Merge back cpufreq material for 6.9-rc1.

12 files changed, 365 insertions, 37 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 31b3a25680d0..522530432548 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -374,6 +374,11 @@
 			  selects a performance level in this range and appropriate
 			  to the current workload.
 
+	amd_prefcore=
+			[X86]
+			disable
+			  Disable amd-pstate preferred core.
+
 	amijoy.map=	[HW,JOY] Amiga joystick support
 			Map of devices attached to JOY0DAT and JOY1DAT
 			Format: <a>,<b>
diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index 9eb26014d34b..1e0d101b020a 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -300,8 +300,8 @@ platforms. The AMD P-States mechanism is the more performance and energy
 efficiency frequency management method on AMD processors.
 
 
-AMD Pstate Driver Operation Modes
-=================================
+``amd-pstate`` Driver Operation Modes
+======================================
 
 ``amd_pstate`` CPPC has 3 operation modes: autonomous (active) mode,
 non-autonomous (passive) mode and guided autonomous (guided) mode.
@@ -353,6 +353,48 @@ is activated.  In this mode, driver requests minimum and maximum performance
 level and the platform autonomously selects a performance level in this range
 and appropriate to the current workload.
 
+``amd-pstate`` Preferred Core
+=================================
+
+The core frequency is subjected to the process variation in semiconductors.
+Not all cores are able to reach the maximum frequency respecting the
+infrastructure limits. Consequently, AMD has redefined the concept of
+maximum frequency of a part. This means that a fraction of cores can reach
+maximum frequency. To find the best process scheduling policy for a given
+scenario, OS needs to know the core ordering informed by the platform through
+highest performance capability register of the CPPC interface.
+
+``amd-pstate`` preferred core enables the scheduler to prefer scheduling on
+cores that can achieve a higher frequency with lower voltage. The preferred
+core rankings can dynamically change based on the workload, platform conditions,
+thermals and ageing.
+
+The priority metric will be initialized by the ``amd-pstate`` driver. The ``amd-pstate``
+driver will also determine whether or not ``amd-pstate`` preferred core is
+supported by the platform.
+
+``amd-pstate`` driver will provide an initial core ordering when the system boots.
+The platform uses the CPPC interfaces to communicate the core ranking to the
+operating system and scheduler to make sure that OS is choosing the cores
+with highest performance firstly for scheduling the process. When ``amd-pstate``
+driver receives a message with the highest performance change, it will
+update the core ranking and set the cpu's priority.
+
+``amd-pstate`` Preferred Core Switch
+=====================================
+Kernel Parameters
+-----------------
+
+``amd-pstate`` peferred core`` has two states: enable and disable.
+Enable/disable states can be chosen by different kernel parameters.
+Default enable ``amd-pstate`` preferred core.
+
+``amd_prefcore=disable``
+
+For systems that support ``amd-pstate`` preferred core, the core rankings will
+always be advertised by the platform. But OS can choose to ignore that via the
+kernel parameter ``amd_prefcore=disable``.
+
 User Space Interface in ``sysfs`` - General
 ===========================================
 
@@ -385,6 +427,19 @@ control its functionality at the system level.  They are located in the
         to the operation mode represented by that string - or to be
         unregistered in the "disable" case.
 
+``prefcore``
+	Preferred core state of the driver: "enabled" or "disabled".
+
+	"enabled"
+		Enable the ``amd-pstate`` preferred core.
+
+	"disabled"
+		Disable the ``amd-pstate`` preferred core
+
+
+        This attribute is read-only to check the state of preferred core set
+        by the kernel parameter.
+
 ``cpupower`` tool support for ``amd-pstate``
 ===============================================
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5edec175b9bf..29d110285438 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1054,8 +1054,9 @@ config SCHED_MC
 
 config SCHED_MC_PRIO
 	bool "CPU core priorities scheduler support"
-	depends on SCHED_MC && CPU_SUP_INTEL
-	select X86_INTEL_PSTATE
+	depends on SCHED_MC
+	select X86_INTEL_PSTATE if CPU_SUP_INTEL
+	select X86_AMD_PSTATE if CPU_SUP_AMD && ACPI
 	select CPU_FREQ
 	default y
 	help
diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
index d155a86a8614..a50e70abdf19 100644
--- a/drivers/acpi/cppc_acpi.c
+++ b/drivers/acpi/cppc_acpi.c
@@ -1158,6 +1158,19 @@ int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 }
 
