diff --git a/Documentation/admin-guide/pm/amd-pstate.rst b/Documentation/admin-guide/pm/amd-pstate.rst
index a95e2ebce005..c7bf7cc2db87 100644
--- a/Documentation/admin-guide/pm/amd-pstate.rst
+++ b/Documentation/admin-guide/pm/amd-pstate.rst
@@ -317,7 +317,9 @@ 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. ``custom`` designates that integer values 0-255 may be written
-as well.  This attribute is read-only.
+as well. ``dynamic`` designates that the EPP is modified dynamically
+on kernel events. See ``Dynamic energy performance profile`` section below to
+know more about the ``dynamic`` mode. This attribute is read-only.
 
 ``energy_performance_preference``
 
@@ -326,13 +328,11 @@ and user can change current preference according to energy or performance needs
 Coarse named profiles are available in the attribute
 ``energy_performance_available_preferences``.
 Users can also write individual integer values between 0 to 255.
-When dynamic EPP is enabled, writes to energy_performance_preference are blocked
-even when EPP feature is enabled by platform firmware. Lower epp values shift the bias
-towards improved performance while a higher epp value shifts the bias towards
-power-savings. The exact impact can change from one platform to the other.
-If a valid integer was last written, then a number will be returned on future reads.
-If a valid string was last written then a string will be returned on future reads.
-This attribute is read-write.
+Lower epp values shift the bias towards improved performance while a higher epp
+value shifts the bias towards power-savings. The exact impact can change from
+one platform to the other. If a valid integer was last written, then a number
+will be returned on future reads. If a valid string was last written then a
+string will be returned on future reads. This attribute is read-write.
 
 ``boost``
 The `boost` sysfs attribute provides control over the CPU core
@@ -356,21 +356,20 @@ Other performance and frequency values can be read back from
 Dynamic energy performance profile
 ==================================
 The amd-pstate driver supports dynamically selecting the energy performance
-profile based on whether the machine is running on AC or DC power.
+profile based on the system profile and the current power source in active mode.
 
-Whether this behavior is enabled by default depends on the kernel command line option
-``amd_dynamic_epp`` is set. This behavior can also be overridden
-at runtime by the sysfs file ``/sys/devices/system/cpu/amd_pstate/dynamic_epp``.
+The ``dynamic`` mode is listed in
+``/sys/devices/system/cpu/cpuX/cpufreq/energy_performance_available_preferences``
+when available while running under the ``powersave`` governor. The ``dynamic``
+mode can be toggled on by writing the same to the sysfs file
+``/sys/devices/system/cpu/cpuX/cpufreq/energy_performance_preference`` when
+available.
 
-When set to enabled, the driver will select a different energy performance
-profile when the machine is running on battery or AC power. The driver will
-also register with the platform profile handler to receive notifications of
-user desired power state and react to those.
-When set to disabled, the driver will not change the energy performance profile
-based on the power source and will not react to user desired power state.
-
-Attempting to manually write to the ``energy_performance_preference`` sysfs
-file will fail when ``dynamic_epp`` is enabled.
+When ``energy_performance_preference`` is set to ``dynamic``, the driver will
+select a different energy performance profile when the machine is running on
+battery or AC power. The driver will also register with the platform profile
+handler to receive notifications of user desired power state and react to
+those.
 
 ``amd-pstate`` vs ``acpi-cpufreq``
 ======================================
diff --git a/Documentation/admin-guide/pm/cpufreq.rst b/Documentation/admin-guide/pm/cpufreq.rst
index 8831cface585..34baf20cc202 100644
--- a/Documentation/admin-guide/pm/cpufreq.rst
+++ b/Documentation/admin-guide/pm/cpufreq.rst
@@ -497,7 +497,7 @@ This governor exposes the following tunables:
 	represented by it to be 1.5 times as high as the transition latency
 	(the default)::
 
-	# echo `$(($(cat cpuinfo_transition_latency) * 3 / 2))` > ondemand/sampling_rate
+	# echo $(($(cat cpuinfo_transition_latency) * 3 / 2)) > ondemand/sampling_rate
 
 ``up_threshold``
 	If the estimated CPU load is above this value (in percent), the governor
diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
index 735b29f76438..e23773680e05 100644
--- a/drivers/cpufreq/amd-pstate-ut.c
+++ b/drivers/cpufreq/amd-pstate-ut.c
@@ -59,6 +59,7 @@ static int amd_pstate_ut_check_freq(u32 index);
 static int amd_pstate_ut_epp(u32 index);
 static int amd_pstate_ut_check_driver(u32 index);
 static int amd_pstate_ut_check_freq_attrs(u32 index);
+static int amd_pstate_ut_check_floor_freq(u32 index);
 
 static struct amd_pstate_ut_struct amd_pstate_ut_cases[] = {
 	{"amd_pstate_ut_acpi_cpc_valid",    amd_pstate_ut_acpi_cpc_valid   },
@@ -68,6 +69,7 @@ static struct amd_pstate_ut_struct amd_pstate_ut_cases[] = {
 	{"amd_pstate_ut_epp",               amd_pstate_ut_epp              },
 	{"amd_pstate_ut_check_driver",      amd_pstate_ut_check_driver     },
 	{"amd_pstate_ut_check_freq_attrs",  amd_pstate_ut_check_freq_attrs },
+	{"amd_pstate_ut_check_floor_freq",  amd_pstate_ut_check_floor_freq },
 };
 
 static bool test_in_list(const char *list, const char *name)
@@ -275,6 +277,7 @@ static int amd_pstate_set_mode(enum amd_pstate_mode mode)
 static int amd_pstate_ut_epp(u32 index)
 {
 	static const char * const epp_strings[] = {
+		"dynamic",
 		"power",
 		"balance_power",
 		"balance_performance",
@@ -282,10 +285,10 @@ static int amd_pstate_ut_epp(u32 index)
 	};
 	char *buf __free(cleanup_page) = NULL;
 	struct cpufreq_policy *policy = NULL;
+	unsigned long orig_dynamic_epp = 0;
 	enum amd_pstate_mode orig_mode;
 	struct amd_cpudata *cpudata;
 	unsigned long orig_policy;
-	bool orig_dynamic_epp;
 	int ret, cpu = 0;
 	u16 epp;
 	int i;
@@ -294,9 +297,11 @@ static int amd_pstate_ut_epp(u32 index)
 	if (!policy)
 		return -ENODEV;
 
-	cpudata = policy->driver_data;
 	orig_mode = amd_pstate_get_status();
-	orig_dynamic_epp = cpudata->dynamic_epp;
+	if (policy->driver_data) {
+		cpudata = policy->driver_data;
+		orig_dynamic_epp = cpudata->dynamic_epp;
+	}
 
 	/* Drop reference before potential driver change. */
 	cpufreq_cpu_put(policy);
@@ -321,16 +326,6 @@ static int amd_pstate_ut_epp(u32 index)
 	orig_policy = cpudata->policy;
 	cpudata->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	/*
-	 * Disable dynamic EPP before running test. If "orig_dynamic_epp" is
-	 * true, the  driver will do a redundant switch at the end and there
-	 * is no need for enabling it again at the end of the test.
-	 */
-	if (cpudata->dynamic_epp) {
-		pr_debug("Dynamic EPP is enabled, disabling it\n");
-		amd_pstate_clear_dynamic_epp(policy);
-	}
-
 	for (epp = 0; epp <= U8_MAX; epp++) {
 		u8 val;
 
