1 files changed, 557 insertions, 606 deletions

diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index d7630bab2516..c45bc98721d2 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -22,6 +22,7 @@
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/bitfield.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -64,13 +65,13 @@ static const char * const amd_pstate_mode_string[] = {
 	[AMD_PSTATE_PASSIVE]     = "passive",
 	[AMD_PSTATE_ACTIVE]      = "active",
 	[AMD_PSTATE_GUIDED]      = "guided",
-	NULL,
 };
+static_assert(ARRAY_SIZE(amd_pstate_mode_string) == AMD_PSTATE_MAX);
 
 const char *amd_pstate_get_mode_string(enum amd_pstate_mode mode)
 {
-	if (mode < 0 || mode >= AMD_PSTATE_MAX)
-		return NULL;
+	if (mode < AMD_PSTATE_UNDEFINED || mode >= AMD_PSTATE_MAX)
+		mode = AMD_PSTATE_UNDEFINED;
 	return amd_pstate_mode_string[mode];
 }
 EXPORT_SYMBOL_GPL(amd_pstate_get_mode_string);
@@ -84,7 +85,6 @@ static struct cpufreq_driver *current_pstate_driver;
 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;
 static struct quirk_entry *quirks;
 
@@ -110,6 +110,7 @@ enum energy_perf_value_index {
 	EPP_INDEX_BALANCE_PERFORMANCE,
 	EPP_INDEX_BALANCE_POWERSAVE,
 	EPP_INDEX_POWERSAVE,
+	EPP_INDEX_MAX,
 };
 
 static const char * const energy_perf_strings[] = {
@@ -118,8 +119,8 @@ static const char * const energy_perf_strings[] = {
 	[EPP_INDEX_BALANCE_PERFORMANCE] = "balance_performance",
 	[EPP_INDEX_BALANCE_POWERSAVE] = "balance_power",
 	[EPP_INDEX_POWERSAVE] = "power",
-	NULL
 };
+static_assert(ARRAY_SIZE(energy_perf_strings) == EPP_INDEX_MAX);
 
 static unsigned int epp_values[] = {
 	[EPP_INDEX_DEFAULT] = 0,
@@ -127,7 +128,8 @@ static unsigned int epp_values[] = {
 	[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_assert(ARRAY_SIZE(epp_values) == EPP_INDEX_MAX);
 
 typedef int (*cppc_mode_transition_fn)(int);
 
@@ -136,6 +138,19 @@ static struct quirk_entry quirk_amd_7k62 = {
 	.lowest_freq = 550,
 };
 
+static inline u8 freq_to_perf(union perf_cached perf, u32 nominal_freq, unsigned int freq_val)
+{
+	u32 perf_val = DIV_ROUND_UP_ULL((u64)freq_val * perf.nominal_perf, nominal_freq);
+
+	return (u8)clamp(perf_val, perf.lowest_perf, perf.highest_perf);
+}
+
+static inline u32 perf_to_freq(union perf_cached perf, u32 nominal_freq, u8 perf_val)
+{
+	return DIV_ROUND_UP_ULL((u64)nominal_freq * perf_val,
+				perf.nominal_perf);
+}
+
 static int __init dmi_matched_7k62_bios_bug(const struct dmi_system_id *dmi)
 {
 	/**
@@ -170,248 +185,280 @@ static inline int get_mode_idx_from_str(const char *str, size_t size)
 {
 	int i;
 
-	for (i=0; i < AMD_PSTATE_MAX; 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)
+static u8 msr_get_epp(struct amd_cpudata *cpudata)
 {
-	u64 epp;
+	u64 value;
 	int ret;
 
-	if (cpu_feature_enabled(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;
-		}
+	ret = rdmsrq_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &value);
+	if (ret < 0) {
+		pr_debug("Could not retrieve energy perf value (%d)\n", ret);
+		return ret;
 	}
 
-	return (s16)(epp & 0xff);
+	return FIELD_GET(AMD_CPPC_EPP_PERF_MASK, value);
 }
 
-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;
+DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_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 inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata)
+{
+	return static_call(amd_pstate_get_epp)(cpudata);
 }
 
-static void msr_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
-			       u32 des_perf, u32 max_perf, bool fast_switch)
+static u8 shmem_get_epp(struct amd_cpudata *cpudata)
 {
-	if (fast_switch)
-		wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
-	else
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
-			      READ_ONCE(cpudata->cppc_req_cached));
-}
+	u64 epp;
+	int ret;
 
-DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf);
+	ret = cppc_get_epp_perf(cpudata->cpu, &epp);
+	if (ret < 0) {
+		pr_debug("Could not retrieve energy perf value (%d)\n", ret);
+		return ret;
+	}
 
-static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
-					  u32 min_perf, u32 des_perf,
-					  u32 max_perf, bool fast_switch)
-{
-	static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
-					    max_perf, fast_switch);
+	return FIELD_GET(AMD_CPPC_EPP_PERF_MASK, epp);
 }
 
-static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp)
+static int msr_update_perf(struct cpufreq_policy *policy, u8 min_perf,
+			   u8 des_perf, u8 max_perf, u8 epp, bool fast_switch)
 {
-	int ret;
-	struct cppc_perf_ctrls perf_ctrls;
-
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		u64 value = READ_ONCE(cpudata->cppc_req_cached);
+	struct amd_cpudata *cpudata = policy->driver_data;
+	u64 value, prev;
+
+	value = prev = READ_ONCE(cpudata->cppc_req_cached);
+
+	value &= ~(AMD_CPPC_MAX_PERF_MASK | AMD_CPPC_MIN_PERF_MASK |
+		   AMD_CPPC_DES_PERF_MASK | AMD_CPPC_EPP_PERF_MASK);
+	value |= FIELD_PREP(AMD_CPPC_MAX_PERF_MASK, max_perf);
+	value |= FIELD_PREP(AMD_CPPC_DES_PERF_MASK, des_perf);
+	value |= FIELD_PREP(AMD_CPPC_MIN_PERF_MASK, min_perf);
+	value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp);
+
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		union perf_cached perf = READ_ONCE(cpudata->perf);
+
+		trace_amd_pstate_epp_perf(cpudata->cpu,
+					  perf.highest_perf,
+					  epp,
+					  min_perf,
+					  max_perf,
+					  policy->boost_enabled,
+					  value != prev);
+	}
 
-		value &= ~GENMASK_ULL(31, 24);
-		value |= (u64)epp << 24;
-		WRITE_ONCE(cpudata->cppc_req_cached, value);
+	if (value == prev)
+		return 0;
 
-		ret = wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-		if (!ret)
-			cpudata->epp_cached = epp;
+	if (fast_switch) {
+		wrmsrq(MSR_AMD_CPPC_REQ, value);
+		return 0;
 	} else {
-		amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
-					     cpudata->max_limit_perf, false);
+		int ret = wrmsrq_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
 
-		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);
+		if (ret)
 			return ret;
-		}
-		cpudata->epp_cached = epp;
 	}
 
-	return ret;
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
+
+	return 0;
 }
 
-static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
-		int pref_index)
+DEFINE_STATIC_CALL(amd_pstate_update_perf, msr_update_perf);
+
+static inline int amd_pstate_update_perf(struct cpufreq_policy *policy,
+					  u8 min_perf, u8 des_perf,
+					  u8 max_perf, u8 epp,
+					  bool fast_switch)
 {
-	int epp = -EINVAL;
+	return static_call(amd_pstate_update_perf)(policy, min_perf, des_perf,
+						   max_perf, epp, fast_switch);
+}
+
+static int msr_set_epp(struct cpufreq_policy *policy, u8 epp)
+{
+	struct amd_cpudata *cpudata = policy->driver_data;
+	u64 value, prev;
 	int ret;
 