 /**
+ * cppc_get_highest_perf - Get the highest performance register value.
+ * @cpunum: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
+{
+	return cppc_get_perf(cpunum, HIGHEST_PERF, highest_perf);
+}
+EXPORT_SYMBOL_GPL(cppc_get_highest_perf);
+
+/**
  * cppc_get_epp_perf - Get the epp register value.
  * @cpunum: CPU from which to get epp preference value.
  * @epp_perf: Return address.
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 4bd16b3f0781..67db60eda370 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -27,6 +27,7 @@
 #define ACPI_PROCESSOR_NOTIFY_PERFORMANCE 0x80
 #define ACPI_PROCESSOR_NOTIFY_POWER	0x81
 #define ACPI_PROCESSOR_NOTIFY_THROTTLING	0x82
+#define ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED	0x85
 
 MODULE_AUTHOR("Paul Diefenbaugh");
 MODULE_DESCRIPTION("ACPI Processor Driver");
@@ -83,6 +84,11 @@ static void acpi_processor_notify(acpi_handle handle, u32 event, void *data)
 		acpi_bus_generate_netlink_event(device->pnp.device_class,
 						  dev_name(&device->dev), event, 0);
 		break;
+	case ACPI_PROCESSOR_NOTIFY_HIGEST_PERF_CHANGED:
+		cpufreq_update_limits(pr->id);
+		acpi_bus_generate_netlink_event(device->pnp.device_class,
+						  dev_name(&device->dev), event, 0);
+		break;
 	default:
 		acpi_handle_debug(handle, "Unsupported event [0x%x]\n", event);
 		break;
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 1791d37fbc53..2015c9fcc3c9 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
 #include <linux/amd-pstate.h>
+#include <linux/topology.h>
 
 #include <acpi/processor.h>
 #include <acpi/cppc_acpi.h>
@@ -49,6 +50,7 @@
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
 #define AMD_PSTATE_TRANSITION_DELAY	1000
+#define AMD_PSTATE_PREFCORE_THRESHOLD	166
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -64,6 +66,7 @@ static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_UNDEFINED;
 static bool cppc_enabled;
+static bool amd_pstate_prefcore = true;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -297,13 +300,14 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
-	/*
-	 * TODO: Introduce AMD specific power feature.
-	 *
-	 * CPPC entry doesn't indicate the highest performance in some ASICs.
+	/* For platforms that do not support the preferred core feature, the
+	 * highest_pef may be configured with 166 or 255, to avoid max frequency
+	 * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as
+	 * the default max perf.
 	 */
-	highest_perf = amd_get_highest_perf();
-	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+	if (cpudata->hw_prefcore)
+		highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
+	else
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -311,6 +315,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
+	WRITE_ONCE(cpudata->prefcore_ranking, AMD_CPPC_HIGHEST_PERF(cap1));
 	WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1));
 	return 0;
 }
@@ -324,8 +329,9 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
-	highest_perf = amd_get_highest_perf();
-	if (highest_perf > cppc_perf.highest_perf)
+	if (cpudata->hw_prefcore)
+		highest_perf = AMD_PSTATE_PREFCORE_THRESHOLD;
+	else
 		highest_perf = cppc_perf.highest_perf;
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -334,6 +340,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	WRITE_ONCE(cpudata->prefcore_ranking, cppc_perf.highest_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf);
 
 	if (cppc_state == AMD_PSTATE_ACTIVE)
@@ -477,12 +484,19 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 
 static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 {
-	u32 max_limit_perf, min_limit_perf;
+	u32 max_limit_perf, min_limit_perf, lowest_perf;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	lowest_perf = READ_ONCE(cpudata->lowest_perf);
+	if (min_limit_perf < lowest_perf)
+		min_limit_perf = lowest_perf;
+
+	if (max_limit_perf < min_limit_perf)
+		max_limit_perf = min_limit_perf;
+
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
@@ -570,7 +584,7 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (target_perf < capacity)
 		des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity);
 
-	min_perf = READ_ONCE(cpudata->highest_perf);
+	min_perf = READ_ONCE(cpudata->lowest_perf);
 	if (_min_perf < capacity)
 		min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity);
 
@@ -706,6 +720,114 @@ static void amd_perf_ctl_reset(unsigned int cpu)
 	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
 }
 