@@ -367,6 +362,11 @@ static int amd_pstate_ut_epp(u32 index)
 		if (ret < 0)
 			goto out;
 		strreplace(buf, '\n', '\0');
+		/*
+		 * "dynamic" mode reports the EPP as "dynamic(profile:X)"
+		 * Trim at "(" and just compare tie the epp string.
+		 */
+		strreplace(buf, '(', '\0');
 
 		if (strcmp(buf, epp_strings[i])) {
 			pr_err("String EPP value mismatch: %s != %s\n", buf, epp_strings[i]);
@@ -380,18 +380,23 @@ static int amd_pstate_ut_epp(u32 index)
 out:
 	if (policy) {
 		cpudata->policy = orig_policy;
+		/*
+		 * If the driver had enabled dynamic_epp to begin with,
+		 * restore it here before dropping policy reference.
+		 */
+		if (orig_dynamic_epp) {
+			int ret2;
+
+			ret2 = store_energy_performance_preference(policy,
+								  epp_strings[0],
+								  strlen(epp_strings[0]));
+			if (!ret && (ret2 < 0))
+				ret = ret2;
+		}
 		up_write(&policy->rwsem);
 		cpufreq_cpu_put(policy);
 	}
 
-	if (orig_dynamic_epp) {
-		int ret2;
-
-		ret2 = amd_pstate_set_mode(AMD_PSTATE_DISABLE);
-		if (!ret && ret2)
-			ret = ret2;
-	}
-
 	if (orig_mode != amd_pstate_get_status()) {
 		int ret2;
 
@@ -557,9 +562,88 @@ static int amd_pstate_ut_check_freq_attrs(u32 index)
 	return ret;
 }
 
+static int amd_pstate_ut_check_floor_freq(u32 index)
+{
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = NULL;
+	char *buf __free(cleanup_page) = NULL;
+	unsigned int orig_floor_freq;
+	unsigned int floor_freq;
+	int ret, cpu = 0;
+
+	if (!cpu_feature_enabled(X86_FEATURE_CPPC_PERF_PRIO))
+		return -EOPNOTSUPP;
+
+	policy = cpufreq_cpu_get(cpu);
+	if (!policy)
+		return -ENODEV;
+
+	buf = (char *)__get_free_page(GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	guard(rwsem_write)(&policy->rwsem);
+
+	if (!policy->driver_data)
+		return -ENODEV;
+
+	/* Retrieve original floor frequency */
+	memset(buf, 0, PAGE_SIZE);
+	ret = show_amd_pstate_floor_freq(policy, buf);
+	if (ret < 0)
+		return ret;
+
+	ret = kstrtou32(buf, 0, &orig_floor_freq);
+	if (ret)
+		return ret;
+
+	memset(buf, 0, PAGE_SIZE);
+	snprintf(buf, PAGE_SIZE, "%u", policy->cpuinfo.min_freq);
+
+	/* Set floor frequency to cpuinfo.min_freq */
+	ret = store_amd_pstate_floor_freq(policy, buf, strlen(buf));
+	if (ret < 0) {
+		pr_err("Failed to set floor frequency to %s\n", buf);
+		return ret;
+	}
+
+	memset(buf, 0, PAGE_SIZE);
+	ret = show_amd_pstate_floor_freq(policy, buf);
+	if (ret < 0)
+		return ret;
+
+	strreplace(buf, '\n', '\0');
+	ret = kstrtou32(buf, 0, &floor_freq);
+	if (ret)
+		return ret;
+
+	/* Confirm sysfs reflects the change correctly. */
+	if (floor_freq != policy->cpuinfo.min_freq) {
+		pr_err("Floor frequency value mismatch: %u != %u\n",
+		       floor_freq, policy->cpuinfo.min_freq);
+		return -EINVAL;
+	}
+
+	memset(buf, 0, PAGE_SIZE);
+	snprintf(buf, PAGE_SIZE, "%u", orig_floor_freq);
+
+	/* Restore the original value. */
+	ret = store_amd_pstate_floor_freq(policy, buf, strlen(buf));
+	if (ret < 0) {
+		pr_err("Failed to restore floor frequency to %s\n", buf);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int __init amd_pstate_ut_init(void)
 {
 	u32 i = 0, arr_size = ARRAY_SIZE(amd_pstate_ut_cases);
+	enum amd_pstate_mode mode = amd_pstate_get_status();
+
+	/* don't test if no running amd-pstate driver */
+	if (mode == AMD_PSTATE_UNDEFINED || mode == AMD_PSTATE_DISABLE)
+		return -EOPNOTSUPP;
 
 	for (i = 0; i < arr_size; i++) {
 		int ret;
@@ -570,10 +654,16 @@ static int __init amd_pstate_ut_init(void)
 
 		ret = amd_pstate_ut_cases[i].func(i);
 
-		if (ret)
+		if (ret) {
+			/* Platform does not support the feature being tested. */
+			if (ret == -EOPNOTSUPP) {
+				pr_err("%-4d %-20s\t skipped!\n", i+1, amd_pstate_ut_cases[i].name);
+				continue;
+			}
 			pr_err("%-4d %-20s\t fail: %d!\n", i+1, amd_pstate_ut_cases[i].name, ret);
-		else
+		} else {
 			pr_info("%-4d %-20s\t success!\n", i+1, amd_pstate_ut_cases[i].name);
+		}
 	}
 
 	return 0;
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 3a6b4b224a66..d4ff8b228f86 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -75,7 +75,7 @@ const char *amd_pstate_get_mode_string(enum amd_pstate_mode mode)
 		mode = AMD_PSTATE_UNDEFINED;
 	return amd_pstate_mode_string[mode];
 }
-EXPORT_SYMBOL_GPL(amd_pstate_get_mode_string);
+EXPORT_SYMBOL_FOR_PSTATE_UT(amd_pstate_get_mode_string);
 
 struct quirk_entry {
 	u32 nominal_freq;
@@ -87,7 +87,6 @@ static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_UNDEFINED;
 static bool amd_pstate_prefcore = true;
-static bool dynamic_epp;
 static struct quirk_entry *quirks;
 
 /*
@@ -106,6 +105,7 @@ static struct quirk_entry *quirks;
  *	3		balance_power
  *	4		power
  *	5		custom (for raw EPP values)
+ *	6		dynamic (platform profile driven selection)
  */
 enum energy_perf_value_index {
 	EPP_INDEX_DEFAULT = 0,
@@ -114,6 +114,7 @@ enum energy_perf_value_index {
 	EPP_INDEX_BALANCE_POWERSAVE,
 	EPP_INDEX_POWERSAVE,
 	EPP_INDEX_CUSTOM,
+	EPP_INDEX_DYNAMIC,
 	EPP_INDEX_MAX,
 };
 
@@ -124,6 +125,7 @@ static const char * const energy_perf_strings[] = {
 	[EPP_INDEX_BALANCE_POWERSAVE] = "balance_power",
 	[EPP_INDEX_POWERSAVE] = "power",
 	[EPP_INDEX_CUSTOM] = "custom",
+	[EPP_INDEX_DYNAMIC] = "dynamic",
 };
 static_assert(ARRAY_SIZE(energy_perf_strings) == EPP_INDEX_MAX);
 
@@ -134,7 +136,7 @@ static unsigned int epp_values[] = {
 	[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 - 1);
+static_assert(ARRAY_SIZE(epp_values) == EPP_INDEX_MAX - 2);
 
 typedef int (*cppc_mode_transition_fn)(int);
 
@@ -199,7 +201,7 @@ static inline int get_mode_idx_from_str(const char *str, size_t size)
 
 static DEFINE_MUTEX(amd_pstate_driver_lock);
 
-static u8 msr_get_epp(struct amd_cpudata *cpudata)
+static int msr_get_epp(struct amd_cpudata *cpudata)
 {
 	u64 value;
 	int ret;
@@ -215,12 +217,12 @@ static u8 msr_get_epp(struct amd_cpudata *cpudata)
 