-	if (!pref_index)
-		epp = cpudata->epp_default;
+	value = prev = READ_ONCE(cpudata->cppc_req_cached);
+	value &= ~AMD_CPPC_EPP_PERF_MASK;
+	value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp);
+
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		union perf_cached perf = cpudata->perf;
+
+		trace_amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf,
+					  epp,
+					  FIELD_GET(AMD_CPPC_MIN_PERF_MASK,
+						    cpudata->cppc_req_cached),
+					  FIELD_GET(AMD_CPPC_MAX_PERF_MASK,
+						    cpudata->cppc_req_cached),
+					  policy->boost_enabled,
+					  value != prev);
+	}
 
-	if (epp == -EINVAL)
-		epp = epp_values[pref_index];
+	if (value == prev)
+		return 0;
 
-	if (epp > 0 && cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
-		pr_debug("EPP cannot be set under performance policy\n");
-		return -EBUSY;
+	ret = wrmsrq_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
+	if (ret) {
+		pr_err("failed to set energy perf value (%d)\n", ret);
+		return ret;
 	}
 
-	ret = amd_pstate_set_epp(cpudata, epp);
+	/* update both so that msr_update_perf() can effectively check */
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
 
 	return ret;
 }
 
-static inline int msr_cppc_enable(bool enable)
+DEFINE_STATIC_CALL(amd_pstate_set_epp, msr_set_epp);
+
+static inline int amd_pstate_set_epp(struct cpufreq_policy *policy, u8 epp)
 {
-	int ret, cpu;
-	unsigned long logical_proc_id_mask = 0;
+	return static_call(amd_pstate_set_epp)(policy, epp);
+}
 
-       /*
-        * MSR_AMD_CPPC_ENABLE is write-once, once set it cannot be cleared.
-        */
-	if (!enable)
-		return 0;
+static int shmem_set_epp(struct cpufreq_policy *policy, u8 epp)
+{
+	struct amd_cpudata *cpudata = policy->driver_data;
+	struct cppc_perf_ctrls perf_ctrls;
+	u8 epp_cached;
+	u64 value;
+	int ret;
 
-	if (enable == cppc_enabled)
-		return 0;
 
-	for_each_present_cpu(cpu) {
-		unsigned long logical_id = topology_logical_package_id(cpu);
+	epp_cached = FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached);
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		union perf_cached perf = cpudata->perf;
 
-		if (test_bit(logical_id, &logical_proc_id_mask))
-			continue;
+		trace_amd_pstate_epp_perf(cpudata->cpu, perf.highest_perf,
+					  epp,
+					  FIELD_GET(AMD_CPPC_MIN_PERF_MASK,
+						    cpudata->cppc_req_cached),
+					  FIELD_GET(AMD_CPPC_MAX_PERF_MASK,
+						    cpudata->cppc_req_cached),
+					  policy->boost_enabled,
+					  epp != epp_cached);
+	}
 
-		set_bit(logical_id, &logical_proc_id_mask);
+	if (epp == epp_cached)
+		return 0;
 
-		ret = wrmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_ENABLE,
-				enable);
-		if (ret)
-			return ret;
+	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;
 	}
 
-	cppc_enabled = enable;
-	return 0;
+	value = READ_ONCE(cpudata->cppc_req_cached);
+	value &= ~AMD_CPPC_EPP_PERF_MASK;
+	value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp);
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
+
+	return ret;
 }
 
-static int shmem_cppc_enable(bool enable)
+static inline int msr_cppc_enable(struct cpufreq_policy *policy)
 {
-	int cpu, ret = 0;
-	struct cppc_perf_ctrls perf_ctrls;
-
-	if (enable == cppc_enabled)
-		return 0;
-
-	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 wrmsrq_safe_on_cpu(policy->cpu, MSR_AMD_CPPC_ENABLE, 1);
+}
 
-	cppc_enabled = enable;
-	return ret;
+static int shmem_cppc_enable(struct cpufreq_policy *policy)
+{
+	return cppc_set_enable(policy->cpu, 1);
 }
 
 DEFINE_STATIC_CALL(amd_pstate_cppc_enable, msr_cppc_enable);
 
-static inline int amd_pstate_cppc_enable(bool enable)
+static inline int amd_pstate_cppc_enable(struct cpufreq_policy *policy)
 {
-	return static_call(amd_pstate_cppc_enable)(enable);
+	return static_call(amd_pstate_cppc_enable)(policy);
 }
 
 static int msr_init_perf(struct amd_cpudata *cpudata)
 {
-	u64 cap1;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+	u64 cap1, numerator, cppc_req;
+	u8 min_perf;
 
-	int ret = rdmsrl_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
+	int ret = rdmsrq_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
-	WRITE_ONCE(cpudata->max_limit_perf, AMD_CPPC_HIGHEST_PERF(cap1));
-	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));
+	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
+	if (ret)
+		return ret;
+
+	ret = rdmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, &cppc_req);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->cppc_req_cached, cppc_req);
+	min_perf = FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cppc_req);
+
+	/*
+	 * Clear out the min_perf part to check if the rest of the MSR is 0, if yes, this is an
+	 * indication that the min_perf value is the one specified through the BIOS option
+	 */
+	cppc_req &= ~(AMD_CPPC_MIN_PERF_MASK);
+
+	if (!cppc_req)
+		perf.bios_min_perf = min_perf;
+
+	perf.highest_perf = numerator;
+	perf.max_limit_perf = numerator;
+	perf.min_limit_perf = FIELD_GET(AMD_CPPC_LOWEST_PERF_MASK, cap1);
+	perf.nominal_perf = FIELD_GET(AMD_CPPC_NOMINAL_PERF_MASK, cap1);
+	perf.lowest_nonlinear_perf = FIELD_GET(AMD_CPPC_LOWNONLIN_PERF_MASK, cap1);
+	perf.lowest_perf = FIELD_GET(AMD_CPPC_LOWEST_PERF_MASK, cap1);
+	WRITE_ONCE(cpudata->perf, perf);
+	WRITE_ONCE(cpudata->prefcore_ranking, FIELD_GET(AMD_CPPC_HIGHEST_PERF_MASK, cap1));
+
 	return 0;
 }
 
 static int shmem_init_perf(struct amd_cpudata *cpudata)
 {
 	struct cppc_perf_caps cppc_perf;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+	u64 numerator;
+	bool auto_sel;
 
 	int ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
 
-	WRITE_ONCE(cpudata->highest_perf, cppc_perf.highest_perf);
-	WRITE_ONCE(cpudata->max_limit_perf, cppc_perf.highest_perf);
-	WRITE_ONCE(cpudata->nominal_perf, cppc_perf.nominal_perf);
-	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
-		   cppc_perf.lowest_nonlinear_perf);
-	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
+	if (ret)
+		return ret;
+
+	perf.highest_perf = numerator;
+	perf.max_limit_perf = numerator;
+	perf.min_limit_perf = cppc_perf.lowest_perf;
+	perf.nominal_perf = cppc_perf.nominal_perf;
+	perf.lowest_nonlinear_perf = cppc_perf.lowest_nonlinear_perf;
+	perf.lowest_perf = cppc_perf.lowest_perf;
+	WRITE_ONCE(cpudata->perf, 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)
 		return 0;
 
-	ret = cppc_get_auto_sel_caps(cpudata->cpu, &cppc_perf);
+	ret = cppc_get_auto_sel(cpudata->cpu, &auto_sel);
 	if (ret) {
 		pr_warn("failed to get auto_sel, ret: %d\n", ret);
 		return 0;
@@ -433,17 +480,56 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
 	return static_call(amd_pstate_init_perf)(cpudata);
 }
 