+/*
+ * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks
+ * due to locking, so queue the work for later.
+ */
+static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
+{
+	sched_set_itmt_support();
+}
+static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
+
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf)
+{
+	int ret;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		u64 cap1;
+
+		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	} else {
+		u64 cppc_highest_perf;
+
+		ret = cppc_get_highest_perf(cpu, &cppc_highest_perf);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, cppc_highest_perf);
+	}
+
+	return (ret);
+}
+
+#define CPPC_MAX_PERF	U8_MAX
+
+static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
+{
+	int ret, prio;
+	u32 highest_perf;
+
+	ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf);
+	if (ret)
+		return;
+
+	cpudata->hw_prefcore = true;
+	/* check if CPPC preferred core feature is enabled*/
+	if (highest_perf < CPPC_MAX_PERF)
+		prio = (int)highest_perf;
+	else {
+		pr_debug("AMD CPPC preferred core is unsupported!\n");
+		cpudata->hw_prefcore = false;
+		return;
+	}
+
+	if (!amd_pstate_prefcore)
+		return;
+
+	/*
+	 * The priorities can be set regardless of whether or not
+	 * sched_set_itmt_support(true) has been called and it is valid to
+	 * update them at any time after it has been called.
+	 */
+	sched_set_itmt_core_prio(prio, cpudata->cpu);
+
+	schedule_work(&sched_prefcore_work);
+}
+
+static void amd_pstate_update_limits(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct amd_cpudata *cpudata = policy->driver_data;
+	u32 prev_high = 0, cur_high = 0;
+	int ret;
+	bool highest_perf_changed = false;
+
+	mutex_lock(&amd_pstate_driver_lock);
+	if ((!amd_pstate_prefcore) || (!cpudata->hw_prefcore))
+		goto free_cpufreq_put;
+
+	ret = amd_pstate_get_highest_perf(cpu, &cur_high);
+	if (ret)
+		goto free_cpufreq_put;
+
+	prev_high = READ_ONCE(cpudata->prefcore_ranking);
+	if (prev_high != cur_high) {
+		highest_perf_changed = true;
+		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
+
+		if (cur_high < CPPC_MAX_PERF)
+			sched_set_itmt_core_prio((int)cur_high, cpu);
+	}
+
+free_cpufreq_put:
+	cpufreq_cpu_put(policy);
+
+	if (!highest_perf_changed)
+		cpufreq_update_policy(cpu);
+
+	mutex_unlock(&amd_pstate_driver_lock);
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
@@ -727,6 +849,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpudata->cpu = policy->cpu;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -877,6 +1001,28 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
 	return sysfs_emit(buf, "%u\n", perf);
 }
 
+static ssize_t show_amd_pstate_prefcore_ranking(struct cpufreq_policy *policy,
+						char *buf)
+{
+	u32 perf;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	perf = READ_ONCE(cpudata->prefcore_ranking);
+
+	return sysfs_emit(buf, "%u\n", perf);
+}
+
+static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy,
+					   char *buf)
+{
+	bool hw_prefcore;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	hw_prefcore = READ_ONCE(cpudata->hw_prefcore);
+
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(hw_prefcore));
+}
+
 static ssize_t show_energy_performance_available_preferences(
 				struct cpufreq_policy *policy, char *buf)
 {
@@ -1074,18 +1220,29 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	return ret < 0 ? ret : count;
 }
 
+static ssize_t prefcore_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore));
+}
+
 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_ro(amd_pstate_prefcore_ranking);
+cpufreq_freq_attr_ro(amd_pstate_hw_prefcore);
 cpufreq_freq_attr_rw(energy_performance_preference);
 cpufreq_freq_attr_ro(energy_performance_available_preferences);
 static DEVICE_ATTR_RW(status);
+static DEVICE_ATTR_RO(prefcore);
 
 static struct freq_attr *amd_pstate_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_prefcore_ranking,
+	&amd_pstate_hw_prefcore,
 	NULL,
 };
 
@@ -1093,6 +1250,8 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_prefcore_ranking,
+	&amd_pstate_hw_prefcore,
 	&energy_performance_preference,
 	&energy_performance_available_preferences,
 	NULL,
@@ -1100,6 +1259,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 
 static struct attribute *pstate_global_attributes[] = {
 	&dev_attr_status.attr,
+	&dev_attr_prefcore.attr,
 	NULL
 };
 