 DEFINE_STATIC_CALL(amd_pstate_get_epp, msr_get_epp);
 
-static inline s16 amd_pstate_get_epp(struct amd_cpudata *cpudata)
+static inline int amd_pstate_get_epp(struct amd_cpudata *cpudata)
 {
 	return static_call(amd_pstate_get_epp)(cpudata);
 }
 
-static u8 shmem_get_epp(struct amd_cpudata *cpudata)
+static int shmem_get_epp(struct amd_cpudata *cpudata)
 {
 	u64 epp;
 	int ret;
@@ -462,7 +464,6 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
 {
 	union perf_cached perf = READ_ONCE(cpudata->perf);
 	u64 cap1, numerator, cppc_req;
-	u8 min_perf;
 
 	int ret = rdmsrq_safe_on_cpu(cpudata->cpu, MSR_AMD_CPPC_CAP1,
 				     &cap1);
@@ -478,16 +479,6 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
 		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;
@@ -495,6 +486,7 @@ static int msr_init_perf(struct amd_cpudata *cpudata)
 	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);
+	perf.bios_min_perf = FIELD_GET(AMD_CPPC_MIN_PERF_MASK, cppc_req);
 	WRITE_ONCE(cpudata->perf, perf);
 	WRITE_ONCE(cpudata->prefcore_ranking, FIELD_GET(AMD_CPPC_HIGHEST_PERF_MASK, cap1));
 	WRITE_ONCE(cpudata->floor_perf_cnt, FIELD_GET(AMD_CPPC_FLOOR_PERF_CNT_MASK, cap1));
@@ -526,9 +518,6 @@ static int shmem_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->perf, perf);
 	WRITE_ONCE(cpudata->prefcore_ranking, cppc_perf.highest_perf);
 
-	if (cppc_state == AMD_PSTATE_ACTIVE)
-		return 0;
-
 	ret = cppc_get_auto_sel(cpudata->cpu, &auto_sel);
 	if (ret) {
 		pr_warn("failed to get auto_sel, ret: %d\n", ret);
@@ -702,9 +691,12 @@ static void amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		u8 min_limit_perf = perf.bios_min_perf ?: perf.nominal_perf;
+		u32 min_limit_freq;
+
 		/*
-		 * For performance policy, set MinPerf to nominal_perf rather than
-		 * highest_perf or lowest_nonlinear_perf.
+		 * For performance policy, set MinPerf to nominal_perf / bios_min_perf
+		 * rather than highest_perf or lowest_nonlinear_perf.
 		 *
 		 * Per commit 0c411b39e4f4c, using highest_perf was observed
 		 * to cause frequency throttling on power-limited platforms, leading to
@@ -712,11 +704,18 @@ static void amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 		 * performance too much for HPC workloads requiring high frequency
 		 * operation and minimal wakeup latency from idle states.
 		 *
-		 * nominal_perf therefore provides a balance by avoiding throttling
-		 * while still maintaining enough performance for HPC workloads.
+		 * nominal_perf therefore provides a balanced default by avoiding
+		 * throttling while still maintaining enough performance for HPC
+		 * workloads when bios_min_perf is not available.
+		 *
+		 * When bios_min_perf is available, users have profiled their workloads
+		 * to understand the best idling frequency. Use that instead.
 		 */
-		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));
+		min_limit_perf = min(min_limit_perf, perf.max_limit_perf);
+		min_limit_freq = perf_to_freq(perf, cpudata->nominal_freq, min_limit_perf);
+		perf.min_limit_perf = min_limit_perf;
+
+		WRITE_ONCE(cpudata->min_limit_freq, min(min_limit_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);
@@ -782,6 +781,7 @@ static unsigned int amd_pstate_fast_switch(struct cpufreq_policy *policy,
 static void amd_pstate_adjust_perf(struct cpufreq_policy *policy,
 				   unsigned long _min_perf,
 				   unsigned long target_perf,
+				   unsigned long _max_perf,
 				   unsigned long capacity)
 {
 	u8 max_perf, min_perf, des_perf, cap_perf;
@@ -1037,6 +1037,13 @@ static int amd_pstate_init_freq(struct amd_cpudata *cpudata)
 		return -EINVAL;
 	}
 
+	if (perf.bios_min_perf) {
+		u32 bios_min_freq = perf_to_freq(perf, cpudata->nominal_freq, perf.bios_min_perf);
+
+		pr_debug("Found Requested CPU Min Frequency of %uKHz on CPU%d\n",
+			 bios_min_freq, cpudata->cpu);
+	}
+
 	return 0;
 }
 
@@ -1173,6 +1180,9 @@ static int amd_pstate_power_supply_notifier(struct notifier_block *nb,
 	if (cpudata->current_profile != PLATFORM_PROFILE_BALANCED)
 		return 0;
 
+	if (!policy)
+		return NOTIFY_OK;
+
 	epp = amd_pstate_get_balanced_epp(policy);
 
 	ret = amd_pstate_set_epp(policy, epp);
@@ -1182,6 +1192,24 @@ static int amd_pstate_power_supply_notifier(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static int amd_pstate_get_epp_from_platform_profile(struct cpufreq_policy *policy,
+						    enum platform_profile_option profile)
+{
+	switch (profile) {
+	case PLATFORM_PROFILE_PERFORMANCE:
+		return AMD_CPPC_EPP_PERFORMANCE;
+	case PLATFORM_PROFILE_BALANCED:
+		return amd_pstate_get_balanced_epp(policy);
+	case PLATFORM_PROFILE_LOW_POWER:
+		return AMD_CPPC_EPP_POWERSAVE;
+	default:
+		break;
+	}
+
+	pr_err("Unknown Platform Profile %d\n", profile);
+	return -EOPNOTSUPP;
+}
+
 static int amd_pstate_profile_probe(void *drvdata, unsigned long *choices)
 {
 	set_bit(PLATFORM_PROFILE_LOW_POWER, choices);
@@ -1207,28 +1235,19 @@ static int amd_pstate_profile_set(struct device *dev,
 	struct amd_cpudata *cpudata = dev_get_drvdata(dev);
 	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpudata->cpu);
 	int ret;
+	u8 epp;
 
-	switch (profile) {
-	case PLATFORM_PROFILE_LOW_POWER:
-		ret = amd_pstate_set_epp(policy, AMD_CPPC_EPP_POWERSAVE);
-		if (ret)
-			return ret;
-		break;
-	case PLATFORM_PROFILE_BALANCED:
-		ret = amd_pstate_set_epp(policy,
-					 amd_pstate_get_balanced_epp(policy));
-		if (ret)
-			return ret;
-		break;
-	case PLATFORM_PROFILE_PERFORMANCE:
-		ret = amd_pstate_set_epp(policy, AMD_CPPC_EPP_PERFORMANCE);
-		if (ret)
-			return ret;
-		break;
-	default:
-		pr_err("Unknown Platform Profile %d\n", profile);
-		return -EOPNOTSUPP;
-	}
+	if (!policy)
+		return -ENODEV;
+
+	ret = amd_pstate_get_epp_from_platform_profile(policy, profile);
+	if (ret < 0)
+		return ret;
+
+	epp = (u8)ret;
+	ret = amd_pstate_set_epp(policy, epp);
+	if (ret)
+		return ret;
 
 	cpudata->current_profile = profile;
 