-static void shmem_update_perf(struct amd_cpudata *cpudata,
-			     u32 min_perf, u32 des_perf,
-			     u32 max_perf, bool fast_switch)
+static int shmem_update_perf(struct cpufreq_policy *policy, u8 min_perf,
+			     u8 des_perf, u8 max_perf, u8 epp, bool fast_switch)
 {
+	struct amd_cpudata *cpudata = policy->driver_data;
 	struct cppc_perf_ctrls perf_ctrls;
+	u64 value, prev;
+	int ret;
+
+	if (cppc_state == AMD_PSTATE_ACTIVE) {
+		int ret = shmem_set_epp(policy, epp);
+
+		if (ret)
+			return ret;
+	}
+
+	value = prev = READ_ONCE(cpudata->cppc_req_cached);
+
+	value &= ~(AMD_CPPC_MAX_PERF_MASK | AMD_CPPC_MIN_PERF_MASK |
+		   AMD_CPPC_DES_PERF_MASK | AMD_CPPC_EPP_PERF_MASK);
+	value |= FIELD_PREP(AMD_CPPC_MAX_PERF_MASK, max_perf);
+	value |= FIELD_PREP(AMD_CPPC_DES_PERF_MASK, des_perf);
+	value |= FIELD_PREP(AMD_CPPC_MIN_PERF_MASK, min_perf);
+	value |= FIELD_PREP(AMD_CPPC_EPP_PERF_MASK, epp);
+
+	if (trace_amd_pstate_epp_perf_enabled()) {
+		union perf_cached perf = READ_ONCE(cpudata->perf);
+
+		trace_amd_pstate_epp_perf(cpudata->cpu,
+					  perf.highest_perf,
+					  epp,
+					  min_perf,
+					  max_perf,
+					  policy->boost_enabled,
+					  value != prev);
+	}
+
+	if (value == prev)
+		return 0;
 
 	perf_ctrls.max_perf = max_perf;
 	perf_ctrls.min_perf = min_perf;
 	perf_ctrls.desired_perf = des_perf;
 
-	cppc_set_perf(cpudata->cpu, &perf_ctrls);
+	ret = cppc_set_perf(cpudata->cpu, &perf_ctrls);
+	if (ret)
+		return ret;
+
+	WRITE_ONCE(cpudata->cppc_req_cached, value);
+
+	return 0;
 }
 
 static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
@@ -452,8 +538,8 @@ static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
 	unsigned long flags;
 
 	local_irq_save(flags);
-	rdmsrl(MSR_IA32_APERF, aperf);
-	rdmsrl(MSR_IA32_MPERF, mperf);
+	rdmsrq(MSR_IA32_APERF, aperf);
+	rdmsrq(MSR_IA32_MPERF, mperf);
 	tsc = rdtsc();
 
 	if (cpudata->prev.mperf == mperf || cpudata->prev.tsc == tsc) {
@@ -479,136 +565,106 @@ static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
 	return true;
 }
 
-static void amd_pstate_update(struct amd_cpudata *cpudata, u32 min_perf,
-			      u32 des_perf, u32 max_perf, bool fast_switch, int gov_flags)
+static void amd_pstate_update(struct amd_cpudata *cpudata, u8 min_perf,
+			      u8 des_perf, u8 max_perf, bool fast_switch, int gov_flags)
 {
-	unsigned long max_freq;
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpudata->cpu);
-	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
-	u32 nominal_perf = READ_ONCE(cpudata->nominal_perf);
-	u64 value = prev;
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu);
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+
+	if (!policy)
+		return;
+
+	/* limit the max perf when core performance boost feature is disabled */
+	if (!cpudata->boost_supported)
+		max_perf = min_t(u8, perf.nominal_perf, max_perf);
 
-	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
-	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
-	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
+	des_perf = clamp_t(u8, des_perf, min_perf, max_perf);
 
-	max_freq = READ_ONCE(cpudata->max_limit_freq);
-	policy->cur = div_u64(des_perf * max_freq, max_perf);
+	policy->cur = perf_to_freq(perf, cpudata->nominal_freq, des_perf);
 
 	if ((cppc_state == AMD_PSTATE_GUIDED) && (gov_flags & CPUFREQ_GOV_DYNAMIC_SWITCHING)) {
 		min_perf = des_perf;
 		des_perf = 0;
 	}
 
-	value &= ~AMD_CPPC_MIN_PERF(~0L);
-	value |= AMD_CPPC_MIN_PERF(min_perf);
-
-	value &= ~AMD_CPPC_DES_PERF(~0L);
-	value |= AMD_CPPC_DES_PERF(des_perf);
-
-	/* limit the max perf when core performance boost feature is disabled */
-	if (!cpudata->boost_supported)
-		max_perf = min_t(unsigned long, nominal_perf, max_perf);
-
-	value &= ~AMD_CPPC_MAX_PERF(~0L);
-	value |= AMD_CPPC_MAX_PERF(max_perf);
-
 	if (trace_amd_pstate_perf_enabled() && amd_pstate_sample(cpudata)) {
 		trace_amd_pstate_perf(min_perf, des_perf, max_perf, cpudata->freq,
 			cpudata->cur.mperf, cpudata->cur.aperf, cpudata->cur.tsc,
-				cpudata->cpu, (value != prev), fast_switch);
+				cpudata->cpu, fast_switch);
 	}
 
-	if (value == prev)
-		goto cpufreq_policy_put;
-
-	WRITE_ONCE(cpudata->cppc_req_cached, value);
-
-	amd_pstate_update_perf(cpudata, min_perf, des_perf,
-			       max_perf, fast_switch);
-
-cpufreq_policy_put:
-	cpufreq_cpu_put(policy);
+	amd_pstate_update_perf(policy, min_perf, des_perf, max_perf, 0, fast_switch);
 }
 
 static int amd_pstate_verify(struct cpufreq_policy_data *policy_data)
 {
 	/*
 	 * Initialize lower frequency limit (i.e.policy->min) with
-	 * lowest_nonlinear_frequency which is the most energy efficient
-	 * frequency. Override the initial value set by cpufreq core and
-	 * amd-pstate qos_requests.
+	 * lowest_nonlinear_frequency or the min frequency (if) specified in BIOS,
+	 * Override the initial value set by cpufreq core and amd-pstate qos_requests.
 	 */
 	if (policy_data->min == FREQ_QOS_MIN_DEFAULT_VALUE) {
-		struct cpufreq_policy *policy = cpufreq_cpu_get(policy_data->cpu);
+		struct cpufreq_policy *policy __free(put_cpufreq_policy) =
+					      cpufreq_cpu_get(policy_data->cpu);
 		struct amd_cpudata *cpudata;
+		union perf_cached perf;
 
 		if (!policy)
 			return -EINVAL;
 
 		cpudata = policy->driver_data;
-		policy_data->min = cpudata->lowest_nonlinear_freq;
-		cpufreq_cpu_put(policy);
+		perf = READ_ONCE(cpudata->perf);
+
+		if (perf.bios_min_perf)
+			policy_data->min = perf_to_freq(perf, cpudata->nominal_freq,
+							perf.bios_min_perf);
+		else
+			policy_data->min = cpudata->lowest_nonlinear_freq;
 	}
 
 	cpufreq_verify_within_cpu_limits(policy_data);
-	pr_debug("policy_max =%d, policy_min=%d\n", policy_data->max, policy_data->min);
 
 	return 0;
 }
 
-static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
+static void amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 {
-	u32 max_limit_perf, min_limit_perf, lowest_perf, max_perf;
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
 
-	if (cpudata->boost_supported && !policy->boost_enabled)
-		max_perf = READ_ONCE(cpudata->nominal_perf);
-	else
-		max_perf = READ_ONCE(cpudata->highest_perf);
-
-	max_limit_perf = div_u64(policy->max * max_perf, policy->cpuinfo.max_freq);
-	min_limit_perf = div_u64(policy->min * max_perf, policy->cpuinfo.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);
+	perf.max_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->max);
 	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
-	WRITE_ONCE(cpudata->min_limit_freq, policy->min);
 