@@ -1151,6 +1311,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	cpudata->cpu = policy->cpu;
 	cpudata->epp_policy = 0;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -1232,6 +1394,12 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	if (min_limit_perf < min_perf)
+		min_limit_perf = min_perf;
+
+	if (max_limit_perf < min_limit_perf)
+		max_limit_perf = min_limit_perf;
+
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 
@@ -1432,6 +1600,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.suspend	= amd_pstate_cpu_suspend,
 	.resume		= amd_pstate_cpu_resume,
 	.set_boost	= amd_pstate_set_boost,
+	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate",
 	.attr		= amd_pstate_attr,
 };
@@ -1446,6 +1615,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.online		= amd_pstate_epp_cpu_online,
 	.suspend	= amd_pstate_epp_suspend,
 	.resume		= amd_pstate_epp_resume,
+	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate-epp",
 	.attr		= amd_pstate_epp_attr,
 };
@@ -1567,7 +1737,17 @@ static int __init amd_pstate_param(char *str)
 
 	return amd_pstate_set_driver(mode_idx);
 }
+
+static int __init amd_prefcore_param(char *str)
+{
+	if (!strcmp(str, "disable"))
+		amd_pstate_prefcore = false;
+
+	return 0;
+}
+
 early_param("amd_pstate", amd_pstate_param);
+early_param("amd_prefcore", amd_prefcore_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 44db4f59c4cc..f6f8d7f450e7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -576,17 +576,26 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy)
 
 	latency = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
 	if (latency) {
+		unsigned int max_delay_us = 2 * MSEC_PER_SEC;
+
+		/*
+		 * If the platform already has high transition_latency, use it
+		 * as-is.
+		 */
+		if (latency > max_delay_us)
+			return latency;
+
 		/*
-		 * For platforms that can change the frequency very fast (< 10
+		 * For platforms that can change the frequency very fast (< 2
 		 * us), the above formula gives a decent transition delay. But
 		 * for platforms where transition_latency is in milliseconds, it
 		 * ends up giving unrealistic values.
 		 *
-		 * Cap the default transition delay to 10 ms, which seems to be
+		 * Cap the default transition delay to 2 ms, which seems to be
 		 * a reasonable amount of time after which we should reevaluate
 		 * the frequency.
 		 */
-		return min(latency * LATENCY_MULTIPLIER, (unsigned int)10000);
+		return min(latency * LATENCY_MULTIPLIER, max_delay_us);
 	}
 
 	return LATENCY_MULTIPLIER;
@@ -1571,7 +1580,8 @@ static int cpufreq_online(unsigned int cpu)
 	if (cpufreq_driver->ready)
 		cpufreq_driver->ready(policy);
 
-	if (cpufreq_thermal_control_enabled(cpufreq_driver))
+	/* Register cpufreq cooling only for a new policy */
+	if (new_policy && cpufreq_thermal_control_enabled(cpufreq_driver))
 		policy->cdev = of_cpufreq_cooling_register(policy);
 
 	pr_debug("initialization complete\n");
@@ -1655,11 +1665,6 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy)
 	else
 		policy->last_policy = policy->policy;
 
-	if (cpufreq_thermal_control_enabled(cpufreq_driver)) {
-		cpufreq_cooling_unregister(policy->cdev);
-		policy->cdev = NULL;
-	}
-
 	if (has_target())
 		cpufreq_exit_governor(policy);
 
@@ -1720,6 +1725,15 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 		return;
 	}
 
+	/*
+	 * Unregister cpufreq cooling once all the CPUs of the policy are
+	 * removed.
+	 */
+	if (cpufreq_thermal_control_enabled(cpufreq_driver)) {
+		cpufreq_cooling_unregister(policy->cdev);
+		policy->cdev = NULL;
+	}
+
 	/* We did light-weight exit earlier, do full tear down now */
 	if (cpufreq_driver->offline)
 		cpufreq_driver->exit(policy);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index c52d19d67557..a7c38b8b3e78 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -22,7 +22,6 @@
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
 #define MICRO_FREQUENCY_UP_THRESHOLD		(95)
-#define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(1)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 79619227ea51..dbbf299f4219 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -25,6 +25,7 @@
 #include <linux/acpi.h>
 #include <linux/vmalloc.h>
 #include <linux/pm_qos.h>
+#include <linux/bitfield.h>
 #include <trace/events/power.h>
 