@@ -1254,28 +1273,20 @@ void amd_pstate_clear_dynamic_epp(struct cpufreq_policy *policy)
 	kfree(cpudata->profile_name);
 	cpudata->dynamic_epp = false;
 }
-EXPORT_SYMBOL_GPL(amd_pstate_clear_dynamic_epp);
+EXPORT_SYMBOL_FOR_PSTATE_UT(amd_pstate_clear_dynamic_epp);
 
 static int amd_pstate_set_dynamic_epp(struct cpufreq_policy *policy)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
+	u64 prev = READ_ONCE(cpudata->cppc_req_cached);
 	int ret;
 	u8 epp;
 
-	switch (cpudata->current_profile) {
-	case PLATFORM_PROFILE_PERFORMANCE:
-		epp = AMD_CPPC_EPP_PERFORMANCE;
-		break;
-	case PLATFORM_PROFILE_LOW_POWER:
-		epp = AMD_CPPC_EPP_POWERSAVE;
-		break;
-	case PLATFORM_PROFILE_BALANCED:
-		epp = amd_pstate_get_balanced_epp(policy);
-		break;
-	default:
-		pr_err("Unknown Platform Profile %d\n", cpudata->current_profile);
-		return -EOPNOTSUPP;
-	}
+	ret = amd_pstate_get_epp_from_platform_profile(policy, cpudata->current_profile);
+	if (ret < 0)
+		return ret;
+
+	epp = (u8)ret;
 	ret = amd_pstate_set_epp(policy, epp);
 	if (ret)
 		return ret;
@@ -1308,6 +1319,9 @@ static int amd_pstate_set_dynamic_epp(struct cpufreq_policy *policy)
 cleanup:
 	amd_pstate_clear_dynamic_epp(policy);
 
+	epp = FIELD_GET(AMD_CPPC_EPP_PERF_MASK, prev);
+	/* Restore previous EPP if toggling Dynamic EPP failed. */
+	amd_pstate_set_epp(policy, epp);
 	return ret;
 }
 
@@ -1378,7 +1392,7 @@ 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 offset = 0, i;
+	int i, offset = 0;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
@@ -1401,11 +1415,6 @@ ssize_t store_energy_performance_preference(struct cpufreq_policy *policy,
 	bool raw_epp = false;
 	u8 epp;
 
-	if (cpudata->dynamic_epp) {
-		pr_debug("EPP cannot be set when dynamic EPP is enabled\n");
-		return -EBUSY;
-	}
-
 	/*
 	 * if the value matches a number, use that, otherwise see if
 	 * matches an index in the energy_perf_strings array
@@ -1416,6 +1425,25 @@ ssize_t store_energy_performance_preference(struct cpufreq_policy *policy,
 		ret = sysfs_match_string(energy_perf_strings, buf);
 		if (ret < 0 || ret == EPP_INDEX_CUSTOM)
 			return -EINVAL;
+
+		if (ret == EPP_INDEX_DYNAMIC) {
+			if (cpudata->policy == CPUFREQ_POLICY_PERFORMANCE)
+				return -EBUSY;
+			/*
+			 * Dynamic EPP was already enabled for this CPU.
+			 * Nothing to do.
+			 */
+			if (cpudata->dynamic_epp)
+				return count;
+
+			cpudata->current_profile = PLATFORM_PROFILE_BALANCED;
+			ret = amd_pstate_set_dynamic_epp(policy);
+			if (ret)
+				return ret;
+
+			return count;
+		}
+
 		if (ret)
 			epp = epp_values[ret];
 		else
@@ -1427,6 +1455,13 @@ ssize_t store_energy_performance_preference(struct cpufreq_policy *policy,
 		return -EBUSY;
 	}
 
+	/*
+	 * Dynamic EPP was enabled previously!
+	 * Switch back to the static EPP mode.
+	 */
+	if (cpudata->dynamic_epp)
+		amd_pstate_clear_dynamic_epp(policy);
+
 	ret = amd_pstate_set_epp(policy, epp);
 	if (ret)
 		return ret;
@@ -1435,7 +1470,7 @@ ssize_t store_energy_performance_preference(struct cpufreq_policy *policy,
 
 	return count;
 }
-EXPORT_SYMBOL_GPL(store_energy_performance_preference);
+EXPORT_SYMBOL_FOR_PSTATE_UT(store_energy_performance_preference);
 
 ssize_t show_energy_performance_preference(struct cpufreq_policy *policy, char *buf)
 {
@@ -1444,7 +1479,7 @@ ssize_t show_energy_performance_preference(struct cpufreq_policy *policy, char *
 
 	epp = FIELD_GET(AMD_CPPC_EPP_PERF_MASK, cpudata->cppc_req_cached);
 
-	if (cpudata->raw_epp)
+	if (!cpudata->dynamic_epp && cpudata->raw_epp)
 		return sysfs_emit(buf, "%u\n", epp);
 
 	switch (epp) {
@@ -1464,12 +1499,14 @@ ssize_t show_energy_performance_preference(struct cpufreq_policy *policy, char *
 		return -EINVAL;
 	}
 
+	if (cpudata->dynamic_epp)
+		return sysfs_emit(buf, "dynamic(profile:%s)\n", energy_perf_strings[preference]);
+
 	return sysfs_emit(buf, "%s\n", energy_perf_strings[preference]);
 }
-EXPORT_SYMBOL_GPL(show_energy_performance_preference);
+EXPORT_SYMBOL_FOR_PSTATE_UT(show_energy_performance_preference);
 
-static ssize_t store_amd_pstate_floor_freq(struct cpufreq_policy *policy,
-					   const char *buf, size_t count)
+ssize_t store_amd_pstate_floor_freq(struct cpufreq_policy *policy, const char *buf, size_t count)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
 	union perf_cached perf = READ_ONCE(cpudata->perf);
@@ -1492,13 +1529,15 @@ static ssize_t store_amd_pstate_floor_freq(struct cpufreq_policy *policy,
 
 	return ret ?: count;
 }
+EXPORT_SYMBOL_FOR_PSTATE_UT(store_amd_pstate_floor_freq);
 
-static ssize_t show_amd_pstate_floor_freq(struct cpufreq_policy *policy, char *buf)
+ssize_t show_amd_pstate_floor_freq(struct cpufreq_policy *policy, char *buf)
 {
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	return sysfs_emit(buf, "%u\n", cpudata->floor_freq);
 }
+EXPORT_SYMBOL_FOR_PSTATE_UT(show_amd_pstate_floor_freq);
 
 static ssize_t show_amd_pstate_floor_count(struct cpufreq_policy *policy, char *buf)
 {
@@ -1566,7 +1605,7 @@ struct freq_attr **amd_pstate_get_current_attrs(void)
 		return NULL;
 	return current_pstate_driver->attr;
 }
-EXPORT_SYMBOL_GPL(amd_pstate_get_current_attrs);
+EXPORT_SYMBOL_FOR_PSTATE_UT(amd_pstate_get_current_attrs);
 
 static struct freq_attr **get_freq_attrs(void)
 {
@@ -1751,7 +1790,7 @@ int amd_pstate_get_status(void)
 {
 	return cppc_state;
 }
-EXPORT_SYMBOL_GPL(amd_pstate_get_status);
+EXPORT_SYMBOL_FOR_PSTATE_UT(amd_pstate_get_status);
 
 int amd_pstate_update_status(const char *buf, size_t size)
 {
@@ -1771,7 +1810,7 @@ int amd_pstate_update_status(const char *buf, size_t size)
 
 	return 0;
 }
-EXPORT_SYMBOL_GPL(amd_pstate_update_status);
+EXPORT_SYMBOL_FOR_PSTATE_UT(amd_pstate_update_status);
 
 static ssize_t status_show(struct device *dev,
 			   struct device_attribute *attr, char *buf)
@@ -1799,50 +1838,12 @@ static ssize_t prefcore_show(struct device *dev,
 	return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore));
 }
 