-	return 0;
+	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		perf.min_limit_perf = min(perf.nominal_perf, perf.max_limit_perf);
+		WRITE_ONCE(cpudata->min_limit_freq, min(cpudata->nominal_freq, cpudata->max_limit_freq));
+	} else {
+		perf.min_limit_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->min);
+		WRITE_ONCE(cpudata->min_limit_freq, policy->min);
+	}
+
+	WRITE_ONCE(cpudata->perf, perf);
 }
 
 static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 				  unsigned int target_freq, bool fast_switch)
 {
 	struct cpufreq_freqs freqs;
-	struct amd_cpudata *cpudata = policy->driver_data;
-	unsigned long max_perf, min_perf, des_perf, cap_perf;
+	struct amd_cpudata *cpudata;
+	union perf_cached perf;
+	u8 des_perf;
 
-	if (!cpudata->max_freq)
-		return -ENODEV;
+	cpudata = policy->driver_data;
 
 	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
 		amd_pstate_update_min_max_limit(policy);
 
-	cap_perf = READ_ONCE(cpudata->highest_perf);
-	min_perf = READ_ONCE(cpudata->lowest_perf);
-	max_perf = cap_perf;
+	perf = READ_ONCE(cpudata->perf);
 
 	freqs.old = policy->cur;
 	freqs.new = target_freq;
 
-	des_perf = DIV_ROUND_CLOSEST(target_freq * cap_perf,
-				     cpudata->max_freq);
+	des_perf = freq_to_perf(perf, cpudata->nominal_freq, target_freq);
 
 	WARN_ON(fast_switch && !policy->fast_switch_enabled);
 	/*
@@ -619,8 +675,9 @@ static int amd_pstate_update_freq(struct cpufreq_policy *policy,
 	if (!fast_switch)
 		cpufreq_freq_transition_begin(policy, &freqs);
 
-	amd_pstate_update(cpudata, min_perf, des_perf,
-			max_perf, fast_switch, policy->governor->flags);
+	amd_pstate_update(cpudata, perf.min_limit_perf, des_perf,
+			  perf.max_limit_perf, fast_switch,
+			  policy->governor->flags);
 
 	if (!fast_switch)
 		cpufreq_freq_transition_end(policy, &freqs, false);
@@ -648,10 +705,10 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 				   unsigned long target_perf,
 				   unsigned long capacity)
 {
-	unsigned long max_perf, min_perf, des_perf,
-		      cap_perf, lowest_nonlinear_perf;
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	u8 max_perf, min_perf, des_perf, cap_perf;
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata;
+	union perf_cached perf;
 
 	if (!policy)
 		return;
@@ -661,45 +718,43 @@ static void amd_pstate_adjust_perf(unsigned int cpu,
 	if (policy->min != cpudata->min_limit_freq || policy->max != cpudata->max_limit_freq)
 		amd_pstate_update_min_max_limit(policy);
 
-
-	cap_perf = READ_ONCE(cpudata->highest_perf);
-	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
+	perf = READ_ONCE(cpudata->perf);
+	cap_perf = perf.highest_perf;
 
 	des_perf = cap_perf;
 	if (target_perf < capacity)
 		des_perf = DIV_ROUND_UP(cap_perf * target_perf, capacity);
 
-	min_perf = READ_ONCE(cpudata->lowest_perf);
 	if (_min_perf < capacity)
 		min_perf = DIV_ROUND_UP(cap_perf * _min_perf, capacity);
+	else
+		min_perf = cap_perf;
 
-	if (min_perf < lowest_nonlinear_perf)
-		min_perf = lowest_nonlinear_perf;
+	if (min_perf < perf.min_limit_perf)
+		min_perf = perf.min_limit_perf;
 
-	max_perf = cap_perf;
+	max_perf = perf.max_limit_perf;
 	if (max_perf < min_perf)
 		max_perf = min_perf;
 
-	des_perf = clamp_t(unsigned long, des_perf, min_perf, max_perf);
-
 	amd_pstate_update(cpudata, min_perf, des_perf, max_perf, true,
 			policy->governor->flags);
-	cpufreq_cpu_put(policy);
 }
 
 static int amd_pstate_cpu_boost_update(struct cpufreq_policy *policy, bool on)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
 	u32 nominal_freq, max_freq;
 	int ret = 0;
 
 	nominal_freq = READ_ONCE(cpudata->nominal_freq);
-	max_freq = READ_ONCE(cpudata->max_freq);
+	max_freq = perf_to_freq(perf, cpudata->nominal_freq, perf.highest_perf);
 
 	if (on)
 		policy->cpuinfo.max_freq = max_freq;
-	else if (policy->cpuinfo.max_freq > nominal_freq * 1000)
-		policy->cpuinfo.max_freq = nominal_freq * 1000;
+	else if (policy->cpuinfo.max_freq > nominal_freq)
+		policy->cpuinfo.max_freq = nominal_freq;
 
 	policy->max = policy->cpuinfo.max_freq;
 
@@ -721,12 +776,9 @@ static int amd_pstate_set_boost(struct cpufreq_policy *policy, int state)
 		pr_err("Boost mode is not supported by this processor or SBIOS\n");
 		return -EOPNOTSUPP;
 	}
-	mutex_lock(&amd_pstate_driver_lock);
+
 	ret = amd_pstate_cpu_boost_update(policy, state);
-	WRITE_ONCE(cpudata->boost_state, !ret ? state : false);
-	policy->boost_enabled = !ret ? state : false;
 	refresh_frequency_limits(policy);
-	mutex_unlock(&amd_pstate_driver_lock);
 
 	return ret;
 }
@@ -746,10 +798,7 @@ static int amd_pstate_init_boost_support(struct amd_cpudata *cpudata)
 		goto exit_err;
 	}
 
-	/* at least one CPU supports CPB, even if others fail later on to set up */
-	current_pstate_driver->boost_enabled = true;
-
-	ret = rdmsrl_on_cpu(cpudata->cpu, MSR_K7_HWCR, &boost_val);
+	ret = rdmsrq_on_cpu(cpudata->cpu, MSR_K7_HWCR, &boost_val);
 	if (ret) {
 		pr_err_once("failed to read initial CPU boost state!\n");
 		ret = -EIO;
@@ -768,18 +817,8 @@ exit_err:
 
 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();
+	wrmsrq_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
 }
-static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
 
 #define CPPC_MAX_PERF	U8_MAX
 
@@ -789,55 +828,44 @@ static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
 	if (!amd_pstate_prefcore)
 		return;
 
-	cpudata->hw_prefcore = true;
+	/* should use amd-hfi instead */
+	if (cpu_feature_enabled(X86_FEATURE_AMD_WORKLOAD_CLASS) &&
+	    IS_ENABLED(CONFIG_AMD_HFI)) {
+		amd_pstate_prefcore = false;
+		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((int)READ_ONCE(cpudata->highest_perf), cpudata->cpu);
+	cpudata->hw_prefcore = true;
 
-	schedule_work(&sched_prefcore_work);
+	/* Priorities must be initialized before ITMT support can be toggled on. */
+	sched_set_itmt_core_prio((int)READ_ONCE(cpudata->prefcore_ranking), cpudata->cpu);
 }
 
-static void amd_pstate_update_limits(unsigned int cpu)
+static void amd_pstate_update_limits(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
 	struct amd_cpudata *cpudata;
 	u32 prev_high = 0, cur_high = 0;
-	int ret;
 	bool highest_perf_changed = false;
+	unsigned int cpu = policy->cpu;
 
-	if (!policy)
+	if (!amd_pstate_prefcore)
 		return;
 
-	cpudata = policy->driver_data;
-
-	if (!amd_pstate_prefcore)
+	if (amd_get_highest_perf(cpu, &cur_high))
 		return;
 