 #include <asm/cpu.h>
@@ -201,8 +202,6 @@ struct global_params {
  * @prev_aperf:		Last APERF value read from APERF MSR
  * @prev_mperf:		Last MPERF value read from MPERF MSR
  * @prev_tsc:		Last timestamp counter (TSC) value
- * @prev_cummulative_iowait: IO Wait time difference from last and
- *			current sample
  * @sample:		Storage for storing last Sample data
  * @min_perf_ratio:	Minimum capacity in terms of PERF or HWP ratios
  * @max_perf_ratio:	Maximum capacity in terms of PERF or HWP ratios
@@ -241,7 +240,6 @@ struct cpudata {
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;
-	u64	prev_cummulative_iowait;
 	struct sample sample;
 	int32_t	min_perf_ratio;
 	int32_t	max_perf_ratio;
@@ -3407,14 +3405,31 @@ static bool intel_pstate_hwp_is_enabled(void)
 	return !!(value & 0x1);
 }
 
-static const struct x86_cpu_id intel_epp_balance_perf[] = {
+#define POWERSAVE_MASK			GENMASK(7, 0)
+#define BALANCE_POWER_MASK		GENMASK(15, 8)
+#define BALANCE_PERFORMANCE_MASK	GENMASK(23, 16)
+#define PERFORMANCE_MASK		GENMASK(31, 24)
+
+#define HWP_SET_EPP_VALUES(powersave, balance_power, balance_perf, performance) \
+	(FIELD_PREP_CONST(POWERSAVE_MASK, powersave) |\
+	 FIELD_PREP_CONST(BALANCE_POWER_MASK, balance_power) |\
+	 FIELD_PREP_CONST(BALANCE_PERFORMANCE_MASK, balance_perf) |\
+	 FIELD_PREP_CONST(PERFORMANCE_MASK, performance))
+
+#define HWP_SET_DEF_BALANCE_PERF_EPP(balance_perf) \
+	(HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, HWP_EPP_BALANCE_POWERSAVE,\
+	 balance_perf, HWP_EPP_PERFORMANCE))
+
+static const struct x86_cpu_id intel_epp_default[] = {
 	/*
 	 * Set EPP value as 102, this is the max suggested EPP
 	 * which can result in one core turbo frequency for
 	 * AlderLake Mobile CPUs.
 	 */
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 102),
-	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 32),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, HWP_SET_DEF_BALANCE_PERF_EPP(102)),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE,
+							HWP_EPP_BALANCE_POWERSAVE, 115, 16)),
 	{}
 };
 
@@ -3512,11 +3527,24 @@ hwp_cpu_matched:
 	intel_pstate_sysfs_expose_params();
 
 	if (hwp_active) {
-		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf);
+		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_default);
 		const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor);
 
-		if (id)
-			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data;
+		if (id) {
+			epp_values[EPP_INDEX_POWERSAVE] =
+					FIELD_GET(POWERSAVE_MASK, id->driver_data);
+			epp_values[EPP_INDEX_BALANCE_POWERSAVE] =
+					FIELD_GET(BALANCE_POWER_MASK, id->driver_data);
+			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] =
+					FIELD_GET(BALANCE_PERFORMANCE_MASK, id->driver_data);
+			epp_values[EPP_INDEX_PERFORMANCE] =
+					FIELD_GET(PERFORMANCE_MASK, id->driver_data);
+			pr_debug("Updated EPPs powersave:%x balanced power:%x balanced perf:%x performance:%x\n",
+				 epp_values[EPP_INDEX_POWERSAVE],
+				 epp_values[EPP_INDEX_BALANCE_POWERSAVE],
+				 epp_values[EPP_INDEX_BALANCE_PERFORMANCE],
+				 epp_values[EPP_INDEX_PERFORMANCE]);
+		}
 