-static ssize_t dynamic_epp_show(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	return sysfs_emit(buf, "%s\n", str_enabled_disabled(dynamic_epp));
-}
-
-static ssize_t dynamic_epp_store(struct device *a, struct device_attribute *b,
-				 const char *buf, size_t count)
-{
-	bool enabled;
-	int ret;
-
-	ret = kstrtobool(buf, &enabled);
-	if (ret)
-		return ret;
-
-	guard(mutex)(&amd_pstate_driver_lock);
-
-	if (cppc_state != AMD_PSTATE_ACTIVE) {
-		pr_debug("dynamic_epp can only be toggled in active mode\n");
-		return -EINVAL;
-	}
-
-	/* Nothing to do */
-	if (dynamic_epp == enabled)
-		return count;
-
-	/* reinitialize with desired dynamic EPP value */
-	dynamic_epp = enabled;
-	ret = amd_pstate_change_driver_mode(cppc_state);
-	if (ret)
-		dynamic_epp = false;
-
-	return ret ? ret : count;
-}
-
 static DEVICE_ATTR_RW(status);
 static DEVICE_ATTR_RO(prefcore);
-static DEVICE_ATTR_RW(dynamic_epp);
 
 static struct attribute *pstate_global_attributes[] = {
 	&dev_attr_status.attr,
 	&dev_attr_prefcore.attr,
-	&dev_attr_dynamic_epp.attr,
 	NULL
 };
 
@@ -1876,6 +1877,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	struct amd_cpudata *cpudata;
 	union perf_cached perf;
 	struct device *dev;
+	int default_epp;
 	int ret;
 
 	/*
@@ -1924,6 +1926,14 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 
 	policy->boost_supported = READ_ONCE(cpudata->boost_supported);
 
+	/* Cache the firmware programmed EPP */
+	default_epp = amd_pstate_get_epp(cpudata);
+	if (default_epp < 0) {
+		ret = default_epp;
+		goto free_cpudata1;
+	}
+	FIELD_MODIFY(AMD_CPPC_EPP_PERF_MASK, &cpudata->cppc_req_cached, default_epp);
+
 	/*
 	 * Set the policy to provide a valid fallback value in case
 	 * the default cpufreq governor is neither powersave nor performance.
@@ -1931,7 +1941,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	if (amd_pstate_acpi_pm_profile_server() ||
 	    amd_pstate_acpi_pm_profile_undefined()) {
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
-		cpudata->epp_default_ac = cpudata->epp_default_dc = amd_pstate_get_epp(cpudata);
+		cpudata->epp_default_ac = cpudata->epp_default_dc = default_epp;
 		cpudata->current_profile = PLATFORM_PROFILE_PERFORMANCE;
 	} else {
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
@@ -1940,10 +1950,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 		cpudata->current_profile = PLATFORM_PROFILE_BALANCED;
 	}
 
-	if (dynamic_epp)
-		ret = amd_pstate_set_dynamic_epp(policy);
-	else
-		ret = amd_pstate_set_epp(policy, cpudata->epp_default_dc);
+	ret = amd_pstate_set_epp(policy, cpudata->epp_default_dc);
 	if (ret)
 		goto free_cpudata1;
 
@@ -2015,6 +2022,18 @@ static int amd_pstate_epp_set_policy(struct cpufreq_policy *policy)
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
+	/* Must be a switch between PERFORMANCE and POWERSAVE */
+	if (cpudata->policy != policy->policy) {
+		/*
+		 * Disable dynamic_epp when switching
+		 * out of CPUFREQ_POLICY_POWERSAVE.
+		 */
+		if (cpudata->dynamic_epp) {
+			WARN_ON_ONCE(cpudata->policy != CPUFREQ_POLICY_POWERSAVE);
+			amd_pstate_clear_dynamic_epp(policy);
+		}
+	}
+
 	cpudata->policy = policy->policy;
 
 	ret = amd_pstate_epp_update_limit(policy, true);
@@ -2342,19 +2361,8 @@ static int __init amd_prefcore_param(char *str)
 	return 0;
 }
 
-static int __init amd_dynamic_epp_param(char *str)
-{
-	if (!strcmp(str, "disable"))
-		dynamic_epp = false;
-	if (!strcmp(str, "enable"))
-		dynamic_epp = true;
-
-	return 0;
-}
-
 early_param("amd_pstate", amd_pstate_param);
 early_param("amd_prefcore", amd_prefcore_param);
-early_param("amd_dynamic_epp", amd_dynamic_epp_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");
diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
index 23e8baa05849..9f5a81976eae 100644
--- a/drivers/cpufreq/amd-pstate.h
+++ b/drivers/cpufreq/amd-pstate.h
@@ -11,6 +11,13 @@
 #include <linux/pm_qos.h>
 #include <linux/platform_profile.h>
 
+#if IS_MODULE(CONFIG_X86_AMD_PSTATE_UT)
+#define EXPORT_SYMBOL_FOR_PSTATE_UT(symbol) \
+	EXPORT_SYMBOL_FOR_MODULES(symbol, "amd-pstate-ut")
+#else
+#define EXPORT_SYMBOL_FOR_PSTATE_UT(symbol)
+#endif
+
 /*********************************************************************
  *                        AMD P-state INTERFACE                       *
  *********************************************************************/
@@ -32,6 +39,7 @@
  * @min_limit_perf: Cached value of the performance corresponding to policy->min
  * @max_limit_perf: Cached value of the performance corresponding to policy->max
  * @bios_min_perf: Cached perf value corresponding to the "Requested CPU Min Frequency" BIOS option
+ * @val: Raw 64-bit value for atomic access via READ_ONCE()/WRITE_ONCE()
  */
 union perf_cached {
 	struct {
@@ -89,7 +97,12 @@ struct amd_aperf_mperf {
  * @epp_default_ac: Default EPP value for AC power source
  * @epp_default_dc: Default EPP value for DC power source
  * @dynamic_epp: Whether dynamic EPP is enabled
+ * @raw_epp: Whether the last EPP write was a raw numeric value rather than a
+ *	     named preference
  * @power_nb: Notifier block for power events
+ * @current_profile: Currently selected platform profile option
+ * @ppdev: Device registered with the platform profile handler
+ * @profile_name: Name under which @ppdev is registered
  *
  * The amd_cpudata is key private data for each CPU thread in AMD P-State, and
  * represents all the attributes and goals that AMD P-State requests at runtime.
@@ -153,6 +166,8 @@ ssize_t store_energy_performance_preference(struct cpufreq_policy *policy,
 				    const char *buf, size_t count);
 ssize_t show_energy_performance_preference(struct cpufreq_policy *policy, char *buf);
 void amd_pstate_clear_dynamic_epp(struct cpufreq_policy *policy);
+ssize_t store_amd_pstate_floor_freq(struct cpufreq_policy *policy, const char *buf, size_t count);
+ssize_t show_amd_pstate_floor_freq(struct cpufreq_policy *policy, char *buf);
 
 struct freq_attr;
 
diff --git a/drivers/cpufreq/apple-soc-cpufreq.c b/drivers/cpufreq/apple-soc-cpufreq.c
index 638e5bf72185..7c50ce74f911 100644
--- a/drivers/cpufreq/apple-soc-cpufreq.c
+++ b/drivers/cpufreq/apple-soc-cpufreq.c
@@ -249,21 +249,19 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy)
 		return -ENODEV;
 	}
 