-	mutex_lock(&amd_pstate_driver_lock);
-	ret = amd_get_highest_perf(cpu, &cur_high);
-	if (ret)
-		goto free_cpufreq_put;
+	cpudata = policy->driver_data;
 
 	prev_high = READ_ONCE(cpudata->prefcore_ranking);
 	highest_perf_changed = (prev_high != cur_high);
 	if (highest_perf_changed) {
 		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
 
-		if (cur_high < CPPC_MAX_PERF)
+		if (cur_high < CPPC_MAX_PERF) {
 			sched_set_itmt_core_prio((int)cur_high, cpu);
+			sched_update_asym_prefer_cpu(cpu, prev_high, cur_high);
+		}
 	}
-
-free_cpufreq_put:
-	cpufreq_cpu_put(policy);
-
-	if (!highest_perf_changed)
-		cpufreq_update_policy(cpu);
-
-	mutex_unlock(&amd_pstate_driver_lock);
 }
 
 /*
@@ -846,10 +874,10 @@ free_cpufreq_put:
  */
 static u32 amd_pstate_get_transition_delay_us(unsigned int cpu)
 {
-	u32 transition_delay_ns;
+	int transition_delay_ns;
 
 	transition_delay_ns = cppc_get_transition_latency(cpu);
-	if (transition_delay_ns == CPUFREQ_ETERNAL) {
+	if (transition_delay_ns < 0) {
 		if (cpu_feature_enabled(X86_FEATURE_AMD_FAST_CPPC))
 			return AMD_PSTATE_FAST_CPPC_TRANSITION_DELAY;
 		else
@@ -865,67 +893,55 @@ static u32 amd_pstate_get_transition_delay_us(unsigned int cpu)
  */
 static u32 amd_pstate_get_transition_latency(unsigned int cpu)
 {
-	u32 transition_latency;
+	int transition_latency;
 
 	transition_latency = cppc_get_transition_latency(cpu);
-	if (transition_latency  == CPUFREQ_ETERNAL)
+	if (transition_latency < 0)
 		return AMD_PSTATE_TRANSITION_LATENCY;
 
 	return transition_latency;
 }
 
 /*
- * amd_pstate_init_freq: Initialize the max_freq, min_freq,
- *                       nominal_freq and lowest_nonlinear_freq for
- *                       the @cpudata object.
+ * amd_pstate_init_freq: Initialize the nominal_freq and lowest_nonlinear_freq
+ *			 for the @cpudata object.
  *
- *  Requires: highest_perf, lowest_perf, nominal_perf and
- *            lowest_nonlinear_perf members of @cpudata to be
- *            initialized.
+ * Requires: all perf members of @cpudata to be initialized.
  *
- *  Returns 0 on success, non-zero value on failure.
+ * Returns 0 on success, non-zero value on failure.
  */
 static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 {
-	int ret;
-	u32 min_freq, max_freq;
-	u64 numerator;
-	u32 nominal_perf, nominal_freq;
-	u32 lowest_nonlinear_perf, lowest_nonlinear_freq;
-	u32 boost_ratio, lowest_nonlinear_ratio;
+	u32 min_freq, max_freq, nominal_freq, lowest_nonlinear_freq;
 	struct cppc_perf_caps cppc_perf;
+	union perf_cached perf;
+	int ret;
 
 	ret = cppc_get_perf_caps(cpudata->cpu, &cppc_perf);
 	if (ret)
 		return ret;
-
-	if (quirks && quirks->lowest_freq)
-		min_freq = quirks->lowest_freq * 1000;
-	else
-		min_freq = cppc_perf.lowest_freq * 1000;
+	perf = READ_ONCE(cpudata->perf);
 
 	if (quirks && quirks->nominal_freq)
-		nominal_freq = quirks->nominal_freq ;
+		nominal_freq = quirks->nominal_freq;
 	else
 		nominal_freq = cppc_perf.nominal_freq;
+	nominal_freq *= 1000;
 
-	nominal_perf = READ_ONCE(cpudata->nominal_perf);
+	if (quirks && quirks->lowest_freq) {
+		min_freq = quirks->lowest_freq;
+		perf.lowest_perf = freq_to_perf(perf, nominal_freq, min_freq);
+		WRITE_ONCE(cpudata->perf, perf);
+	} else
+		min_freq = cppc_perf.lowest_freq;
 
-	ret = amd_get_boost_ratio_numerator(cpudata->cpu, &numerator);
-	if (ret)
-		return ret;
-	boost_ratio = div_u64(numerator << SCHED_CAPACITY_SHIFT, nominal_perf);
-	max_freq = (nominal_freq * boost_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
+	min_freq *= 1000;
 
-	lowest_nonlinear_perf = READ_ONCE(cpudata->lowest_nonlinear_perf);
-	lowest_nonlinear_ratio = div_u64(lowest_nonlinear_perf << SCHED_CAPACITY_SHIFT,
-					 nominal_perf);
-	lowest_nonlinear_freq = (nominal_freq * lowest_nonlinear_ratio >> SCHED_CAPACITY_SHIFT) * 1000;
+	WRITE_ONCE(cpudata->nominal_freq, nominal_freq);
 
-	WRITE_ONCE(cpudata->min_freq, min_freq);
+	max_freq = perf_to_freq(perf, nominal_freq, perf.highest_perf);
+	lowest_nonlinear_freq = perf_to_freq(perf, nominal_freq, perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_nonlinear_freq, lowest_nonlinear_freq);
-	WRITE_ONCE(cpudata->nominal_freq, nominal_freq);
-	WRITE_ONCE(cpudata->max_freq, max_freq);
 
 	/**
 	 * Below values need to be initialized correctly, otherwise driver will fail to load
@@ -935,13 +951,13 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 	 */
 	if (min_freq <= 0 || max_freq <= 0 || nominal_freq <= 0 || min_freq > max_freq) {
 		pr_err("min_freq(%d) or max_freq(%d) or nominal_freq(%d) value is incorrect\n",
-			min_freq, max_freq, nominal_freq * 1000);
+			min_freq, max_freq, nominal_freq);
 		return -EINVAL;
 	}
 
-	if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq * 1000) {
+	if (lowest_nonlinear_freq <= min_freq || lowest_nonlinear_freq > nominal_freq) {
 		pr_err("lowest_nonlinear_freq(%d) value is out of range [min_freq(%d), nominal_freq(%d)]\n",
-			lowest_nonlinear_freq, min_freq, nominal_freq * 1000);
+			lowest_nonlinear_freq, min_freq, nominal_freq);
 		return -EINVAL;
 	}
 
@@ -950,9 +966,10 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
-	int min_freq, max_freq, ret;
-	struct device *dev;
 	struct amd_cpudata *cpudata;
+	union perf_cached perf;
+	struct device *dev;
+	int ret;
 
 	/*
 	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
@@ -983,19 +1000,23 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto free_cpudata1;
 
-	min_freq = READ_ONCE(cpudata->min_freq);
-	max_freq = READ_ONCE(cpudata->max_freq);
-
 	policy->cpuinfo.transition_latency = amd_pstate_get_transition_latency(policy->cpu);
 	policy->transition_delay_us = amd_pstate_get_transition_delay_us(policy->cpu);
 
-	policy->min = min_freq;
-	policy->max = max_freq;
+	perf = READ_ONCE(cpudata->perf);
 
-	policy->cpuinfo.min_freq = min_freq;
-	policy->cpuinfo.max_freq = max_freq;
+	policy->cpuinfo.min_freq = policy->min = perf_to_freq(perf,
+							      cpudata->nominal_freq,
+							      perf.lowest_perf);
+	policy->cpuinfo.max_freq = policy->max = perf_to_freq(perf,
+							      cpudata->nominal_freq,
+							      perf.highest_perf);
+
+	ret = amd_pstate_cppc_enable(policy);
+	if (ret)
+		goto free_cpudata1;
 