 		if (hybrid_id) {
 			hybrid_scaling_factor = hybrid_id->driver_data;
diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
index 3a0995f8bce8..930b6afba6f4 100644
--- a/include/acpi/cppc_acpi.h
+++ b/include/acpi/cppc_acpi.h
@@ -139,6 +139,7 @@ struct cppc_cpudata {
 #ifdef CONFIG_ACPI_CPPC_LIB
 extern int cppc_get_desired_perf(int cpunum, u64 *desired_perf);
 extern int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf);
+extern int cppc_get_highest_perf(int cpunum, u64 *highest_perf);
 extern int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs);
 extern int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls);
 extern int cppc_set_enable(int cpu, bool enable);
@@ -167,6 +168,10 @@ static inline int cppc_get_nominal_perf(int cpunum, u64 *nominal_perf)
 {
 	return -ENOTSUPP;
 }
+static inline int cppc_get_highest_perf(int cpunum, u64 *highest_perf)
+{
+	return -ENOTSUPP;
+}
 static inline int cppc_get_perf_ctrs(int cpu, struct cppc_perf_fb_ctrs *perf_fb_ctrs)
 {
 	return -ENOTSUPP;
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
index 6ad02ad9c7b4..d21838835abd 100644
--- a/include/linux/amd-pstate.h
+++ b/include/linux/amd-pstate.h
@@ -39,11 +39,16 @@ struct amd_aperf_mperf {
  * @cppc_req_cached: cached performance request hints
  * @highest_perf: the maximum performance an individual processor may reach,
  *		  assuming ideal conditions
+ *		  For platforms that do not support the preferred core feature, the
+ *		  highest_pef may be configured with 166 or 255, to avoid max frequency
+ *		  calculated wrongly. we take the fixed value as the highest_perf.
  * @nominal_perf: the maximum sustained performance level of the processor,
  *		  assuming ideal operating conditions
  * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power
  *			   savings are achieved
  * @lowest_perf: the absolute lowest performance level of the processor
+ * @prefcore_ranking: the preferred core ranking, the higher value indicates a higher
+ * 		  priority.
  * @max_freq: the frequency that mapped to highest_perf
  * @min_freq: the frequency that mapped to lowest_perf
  * @nominal_freq: the frequency that mapped to nominal_perf
@@ -52,6 +57,9 @@ struct amd_aperf_mperf {
  * @prev: Last Aperf/Mperf/tsc count value read from register
  * @freq: current cpu frequency value
  * @boost_supported: check whether the Processor or SBIOS supports boost mode
+ * @hw_prefcore: check whether HW supports preferred core featue.
+ * 		  Only when hw_prefcore and early prefcore param are true,
+ * 		  AMD P-State driver supports preferred core featue.
  * @epp_policy: Last saved policy used to set energy-performance preference
  * @epp_cached: Cached CPPC energy-performance preference value
  * @policy: Cpufreq policy value
@@ -70,6 +78,7 @@ struct amd_cpudata {
 	u32	nominal_perf;
 	u32	lowest_nonlinear_perf;
 	u32	lowest_perf;
+	u32     prefcore_ranking;
 	u32     min_limit_perf;
 	u32     max_limit_perf;
 	u32     min_limit_freq;
@@ -85,6 +94,7 @@ struct amd_cpudata {
 
 	u64	freq;
 	bool	boost_supported;
+	bool	hw_prefcore;
 
 	/* EPP feature related attributes*/
 	s16	epp_policy;
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index afda5f24d3dd..692ea6e55129 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -263,6 +263,7 @@ static inline bool cpufreq_supports_freq_invariance(void)
 	return false;
 }
 static inline void disable_cpufreq(void) { }
+static inline void cpufreq_update_limits(unsigned int cpu) { }
 #endif
 
 #ifdef CONFIG_CPU_FREQ_STAT
@@ -568,9 +569,7 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
 
 /*
  * The polling frequency depends on the capability of the processor. Default
- * polling frequency is 1000 times the transition latency of the processor. The
- * ondemand governor will work on any processor with transition latency <= 10ms,
- * using appropriate sampling rate.
+ * polling frequency is 1000 times the transition latency of the processor.
  */
 #define LATENCY_MULTIPLIER		(1000)
 
@@ -1021,6 +1020,18 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy, int idx)
+{
+	unsigned int freq;
+
+	if (idx < 0)
+		return false;
+
+	freq = policy->freq_table[idx].frequency;
+
+	return freq == clamp_val(freq, policy->min, policy->max);
+}
+
 static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 						 unsigned int target_freq,
 						 unsigned int relation)
@@ -1054,7 +1065,8 @@ retry:
 		return 0;
 	}
 
-	if (idx < 0 && efficiencies) {
+	/* Limit frequency index to honor policy->min/max */
+	if (!cpufreq_is_in_limits(policy, idx) && efficiencies) {
 		efficiencies = false;
 		goto retry;
 	}