-	ret = dev_pm_opp_of_add_table(cpu_dev);
-	if (ret < 0) {
-		dev_err(cpu_dev, "%s: failed to add OPP table: %d\n", __func__, ret);
-		return ret;
-	}
+	priv = kzalloc_obj(*priv);
+	if (!priv)
+		return -ENOMEM;
 
 	ret = apple_soc_cpufreq_find_cluster(policy, &reg_base, &info);
 	if (ret) {
 		dev_err(cpu_dev, "%s: failed to get cluster info: %d\n", __func__, ret);
-		return ret;
+		goto out_free_priv;
 	}
 
-	ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
-	if (ret) {
-		dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n", __func__, ret);
+	ret = dev_pm_opp_of_cpumask_add_table(policy->cpus);
+	if (ret < 0) {
+		dev_err(cpu_dev, "%s: failed to add OPP table: %d\n", __func__, ret);
 		goto out_iounmap;
 	}
 
@@ -271,24 +269,18 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy)
 	if (ret <= 0) {
 		dev_dbg(cpu_dev, "OPP table is not ready, deferring probe\n");
 		ret = -EPROBE_DEFER;
-		goto out_free_opp;
-	}
-
-	priv = kzalloc_obj(*priv);
-	if (!priv) {
-		ret = -ENOMEM;
-		goto out_free_opp;
+		goto out_free_table;
 	}
 
 	ret = dev_pm_opp_init_cpufreq_table(cpu_dev, &freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
-		goto out_free_priv;
+		goto out_free_table;
 	}
 
 	/* Get OPP levels (p-state indexes) and stash them in driver_data */
 	for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
-		unsigned long rate = freq_table[i].frequency * 1000 + 999;
+		unsigned long rate = freq_table[i].frequency * 1000UL + 999;
 		struct dev_pm_opp *opp = dev_pm_opp_find_freq_floor(cpu_dev, &rate);
 
 		if (IS_ERR(opp)) {
@@ -318,12 +310,12 @@ static int apple_soc_cpufreq_init(struct cpufreq_policy *policy)
 
 out_free_cpufreq_table:
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
-out_free_priv:
-	kfree(priv);
-out_free_opp:
-	dev_pm_opp_remove_all_dynamic(cpu_dev);
+out_free_table:
+	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
 out_iounmap:
 	iounmap(reg_base);
+out_free_priv:
+	kfree(priv);
 	return ret;
 }
 
@@ -332,7 +324,7 @@ static void apple_soc_cpufreq_exit(struct cpufreq_policy *policy)
 	struct apple_cpu_priv *priv = policy->driver_data;
 
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	dev_pm_opp_remove_all_dynamic(priv->cpu_dev);
+	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
 	iounmap(priv->reg_base);
 	kfree(priv);
 }
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index 71450cca8e9f..7d902856ac01 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -584,11 +584,8 @@ static int brcm_avs_prepare_init(struct platform_device *pdev)
 	ret = devm_request_irq(dev, priv->host_irq, irq_handler,
 			       IRQF_TRIGGER_RISING,
 			       BRCM_AVS_HOST_INTR, priv);
-	if (ret && priv->host_irq >= 0) {
-		dev_err(dev, "IRQ request failed: %s (%d) -- %d\n",
-			BRCM_AVS_HOST_INTR, priv->host_irq, ret);
+	if (ret && priv->host_irq >= 0)
 		goto unmap_intr_base;
-	}
 
 	if (brcm_avs_is_firmware_loaded(priv))
 		return 0;
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index ff1204c666b1..284eece9e230 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -200,6 +200,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "ti,am62l3", },
 	{ .compatible = "ti,am62p5", },
 
+	{ .compatible = "qcom,ipq5210", },
 	{ .compatible = "qcom,ipq5332", },
 	{ .compatible = "qcom,ipq5424", },
 	{ .compatible = "qcom,ipq6018", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index b898b6544069..0d0df986fa3d 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -2225,14 +2225,17 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
  * @policy: cpufreq policy object of the target CPU.
  * @min_perf: Minimum (required) performance level (units of @capacity).
  * @target_perf: Target (desired) performance level (units of @capacity).
+ * @max_perf: Maximum (allowed) performance level (units of @capacity).
  * @capacity: Capacity of the target CPU.
  *
- * Carry out a fast performance level switch of @cpu without sleeping.
+ * Carry out a fast performance level adjustment for the CPU represented by
+ * @policy without sleeping.
  *
  * The driver's ->adjust_perf() callback invoked by this function must be
- * suitable for being called from within RCU-sched read-side critical sections
- * and it is expected to select a suitable performance level equal to or above
- * @min_perf and preferably equal to or below @target_perf.
+ * suitable for calling from within RCU-sched read-side critical sections and
+ * it is expected to program the processor to select suitable performance
+ * levels between @min_perf and @max_perf inclusive and preferably close to
+ * @target_perf going forward for the CPU represented by @policy.
  *
  * This function must not be called if policy->fast_switch_enabled is unset.
  *
@@ -2244,9 +2247,10 @@ EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy,
 				 unsigned long min_perf,
 				 unsigned long target_perf,
+				 unsigned long max_perf,
 				 unsigned long capacity)
 {
-	cpufreq_driver->adjust_perf(policy, min_perf, target_perf, capacity);
+	cpufreq_driver->adjust_perf(policy, min_perf, target_perf, max_perf, capacity);
 }
 
 /**
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index e93697d3edfd..731f5721ff1e 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -55,7 +55,6 @@ static unsigned int max_freq;
 static unsigned int transition_latency;
 
 static u32 *imx6_soc_volt;
-static u32 soc_opp_count;
 
 static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
@@ -330,6 +329,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	const struct property *prop;
 	const __be32 *val;
 	u32 nr, i, j;
+	u32 soc_opp_count = 0;
 
 	cpu_dev = get_cpu_device(0);
 	if (!cpu_dev) {
@@ -400,7 +400,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	}
 
 	/* Make imx6_soc_volt array's size same as arm opp number */
-	imx6_soc_volt = devm_kcalloc(cpu_dev, num, sizeof(*imx6_soc_volt),
+	imx6_soc_volt = devm_kcalloc(&pdev->dev, num, sizeof(*imx6_soc_volt),
 				     GFP_KERNEL);
 	if (imx6_soc_volt == NULL) {
 		ret = -ENOMEM;
@@ -485,6 +485,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	return 0;
 
 free_freq_table:
+	imx6_soc_volt = NULL;
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_free_opp:
 	dev_pm_opp_of_remove_table(cpu_dev);
@@ -506,6 +507,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 static void imx6q_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&imx6q_cpufreq_driver);
+	imx6_soc_volt = NULL;
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 	dev_pm_opp_of_remove_table(cpu_dev);
 	regulator_put(arm_reg);
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 6e984c114d96..7ce5981cbae5 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -299,7 +299,6 @@ struct pstate_funcs {
 static struct pstate_funcs pstate_funcs __read_mostly;
 
 static bool hwp_active __ro_after_init;
-static int hwp_mode_bdw __ro_after_init;
 static bool per_cpu_limits __ro_after_init;
 static bool hwp_forced __ro_after_init;
 static bool hwp_boost __read_mostly;
@@ -587,21 +586,14 @@ static void intel_pstate_hybrid_hwp_adjust(struct cpudata *cpu)
 
 	hwp_is_hybrid = true;
 
-	cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_pstate * scaling,
-					   perf_ctl_scaling);
-	cpu->pstate.max_freq = rounddown(cpu->pstate.max_pstate * scaling,
-					 perf_ctl_scaling);
-
 	freq = perf_ctl_max_phys * perf_ctl_scaling;
 	cpu->pstate.max_pstate_physical = intel_pstate_freq_to_hwp(cpu, freq);
 
