sysfs_emit_at(buf, offset, "\n");
+
+	return offset;
+}
+
+static ssize_t store_energy_performance_preference(
+		struct cpufreq_policy *policy, const char *buf, size_t count)
+{
+	struct amd_cpudata *cpudata = policy->driver_data;
+	char str_preference[21];
+	ssize_t ret;
+
+	ret = sscanf(buf, "%20s", str_preference);
+	if (ret != 1)
+		return -EINVAL;
+
+	ret = match_string(energy_perf_strings, -1, str_preference);
+	if (ret < 0)
+		return -EINVAL;
+
+	mutex_lock(&amd_pstate_limits_lock);
+	ret = amd_pstate_set_energy_pref_index(cpudata, ret);
+	mutex_unlock(&amd_pstate_limits_lock);
+
+	return ret ?: count;
+}
+
+static ssize_t show_energy_performance_preference(
+				struct cpufreq_policy *policy, char *buf)
+{
+	struct amd_cpudata *cpudata = policy->driver_data;
+	int preference;
+
+	preference = amd_pstate_get_energy_pref_index(cpudata);
+	if (preference < 0)
+		return preference;
+
+	return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]);
+}
+
+static ssize_t amd_pstate_show_status(char *buf)
+{
+	if (!current_pstate_driver)
+		return sysfs_emit(buf, "disable\n");
+
+	return sysfs_emit(buf, "%s\n", amd_pstate_mode_string[cppc_state]);
+}
+
+static void amd_pstate_driver_cleanup(void)
+{
+	current_pstate_driver = NULL;
+}
+
+static int amd_pstate_update_status(const char *buf, size_t size)
+{
+	int ret = 0;
+	int mode_idx;
+
+	if (size > 7 || size < 6)
+		return -EINVAL;
+	mode_idx = get_mode_idx_from_str(buf, size);
+
+	switch(mode_idx) {
+	case AMD_PSTATE_DISABLE:
+		if (!current_pstate_driver)
+			return -EINVAL;
+		if (cppc_state == AMD_PSTATE_ACTIVE)
+			return -EBUSY;
+		cpufreq_unregister_driver(current_pstate_driver);
+		amd_pstate_driver_cleanup();
+		break;
+	case AMD_PSTATE_PASSIVE:
+		if (current_pstate_driver) {
+			if (current_pstate_driver == &amd_pstate_driver)
+				return 0;
+			cpufreq_unregister_driver(current_pstate_driver);
+			cppc_state = AMD_PSTATE_PASSIVE;
+			current_pstate_driver = &amd_pstate_driver;
+		}
+
+		ret = cpufreq_register_driver(current_pstate_driver);
+		break;
+	case AMD_PSTATE_ACTIVE:
+		if (current_pstate_driver) {
+			if (current_pstate_driver == &amd_pstate_epp_driver)
+				return 0;
+			cpufreq_unregister_driver(current_pstate_driver);
+			current_pstate_driver = &amd_pstate_epp_driver;
+			cppc_state = AMD_PSTATE_ACTIVE;
+		}
+
+		ret = cpufreq_register_driver(current_pstate_driver);
+		break;
+	default:
+		ret = -EINVAL;
+		break;
+	}
+
+	return ret;
+}
+
+static ssize_t show_status(struct kobject *kobj,
+			   struct kobj_attribute *attr, char *buf)
+{
+	ssize_t ret;
+
+	mutex_lock(&amd_pstate_driver_lock);
+	ret = amd_pstate_show_status(buf);
+	mutex_unlock(&amd_pstate_driver_lock);
+
+	return ret;
+}
+
+static ssize_t store_status(struct kobject *a, struct kobj_attribute *b,
+			    const char *buf, size_t count)
+{
+	char *p = memchr(buf, '\n', count);
+	int ret;
+
+	mutex_lock(&amd_pstate_driver_lock);
+	ret = amd_pstate_update_status(buf, p ? p - buf : count);
+	mutex_unlock(&amd_pstate_driver_lock);
+
+	return ret < 0 ? ret : count;
 }
 
 cpufreq_freq_attr_ro(amd_pstate_max_freq);
 cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq);
 
 cpufreq_freq_attr_ro(amd_pstate_highest_perf);
+cpufreq_freq_attr_rw(energy_performance_preference);
+cpufreq_freq_attr_ro(energy_performance_available_preferences);
+define_one_global_rw(status);
 
 static struct freq_attr *amd_pstate_attr[] = {
 	&amd_pstate_max_freq,
@@ -604,6 +917,312 @@ static struct freq_attr *amd_pstate_attr[] = {
 	NULL,
 };
 