-	policy->boost_enabled = READ_ONCE(cpudata->boost_supported);
+	policy->boost_supported = READ_ONCE(cpudata->boost_supported);
 
 	/* It will be updated by governor */
 	policy->cur = policy->cpuinfo.min_freq;
@@ -1017,9 +1038,6 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 		goto free_cpudata2;
 	}
 
-	cpudata->max_limit_freq = max_freq;
-	cpudata->min_limit_freq = min_freq;
-
 	policy->driver_data = cpudata;
 
 	if (!current_pstate_driver->adjust_perf)
@@ -1030,6 +1048,7 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 free_cpudata2:
 	freq_qos_remove_request(&cpudata->req[0]);
 free_cpudata1:
+	pr_warn("Failed to initialize CPU %d: %d\n", policy->cpu, ret);
 	kfree(cpudata);
 	return ret;
 }
@@ -1037,6 +1056,10 @@ free_cpudata1:
 static void amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+
+	/* Reset CPPC_REQ MSR to the BIOS value */
+	amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
 
 	freq_qos_remove_request(&cpudata->req[1]);
 	freq_qos_remove_request(&cpudata->req[0]);
@@ -1044,28 +1067,6 @@ static void amd_pstate_cpu_exit(struct cpufreq_policy *policy)
 	kfree(cpudata);
 }
 
-static int amd_pstate_cpu_resume(struct cpufreq_policy *policy)
-{
-	int ret;
-
-	ret = amd_pstate_cppc_enable(true);
-	if (ret)
-		pr_err("failed to enable amd-pstate during resume, return %d\n", ret);
-
-	return ret;
-}
-
-static int amd_pstate_cpu_suspend(struct cpufreq_policy *policy)
-{
-	int ret;
-
-	ret = amd_pstate_cppc_enable(false);
-	if (ret)
-		pr_err("failed to disable amd-pstate during suspend, return %d\n", ret);
-
-	return ret;
-}
-
 /* Sysfs attributes */
 
 /*
@@ -1076,27 +1077,27 @@ static int amd_pstate_cpu_suspend(struct cpufreq_policy *policy)
 static ssize_t show_amd_pstate_max_freq(struct cpufreq_policy *policy,
 					char *buf)
 {
-	int max_freq;
-	struct amd_cpudata *cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata;
+	union perf_cached perf;
 
-	max_freq = READ_ONCE(cpudata->max_freq);
-	if (max_freq < 0)
-		return max_freq;
+	cpudata = policy->driver_data;
+	perf = READ_ONCE(cpudata->perf);
 
-	return sysfs_emit(buf, "%u\n", max_freq);
+	return sysfs_emit(buf, "%u\n",
+			  perf_to_freq(perf, cpudata->nominal_freq, perf.highest_perf));
 }
 
 static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *policy,
 						     char *buf)
 {
-	int freq;
-	struct amd_cpudata *cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata;
+	union perf_cached perf;
 
-	freq = READ_ONCE(cpudata->lowest_nonlinear_freq);
-	if (freq < 0)
-		return freq;
+	cpudata = policy->driver_data;
+	perf = READ_ONCE(cpudata->perf);
 
-	return sysfs_emit(buf, "%u\n", freq);
+	return sysfs_emit(buf, "%u\n",
+			  perf_to_freq(perf, cpudata->nominal_freq, perf.lowest_nonlinear_perf));
 }
 
 /*
@@ -1106,18 +1107,17 @@ static ssize_t show_amd_pstate_lowest_nonlinear_freq(struct cpufreq_policy *poli
 static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
 					    char *buf)
 {
-	u32 perf;
-	struct amd_cpudata *cpudata = policy->driver_data;
+	struct amd_cpudata *cpudata;
 
-	perf = READ_ONCE(cpudata->highest_perf);
+	cpudata = policy->driver_data;
 
-	return sysfs_emit(buf, "%u\n", perf);
+	return sysfs_emit(buf, "%u\n", cpudata->perf.highest_perf);
 }
 
 static ssize_t show_amd_pstate_prefcore_ranking(struct cpufreq_policy *policy,
 						char *buf)
 {
-	u32 perf;
+	u8 perf;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	perf = READ_ONCE(cpudata->prefcore_ranking);
@@ -1139,16 +1139,15 @@ static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy,
 static ssize_t show_energy_performance_available_preferences(
 				struct cpufreq_policy *policy, char *buf)
 {
-	int i = 0;
-	int offset = 0;
+	int offset = 0, i;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
 		return sysfs_emit_at(buf, offset, "%s\n",
 				energy_perf_strings[EPP_INDEX_PERFORMANCE]);
 
-	while (energy_perf_strings[i] != NULL)
-		offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i++]);
+	for (i = 0; i < ARRAY_SIZE(energy_perf_strings); i++)
+		offset += sysfs_emit_at(buf, offset, "%s ", energy_perf_strings[i]);
 
 	offset += sysfs_emit_at(buf, offset, "\n");
 
@@ -1159,40 +1158,61 @@ 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;
+	u8 epp;
 
-	ret = sscanf(buf, "%20s", str_preference);
-	if (ret != 1)
-		return -EINVAL;
-
-	ret = match_string(energy_perf_strings, -1, str_preference);
+	ret = sysfs_match_string(energy_perf_strings, buf);
 	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);
+	if (!ret)
+		epp = cpudata->epp_default;
+	else
+		epp = epp_values[ret];
+
+	if (epp > 0 && policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		pr_debug("EPP cannot be set under performance policy\n");
+		return -EBUSY;
+	}
+
+	ret = amd_pstate_set_epp(policy, epp);
 
-	return ret ?: count;
+	return ret ? ret : count;
 }
 
 static ssize_t show_energy_performance_preference(
 				struct cpufreq_policy *policy, char *buf)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
-	int preference;
+	u8 preference, epp;
 
-	preference = amd_pstate_get_energy_pref_index(cpudata);
-	if (preference < 0)
-		return preference;
+	epp = FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached);
+
+	switch (epp) {
+	case AMD_CPPC_EPP_PERFORMANCE:
+		preference = EPP_INDEX_PERFORMANCE;
+		break;
+	case AMD_CPPC_EPP_BALANCE_PERFORMANCE:
+		preference = EPP_INDEX_BALANCE_PERFORMANCE;
+		break;
+	case AMD_CPPC_EPP_BALANCE_POWERSAVE:
+		preference = EPP_INDEX_BALANCE_POWERSAVE;
+		break;
+	case AMD_CPPC_EPP_POWERSAVE:
+		preference = EPP_INDEX_POWERSAVE;
+		break;
+	default:
+		return -EINVAL;
+	}
 
 	return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]);
 }
 
 static void amd_pstate_driver_cleanup(void)
 {
-	amd_pstate_cppc_enable(false);
+	if (amd_pstate_prefcore)
+		sched_clear_itmt_support();
+
 	cppc_state = AMD_PSTATE_DISABLE;
 	current_pstate_driver = NULL;
 }
@@ -1226,13 +1246,8 @@ static int amd_pstate_register_driver(int mode)
 
 	cppc_state = mode;
 
-	ret = amd_pstate_cppc_enable(true);
-	if (ret) {
-		pr_err("failed to enable cppc during amd-pstate driver registration, return %d\n",
-		       ret);
-		amd_pstate_driver_cleanup();
-		return ret;
-	}
+	/* at least one CPU supports CPB */
+	current_pstate_driver->boost_enabled = cpu_feature_enabled(X86_FEATURE_CPB);
 
 	ret = cpufreq_register_driver(current_pstate_driver);
 	if (ret) {
@@ -1240,6 +1255,10 @@ static int amd_pstate_register_driver(int mode)
 		return ret;
 	}
 