-	freq = cpu->pstate.min_pstate * perf_ctl_scaling;
-	cpu->pstate.min_freq = freq;
 	/*
 	 * Cast the min P-state value retrieved via pstate_funcs.get_min() to
 	 * the effective range of HWP performance levels.
 	 */
-	cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, freq);
+	cpu->pstate.min_pstate = intel_pstate_freq_to_hwp(cpu, cpu->pstate.min_freq);
 }
 
 static bool turbo_is_disabled(void)
@@ -979,12 +971,10 @@ static int hybrid_get_cost(struct device *dev, unsigned long freq,
 	 * capacity.  Similarly, P-cores start to be populated when E-cores are
 	 * utilized above 60% of the capacity.
 	 */
-	if (hybrid_get_cpu_type(dev->id) == INTEL_CPU_TYPE_ATOM) {
-		if (hybrid_has_l3(dev->id)) /* E-core */
-			*cost += 1;
-	} else { /* P-core */
+	if (hybrid_get_cpu_type(dev->id) == INTEL_CPU_TYPE_CORE) /* P-core */
 		*cost += 2;
-	}
+	else if (hybrid_has_l3(dev->id)) /* E-core */
+		*cost += 1;
 
 	return 0;
 }
@@ -1185,6 +1175,22 @@ static bool hybrid_clear_max_perf_cpu(void)
 	return ret;
 }
 
+static void intel_pstate_update_freq_limits(struct cpudata *cpu)
+{
+	int scaling = cpu->pstate.scaling;
+	unsigned int turbo_freq = cpu->pstate.turbo_pstate * scaling;
+	unsigned int max_freq = cpu->pstate.max_pstate * scaling;
+	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
+
+	if (scaling != perf_ctl_scaling) {
+		turbo_freq = rounddown(turbo_freq, perf_ctl_scaling);
+		max_freq = rounddown(max_freq, perf_ctl_scaling);
+	}
+
+	cpu->pstate.turbo_freq = turbo_freq;
+	cpu->pstate.max_freq = max_freq;
+}
+
 static void __intel_pstate_get_hwp_cap(struct cpudata *cpu)
 {
 	u64 cap;
@@ -1197,20 +1203,8 @@ static void __intel_pstate_get_hwp_cap(struct cpudata *cpu)
 
 static void intel_pstate_get_hwp_cap(struct cpudata *cpu)
 {
-	int scaling = cpu->pstate.scaling;
-
 	__intel_pstate_get_hwp_cap(cpu);
-
-	cpu->pstate.max_freq = cpu->pstate.max_pstate * scaling;
-	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * scaling;
-	if (scaling != cpu->pstate.perf_ctl_scaling) {
-		int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
-
-		cpu->pstate.max_freq = rounddown(cpu->pstate.max_freq,
-						 perf_ctl_scaling);
-		cpu->pstate.turbo_freq = rounddown(cpu->pstate.turbo_freq,
-						   perf_ctl_scaling);
-	}
+	intel_pstate_update_freq_limits(cpu);
 }
 
 static void hybrid_update_capacity(struct cpudata *cpu)
@@ -2299,33 +2293,16 @@ static int hwp_get_cpu_scaling(int cpu)
 	return intel_pstate_cppc_get_scaling(cpu);
 }
 
-static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
-{
-	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
-	cpu->pstate.current_pstate = pstate;
-	/*
-	 * Generally, there is no guarantee that this code will always run on
-	 * the CPU being updated, so force the register update to run on the
-	 * right CPU.
-	 */
-	wrmsrq_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
-		      pstate_funcs.get_val(cpu, pstate));
-}
-
-static void intel_pstate_set_min_pstate(struct cpudata *cpu)
-{
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
-}
-
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
 	int perf_ctl_scaling = pstate_funcs.get_scaling();
 
 	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical(cpu->cpu);
 	cpu->pstate.min_pstate = pstate_funcs.get_min(cpu->cpu);
+	cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
 	cpu->pstate.perf_ctl_scaling = perf_ctl_scaling;
 
-	if (hwp_active && !hwp_mode_bdw) {
+	if (hwp_active) {
 		__intel_pstate_get_hwp_cap(cpu);
 
 		if (pstate_funcs.get_cpu_scaling) {
@@ -2345,19 +2322,13 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo(cpu->cpu);
 	}
 
-	if (cpu->pstate.scaling == perf_ctl_scaling) {
-		cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
-		cpu->pstate.max_freq = cpu->pstate.max_pstate * perf_ctl_scaling;
-		cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * perf_ctl_scaling;
-	}
+	intel_pstate_update_freq_limits(cpu);
 
 	if (pstate_funcs.get_aperf_mperf_shift)
 		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
-
-	intel_pstate_set_min_pstate(cpu);
 }
 
 /*
@@ -2884,8 +2855,22 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 		 cpu->min_perf_ratio);
 }
 
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
+{
+	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
+	cpu->pstate.current_pstate = pstate;
+	/*
+	 * Generally, there is no guarantee that this code will always run on
+	 * the CPU being updated, so force the register update to run on the
+	 * right CPU.
+	 */
+	wrmsrq_on_cpu(cpu->cpu, MSR_IA32_PERF_CTL,
+		      pstate_funcs.get_val(cpu, pstate));
+}
+
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
+	unsigned int freq = policy->min;
 	struct cpudata *cpu;
 
 	if (!policy->cpuinfo.max_freq)
@@ -2901,7 +2886,23 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	intel_pstate_update_perf_limits(cpu, policy->min, policy->max);
 
-	if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+	if (hwp_active) {
+		/*
+		 * The active mode only requires an update util hook if HWP
+		 * boost is used and the policy is not "performance".
+		 */
+		if (hwp_boost && cpu->policy != CPUFREQ_POLICY_PERFORMANCE) {
+			intel_pstate_set_update_util_hook(policy->cpu);
+		} else {
+			intel_pstate_clear_update_util_hook(policy->cpu);
+			if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
+				freq = cpu->max_perf_ratio * cpu->pstate.scaling;
+				if (cpu->pstate.scaling != cpu->pstate.perf_ctl_scaling)
+					freq = rounddown(freq, cpu->pstate.perf_ctl_scaling);
+			}
+		}
+		intel_pstate_hwp_set(policy->cpu);
+	} else if (cpu->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		int pstate = max(cpu->pstate.min_pstate, cpu->max_perf_ratio);
 
 		/*
@@ -2910,25 +2911,17 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 		 */
 		intel_pstate_clear_update_util_hook(policy->cpu);
 		intel_pstate_set_pstate(cpu, pstate);
+		freq = pstate * cpu->pstate.scaling;
 	} else {
 		intel_pstate_set_update_util_hook(policy->cpu);
 	}
-
-	if (hwp_active) {
-		/*
-		 * When hwp_boost was active before and dynamically it
-		 * was turned off, in that case we need to clear the
-		 * update util hook.
-		 */
-		if (!hwp_boost)
-			intel_pstate_clear_update_util_hook(policy->cpu);
-		intel_pstate_hwp_set(policy->cpu);
-	}
 	/*
-	 * policy->cur is never updated with the intel_pstate driver, but it
-	 * is used as a stale frequency value. So, keep it within limits.
+	 * policy->cur is never updated in the intel_pstate driver, but it is
+	 * used as a stale frequency value, so set it to reflect the actual
+	 * requested P-state in the "performance" policy case and to the min
+	 * otherwise.
 	 */
-	policy->cur = policy->min;
+	policy->cur = freq;
 
 	mutex_unlock(&intel_pstate_limits_lock);
 
@@ -2971,6 +2964,11 @@ static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
+static void intel_pstate_set_min_pstate(struct cpudata *cpu)
+{
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+}
+
 static int intel_cpufreq_cpu_offline(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
@@ -3063,6 +3061,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int ret = __intel_pstate_cpu_init(policy);
+	struct cpudata *cpu;
 
 	if (ret)
 		return ret;
@@ -3073,11 +3072,11 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	 */
 	policy->policy = CPUFREQ_POLICY_POWERSAVE;
 