+static struct freq_attr *amd_pstate_epp_attr[] = {
+	&amd_pstate_max_freq,
+	&amd_pstate_lowest_nonlinear_freq,
+	&amd_pstate_highest_perf,
+	&energy_performance_preference,
+	&energy_performance_available_preferences,
+	NULL,
+};
+
+static struct attribute *pstate_global_attributes[] = {
+	&status.attr,
+	NULL
+};
+
+static const struct attribute_group amd_pstate_global_attr_group = {
+	.attrs = pstate_global_attributes,
+};
+
+static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
+{
+	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
+	struct amd_cpudata *cpudata;
+	struct device *dev;
+	u64 value;
+
+	/*
+	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
+	 * which is ideal for initialization process.
+	 */
+	amd_perf_ctl_reset(policy->cpu);
+	dev = get_cpu_device(policy->cpu);
+	if (!dev)
+		return -ENODEV;
+
+	cpudata = kzalloc(sizeof(*cpudata), GFP_KERNEL);
+	if (!cpudata)
+		return -ENOMEM;
+
+	cpudata->cpu = policy->cpu;
+	cpudata->epp_policy = 0;
+
+	ret = amd_pstate_init_perf(cpudata);
+	if (ret)
+		goto free_cpudata1;
+
+	min_freq = amd_get_min_freq(cpudata);
+	max_freq = amd_get_max_freq(cpudata);
+	nominal_freq = amd_get_nominal_freq(cpudata);
+	lowest_nonlinear_freq = amd_get_lowest_nonlinear_freq(cpudata);
+	if (min_freq < 0 || max_freq < 0 || min_freq > max_freq) {
+		dev_err(dev, "min_freq(%d) or max_freq(%d) value is incorrect\n",
+				min_freq, max_freq);
+		ret = -EINVAL;
+		goto free_cpudata1;
+	}
+
+	policy->cpuinfo.min_freq = min_freq;
+	policy->cpuinfo.max_freq = max_freq;
+	/* It will be updated by governor */
+	policy->cur = policy->cpuinfo.min_freq;
+
+	/* Initial processor data capability frequencies */
+	cpudata->max_freq = max_freq;
+	cpudata->min_freq = min_freq;
+	cpudata->nominal_freq = nominal_freq;
+	cpudata->lowest_nonlinear_freq = lowest_nonlinear_freq;
+
+	policy->driver_data = cpudata;
+
+	cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0);
+
+	policy->min = policy->cpuinfo.min_freq;
+	policy->max = policy->cpuinfo.max_freq;
+
+	/*
+	 * Set the policy to powersave to provide a valid fallback value in case
+	 * the default cpufreq governor is neither powersave nor performance.
+	 */
+	policy->policy = CPUFREQ_POLICY_POWERSAVE;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		policy->fast_switch_possible = true;
+		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
+		if (ret)
+			return ret;
+		WRITE_ONCE(cpudata->cppc_req_cached, value);
+
+		ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1, &value);
+		if (ret)
+			return ret;
+		WRITE_ONCE(cpudata->cppc_cap1_cached, value);
+	}
+	amd_pstate_boost_init(cpudata);
+
+	return 0;
+
+free_cpudata1:
+	kfree(cpudata);
+	return ret;
+}
+
+static int amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
+{
+	pr_debug("CPU %d exiting\n", policy->cpu);
+	policy->fast_switch_possible = false;
+	return 0;
+}
+
+static void amd_pstate_epp_init(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct amd_cpudata *cpudata = policy->driver_data;
+	u32 max_perf, min_perf;
+	u64 value;
+	s16 epp;
+
+	max_perf = READ_ONCE(cpudata->highest_perf);
+	min_perf = READ_ONCE(cpudata->lowest_perf);
+
+	value = READ_ONCE(cpudata->cppc_req_cached);
+
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
+		min_perf = max_perf;
+
+	/* Initial min/max values for CPPC Performance Controls Register */
+	value &= ~AMD_CPPC_MIN_PERF(~0L);
+	value |= AMD_CPPC_MIN_PERF(min_perf);
+
+	value &= ~AMD_CPPC_MAX_PERF(~0L);
+	value |= AMD_CPPC_MAX_PERF(max_perf);
+
+	/* CPPC EPP feature require to set zero to the desire perf bit */
+	value &= ~AMD_CPPC_DES_PERF(~0L);
+	value |= AMD_CPPC_DES_PERF(0);
+
+	if (cpudata->epp_policy == cpudata->policy)
+		goto skip_epp;
+
+	cpudata->epp_policy = cpudata->policy;
+
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		epp = amd_pstate_get_epp(cpudata, value);
+		if (epp < 0)
+			goto skip_epp;
+		/* force the epp value to be zero for performance policy */
+		epp = 0;
+	} else {
+		/* Get BIOS pre-defined epp value */
+		epp = amd_pstate_get_epp(cpudata, value);
+		if (epp)
+			goto skip_epp;
+	}
+	/* Set initial EPP value */
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		value &= ~GENMASK_ULL(31, 24);
+		value |= (u64)epp << 24;
+	}
+
+	amd_pstate_set_epp(cpudata, epp);
+skip_epp:
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
+	cpufreq_cpu_put(policy);
+}
+
+static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
+{
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	if (!policy->cpuinfo.max_freq)
+		return -ENODEV;
+
+	pr_debug("set_policy: cpuinfo.max %u policy->max %u\n",
+				policy->cpuinfo.max_freq, policy->max);
+
+	cpudata->policy = policy->policy;
+
+	amd_pstate_epp_init(policy->cpu);
+
+	return 0;
+}
+
+static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
+{
+	struct cppc_perf_ctrls perf_ctrls;
+	u64 value, max_perf;
+	int ret;
+
+	ret = amd_pstate_enable(true);
+	if (ret)
+		pr_err("failed to enable amd pstate during resume, return %d\n", ret);
+
+	value = READ_ONCE(cpudata->cppc_req_cached);
+	max_perf = READ_ONCE(cpudata->highest_perf);
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
+	} else {