+	/* Enable ITMT support once all CPUs have initialized their asym priorities. */
+	if (amd_pstate_prefcore)
+		sched_set_itmt_support();
+
 	return 0;
 }
 
@@ -1259,7 +1278,7 @@ static int amd_pstate_change_mode_without_dvr_change(int mode)
 	if (cpu_feature_enabled(X86_FEATURE_CPPC) || cppc_state == AMD_PSTATE_ACTIVE)
 		return 0;
 
-	for_each_present_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		cppc_set_auto_sel(cpu, (cppc_state == AMD_PSTATE_PASSIVE) ? 0 : 1);
 	}
 
@@ -1316,6 +1335,12 @@ static ssize_t amd_pstate_show_status(char *buf)
 	return sysfs_emit(buf, "%s\n", amd_pstate_mode_string[cppc_state]);
 }
 
+int amd_pstate_get_status(void)
+{
+	return cppc_state;
+}
+EXPORT_SYMBOL_GPL(amd_pstate_get_status);
+
 int amd_pstate_update_status(const char *buf, size_t size)
 {
 	int mode_idx;
@@ -1324,12 +1349,13 @@ int amd_pstate_update_status(const char *buf, size_t size)
 		return -EINVAL;
 
 	mode_idx = get_mode_idx_from_str(buf, size);
+	if (mode_idx < 0)
+		return mode_idx;
 
-	if (mode_idx < 0 || mode_idx >= AMD_PSTATE_MAX)
-		return -EINVAL;
-
-	if (mode_state_machine[cppc_state][mode_idx])
+	if (mode_state_machine[cppc_state][mode_idx]) {
+		guard(mutex)(&amd_pstate_driver_lock);
 		return mode_state_machine[cppc_state][mode_idx](mode_idx);
+	}
 
 	return 0;
 }
@@ -1338,13 +1364,10 @@ EXPORT_SYMBOL_GPL(amd_pstate_update_status);
 static ssize_t status_show(struct device *dev,
 			   struct device_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);
+	guard(mutex)(&amd_pstate_driver_lock);
 
-	return ret;
+	return amd_pstate_show_status(buf);
 }
 
 static ssize_t status_store(struct device *a, struct device_attribute *b,
@@ -1353,9 +1376,7 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	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;
 }
@@ -1430,10 +1451,10 @@ static bool amd_pstate_acpi_pm_profile_undefined(void)
 
 static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 {
-	int min_freq, max_freq, ret;
 	struct amd_cpudata *cpudata;
+	union perf_cached perf;
 	struct device *dev;
-	u64 value;
+	int ret;
 
 	/*
 	 * Resetting PERF_CTL_MSR will put the CPU in P0 frequency,
@@ -1449,7 +1470,6 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 		return -ENOMEM;
 
 	cpudata->cpu = policy->cpu;
-	cpudata->epp_policy = 0;
 
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
@@ -1465,50 +1485,49 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	if (ret)
 		goto free_cpudata1;
 
-	min_freq = READ_ONCE(cpudata->min_freq);
-	max_freq = READ_ONCE(cpudata->max_freq);
-
-	policy->cpuinfo.min_freq = min_freq;
-	policy->cpuinfo.max_freq = max_freq;
-	/* It will be updated by governor */
-	policy->cur = policy->cpuinfo.min_freq;
+	perf = READ_ONCE(cpudata->perf);
 
+	policy->cpuinfo.min_freq = policy->min = perf_to_freq(perf,
+							      cpudata->nominal_freq,
+							      perf.lowest_perf);
+	policy->cpuinfo.max_freq = policy->max = perf_to_freq(perf,
+							      cpudata->nominal_freq,
+							      perf.highest_perf);
 	policy->driver_data = cpudata;
 
-	cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata, 0);
+	ret = amd_pstate_cppc_enable(policy);
+	if (ret)
+		goto free_cpudata1;
+
+	/* It will be updated by governor */
+	policy->cur = policy->cpuinfo.min_freq;
 
-	policy->min = policy->cpuinfo.min_freq;
-	policy->max = policy->cpuinfo.max_freq;
 
-	policy->boost_enabled = READ_ONCE(cpudata->boost_supported);
+	policy->boost_supported = READ_ONCE(cpudata->boost_supported);
 
 	/*
 	 * Set the policy to provide a valid fallback value in case
 	 * the default cpufreq governor is neither powersave nor performance.
 	 */
 	if (amd_pstate_acpi_pm_profile_server() ||
-	    amd_pstate_acpi_pm_profile_undefined())
+	    amd_pstate_acpi_pm_profile_undefined()) {
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
-	else
+		cpudata->epp_default = amd_pstate_get_epp(cpudata);
+	} else {
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
-
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		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);
+		cpudata->epp_default = AMD_CPPC_EPP_BALANCE_PERFORMANCE;
 	}
 
+	ret = amd_pstate_set_epp(policy, cpudata->epp_default);
+	if (ret)
+		return ret;
+
 	current_pstate_driver->adjust_perf = NULL;
 
 	return 0;
 
 free_cpudata1:
+	pr_warn("Failed to initialize CPU %d: %d\n", policy->cpu, ret);
 	kfree(cpudata);
 	return ret;
 }
@@ -1518,6 +1537,11 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata) {
+		union perf_cached perf = READ_ONCE(cpudata->perf);
+
+		/* Reset CPPC_REQ MSR to the BIOS value */
+		amd_pstate_update_perf(policy, perf.bios_min_perf, 0U, 0U, 0U, false);
+
 		kfree(cpudata);
 		policy->driver_data = NULL;
 	}
@@ -1525,54 +1549,26 @@ static void amd_pstate_epp_cpu_exit(struct cpufreq_policy *policy)
 	pr_debug("CPU %d exiting\n", policy->cpu);
 }
 
-static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
+static int amd_pstate_epp_update_limit(struct cpufreq_policy *policy, bool policy_change)
 {
 	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);
-	amd_pstate_update_min_max_limit(policy);
-
-	max_perf = clamp_t(unsigned long, max_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
-	min_perf = clamp_t(unsigned long, min_perf, cpudata->min_limit_perf,
-			cpudata->max_limit_perf);
-	value = READ_ONCE(cpudata->cppc_req_cached);
-
-	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
-		min_perf = min(cpudata->nominal_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);
+	union perf_cached perf;
+	u8 epp;
 
-	cpudata->epp_policy = cpudata->policy;
-
-	/* Get BIOS pre-defined epp value */
-	epp = amd_pstate_get_epp(cpudata, value);
-	if (epp < 0) {
-		/**
-		 * This return value can only be negative for shared_memory
-		 * systems where EPP register read/write not supported.
-		 */
-		return epp;
-	}
+	if (policy_change ||
+	    policy->min != cpudata->min_limit_freq ||
+	    policy->max != cpudata->max_limit_freq)
+		amd_pstate_update_min_max_limit(policy);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
 		epp = 0;
+	else
+		epp = FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached);
 
-	WRITE_ONCE(cpudata->cppc_req_cached, value);
-	return amd_pstate_set_epp(cpudata, epp);
+	perf = READ_ONCE(cpudata->perf);
+
+	return amd_pstate_update_perf(policy, perf.min_limit_perf, 0U,
+				      perf.max_limit_perf, epp, false);
 }
 
 static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
@@ -1583,12 +1579,9 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 	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;
 
-	ret = amd_pstate_epp_update_limit(policy);
+	ret = amd_pstate_epp_update_limit(policy, true);
 	if (ret)
 		return ret;
 
@@ -1601,107 +1594,62 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void amd_pstate_epp_reenable(struct amd_cpudata *cpudata)
+static int amd_pstate_cpu_online(struct cpufreq_policy *policy)
 {
-	struct cppc_perf_ctrls perf_ctrls;
-	u64 value, max_perf;
-	int ret;
-
-	ret = amd_pstate_cppc_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 (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-	} else {
-		perf_ctrls.max_perf = max_perf;
-		cppc_set_perf(cpudata->cpu, &perf_ctrls);
-		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(cpudata->epp_cached);
-		cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
-	}
+	return amd_pstate_cppc_enable(policy);
 }
 
-static int amd_pstate_epp_cpu_online(struct cpufreq_policy *policy)
+static int amd_pstate_cpu_offline(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
 
-	pr_debug("AMD CPU Core %d going online\n", cpudata->cpu);
-
-	if (cppc_state == AMD_PSTATE_ACTIVE) {
-		amd_pstate_epp_reenable(cpudata);
-		cpudata->suspended = false;
-	}
-
-	return 0;
-}
-
-static void amd_pstate_epp_offline(struct cpufreq_policy *policy)
-{
-	struct amd_cpudata *cpudata = policy->driver_data;
-	struct cppc_perf_ctrls perf_ctrls;
-	int min_perf;
-	u64 value;
-
-	min_perf = READ_ONCE(cpudata->lowest_perf);
-	value = READ_ONCE(cpudata->cppc_req_cached);
-
-	mutex_lock(&amd_pstate_limits_lock);
-	if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
-		cpudata->epp_policy = CPUFREQ_POLICY_UNKNOWN;
-
-		/* Set max perf same as min perf */
-		value &= ~AMD_CPPC_MAX_PERF(~0L);
-		value |= AMD_CPPC_MAX_PERF(min_perf);
-		value &= ~AMD_CPPC_MIN_PERF(~0L);
-		value |= AMD_CPPC_MIN_PERF(min_perf);
-		wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ, value);
-	} else {
-		perf_ctrls.desired_perf = 0;
-		perf_ctrls.min_perf = min_perf;
-		perf_ctrls.max_perf = min_perf;
-		cppc_set_perf(cpudata->cpu, &perf_ctrls);
-		perf_ctrls.energy_perf = AMD_CPPC_ENERGY_PERF_PREF(HWP_EPP_BALANCE_POWERSAVE);
-		cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
-	}
-	mutex_unlock(&amd_pstate_limits_lock);
+	/*
+	 * Reset CPPC_REQ MSR to the BIOS value, this will allow us to retain the BIOS specified
+	 * min_perf value across kexec reboots. If this CPU is just onlined normally after this, the
+	 * limits, epp and desired perf will get reset to the cached values in cpudata struct
+	 */
+	return amd_pstate_update_perf(policy, perf.bios_min_perf,
+				     FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached),
+				     false);
 }
 
-static int amd_pstate_epp_cpu_offline(struct cpufreq_policy *policy)
+static int amd_pstate_suspend(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+	int ret;
 
-	pr_debug("AMD CPU Core %d going offline\n", cpudata->cpu);
-
-	if (cpudata->suspended)
-		return 0;
+	/*
+	 * Reset CPPC_REQ MSR to the BIOS value, this will allow us to retain the BIOS specified
+	 * min_perf value across kexec reboots. If this CPU is just resumed back without kexec,
+	 * the limits, epp and desired perf will get reset to the cached values in cpudata struct
+	 */
+	ret = amd_pstate_update_perf(policy, perf.bios_min_perf,
+				     FIELD_GET(AMD_CPPC_DES_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_MAX_PERF_MASK, cpudata->cppc_req_cached),
+				     FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached),
+				     false);
+	if (ret)
+		return ret;
 
-	if (cppc_state == AMD_PSTATE_ACTIVE)
-		amd_pstate_epp_offline(policy);
+	/* set this flag to avoid setting core offline*/
+	cpudata->suspended = true;
 
 	return 0;
 }
 
-static int amd_pstate_epp_suspend(struct cpufreq_policy *policy)
+static int amd_pstate_resume(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
-	int ret;
-
-	/* avoid suspending when EPP is not enabled */
-	if (cppc_state != AMD_PSTATE_ACTIVE)
-		return 0;
-
-	/* set this flag to avoid setting core offline*/
-	cpudata->suspended = true;
+	union perf_cached perf = READ_ONCE(cpudata->perf);
+	int cur_perf = freq_to_perf(perf, cpudata->nominal_freq, policy->cur);
 
-	/* disable CPPC in lowlevel firmware */
-	ret = amd_pstate_cppc_enable(false);
-	if (ret)
-		pr_err("failed to suspend, return %d\n", ret);
-
-	return 0;
+	/* Set CPPC_REQ to last sane value until the governor updates it */
+	return amd_pstate_update_perf(policy, perf.min_limit_perf, cur_perf, perf.max_limit_perf,
+				      0U, false);
 }
 
 static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
@@ -1709,12 +1657,12 @@ static int amd_pstate_epp_resume(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata->suspended) {
-		mutex_lock(&amd_pstate_limits_lock);
+		int ret;
 
 		/* enable amd pstate from suspend state*/
-		amd_pstate_epp_reenable(cpudata);
-
-		mutex_unlock(&amd_pstate_limits_lock);
+		ret = amd_pstate_epp_update_limit(policy, false);
+		if (ret)
+			return ret;
 
 		cpudata->suspended = false;
 	}
@@ -1729,8 +1677,10 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.fast_switch    = amd_pstate_fast_switch,
 	.init		= amd_pstate_cpu_init,
 	.exit		= amd_pstate_cpu_exit,
-	.suspend	= amd_pstate_cpu_suspend,
-	.resume		= amd_pstate_cpu_resume,
+	.online		= amd_pstate_cpu_online,
+	.offline	= amd_pstate_cpu_offline,
+	.suspend	= amd_pstate_suspend,
+	.resume		= amd_pstate_resume,
 	.set_boost	= amd_pstate_set_boost,
 	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate",
@@ -1743,9 +1693,9 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.setpolicy	= amd_pstate_epp_set_policy,
 	.init		= amd_pstate_epp_cpu_init,
 	.exit		= amd_pstate_epp_cpu_exit,
-	.offline	= amd_pstate_epp_cpu_offline,
-	.online		= amd_pstate_epp_cpu_online,
-	.suspend	= amd_pstate_epp_suspend,
+	.offline	= amd_pstate_cpu_offline,
+	.online		= amd_pstate_cpu_online,
+	.suspend	= amd_pstate_suspend,
 	.resume		= amd_pstate_epp_resume,
 	.update_limits	= amd_pstate_update_limits,
 	.set_boost	= amd_pstate_set_boost,
@@ -1867,12 +1817,8 @@ static int __init amd_pstate_init(void)
 		static_call_update(amd_pstate_cppc_enable, shmem_cppc_enable);
 		static_call_update(amd_pstate_init_perf, shmem_init_perf);
 		static_call_update(amd_pstate_update_perf, shmem_update_perf);
-	}
-
-	ret = amd_pstate_register_driver(cppc_state);
-	if (ret) {
-		pr_err("failed to register with return %d\n", ret);
-		return ret;
+		static_call_update(amd_pstate_get_epp, shmem_get_epp);
+		static_call_update(amd_pstate_set_epp, shmem_set_epp);
 	}
 
 	if (amd_pstate_prefcore) {
@@ -1881,6 +1827,12 @@ static int __init amd_pstate_init(void)
 			return ret;
 	}
 
+	ret = amd_pstate_register_driver(cppc_state);
+	if (ret) {
+		pr_err("failed to register with return %d\n", ret);
+		return ret;
+	}
+
 	dev_root = bus_get_dev_root(&cpu_subsys);
 	if (dev_root) {
 		ret = sysfs_create_group(&dev_root->kobj, &amd_pstate_global_attr_group);
@@ -1895,7 +1847,6 @@ static int __init amd_pstate_init(void)
 
 global_attr_free:
 	cpufreq_unregister_driver(current_pstate_driver);
-	amd_pstate_cppc_enable(false);
 	return ret;
 }
 device_initcall(amd_pstate_init);