-	if (hwp_active) {
-		struct cpudata *cpu = all_cpu_data[policy->cpu];
-
+	cpu = all_cpu_data[policy->cpu];
+	if (hwp_active)
 		cpu->epp_cached = intel_pstate_get_epp(cpu, 0);
-	}
+	else
+		intel_pstate_set_min_pstate(cpu);
 
 	return 0;
 }
@@ -3243,6 +3242,7 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 static void intel_cpufreq_adjust_perf(struct cpufreq_policy *policy,
 				      unsigned long min_perf,
 				      unsigned long target_perf,
+				      unsigned long max_perf,
 				      unsigned long capacity)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
@@ -3273,7 +3273,13 @@ static void intel_cpufreq_adjust_perf(struct cpufreq_policy *policy,
 	if (min_pstate > cpu->max_perf_ratio)
 		min_pstate = cpu->max_perf_ratio;
 
-	max_pstate = min(cap_pstate, cpu->max_perf_ratio);
+	max_pstate = cap_pstate;
+	if (max_perf < capacity)
+		max_pstate = DIV_ROUND_UP(cap_pstate * max_perf, capacity);
+
+	if (max_pstate > cpu->max_perf_ratio)
+		max_pstate = cpu->max_perf_ratio;
+
 	if (max_pstate < min_pstate)
 		max_pstate = min_pstate;
 
@@ -3301,8 +3307,6 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		return ret;
 
 	policy->cpuinfo.transition_latency = INTEL_CPUFREQ_TRANSITION_LATENCY;
-	/* This reflects the intel_pstate_get_cpu_pstates() setting. */
-	policy->cur = policy->cpuinfo.min_freq;
 
 	req = kzalloc_objs(*req, 2);
 	if (!req) {
@@ -3323,9 +3327,15 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		WRITE_ONCE(cpu->hwp_req_cached, value);
 
 		cpu->epp_cached = intel_pstate_get_epp(cpu, value);
+
+		intel_cpufreq_hwp_update(cpu, cpu->pstate.min_pstate,
+					 cpu->pstate.max_pstate,
+					 cpu->pstate.min_pstate, false);
 	} else {
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
+		intel_pstate_set_min_pstate(cpu);
 	}
+	policy->cur = policy->cpuinfo.min_freq;
 
 	freq = DIV_ROUND_UP(cpu->pstate.turbo_freq * global.min_perf_pct, 100);
 
@@ -3676,14 +3686,14 @@ static inline bool intel_pstate_has_acpi_ppc(void) { return false; }
 static inline void intel_pstate_request_control_from_smm(void) {}
 #endif /* CONFIG_ACPI */
 
-#define INTEL_PSTATE_HWP_BROADWELL	0x01
+#define INTEL_PSTATE_HWP_NOT_HYBRID	0x01
 
 #define X86_MATCH_HWP(vfm, hwp_mode)				\
 	X86_MATCH_VFM_FEATURE(vfm, X86_FEATURE_HWP, hwp_mode)
 
 static const struct x86_cpu_id hwp_support_ids[] __initconst = {
-	X86_MATCH_HWP(INTEL_BROADWELL_X,	INTEL_PSTATE_HWP_BROADWELL),
-	X86_MATCH_HWP(INTEL_BROADWELL_D,	INTEL_PSTATE_HWP_BROADWELL),
+	X86_MATCH_HWP(INTEL_BROADWELL_X,	INTEL_PSTATE_HWP_NOT_HYBRID),
+	X86_MATCH_HWP(INTEL_BROADWELL_D,	INTEL_PSTATE_HWP_NOT_HYBRID),
 	X86_MATCH_HWP(INTEL_ANY,		0),
 	{}
 };
@@ -3808,7 +3818,6 @@ static int __init intel_pstate_init(void)
 
 		if (!no_hwp) {
 			hwp_active = true;
-			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
 			intel_cpufreq.attr = hwp_cpufreq_attrs;
 			intel_cpufreq.flags |= CPUFREQ_NEED_UPDATE_LIMITS;
@@ -3816,7 +3825,8 @@ static int __init intel_pstate_init(void)
 			if (!default_driver)
 				default_driver = &intel_pstate;
 
-			pstate_funcs.get_cpu_scaling = hwp_get_cpu_scaling;
+			if (!id->driver_data)
+				pstate_funcs.get_cpu_scaling = hwp_get_cpu_scaling;
 
 			goto hwp_cpu_matched;
 		}
diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
index e6d28d162442..efa766e98d86 100644
--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
+++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
@@ -200,6 +200,13 @@ static int qcom_cpufreq_kryo_name_version(struct device *cpu_dev,
 	case QCOM_ID_IPQ9574:
 		drv->versions = 1 << (unsigned int)(*speedbin);
 		break;
+	case QCOM_ID_IPQ5200:
+	case QCOM_ID_IPQ5210:
+	case QCOM_ID_QCF2200:
+	case QCOM_ID_QCF3200:
+	case QCOM_ID_QCF3210:
+		drv->versions = (*speedbin == 0xcd) ? BIT(1) : BIT(0);
+		break;
 	case QCOM_ID_IPQ5424:
 	case QCOM_ID_IPQ5404:
 		drv->versions = (*speedbin == 0x3b) ? BIT(1) : BIT(0);
@@ -618,6 +625,7 @@ static const struct of_device_id qcom_cpufreq_match_list[] __initconst __maybe_u
 	{ .compatible = "qcom,msm8909", .data = &match_data_msm8909 },
 	{ .compatible = "qcom,msm8996", .data = &match_data_kryo },
 	{ .compatible = "qcom,qcs404", .data = &match_data_qcs404 },
+	{ .compatible = "qcom,ipq5210", .data = &match_data_kryo },
 	{ .compatible = "qcom,ipq5332", .data = &match_data_kryo },
 	{ .compatible = "qcom,ipq5424", .data = &match_data_kryo },
 	{ .compatible = "qcom,ipq6018", .data = &match_data_ipq6018 },
diff --git a/drivers/cpufreq/rcpufreq_dt.rs b/drivers/cpufreq/rcpufreq_dt.rs
index 10106fa13095..5d27857261da 100644
--- a/drivers/cpufreq/rcpufreq_dt.rs
+++ b/drivers/cpufreq/rcpufreq_dt.rs
@@ -4,12 +4,19 @@
 
 use kernel::{
     clk::Clk,
-    cpu, cpufreq,
+    cpu,
+    cpufreq, //
     cpumask::CpumaskVar,
-    device::{Core, Device},
+    device::{
+        Core,
+        Device, //
+    },
     error::code::*,
     macros::vtable,
-    module_platform_driver, of, opp, platform,
+    module_platform_driver,
+    of,
+    opp,
+    platform, //
     prelude::*,
     str::CString,
     sync::Arc,
diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c
index 81a0780b2ebf..ffe5eda82f0b 100644
--- a/drivers/cpufreq/spear-cpufreq.c
+++ b/drivers/cpufreq/spear-cpufreq.c
@@ -79,9 +79,9 @@ static int spear1340_set_cpu_rate(struct clk *sys_pclk, unsigned long newfreq)
 	int ret = 0;
 
 	sys_clk = clk_get_parent(spear_cpufreq.clk);
-	if (IS_ERR(sys_clk)) {
+	if (!sys_clk) {
 		pr_err("failed to get cpu's parent (sys) clock\n");
-		return PTR_ERR(sys_clk);
+		return -EINVAL;
 	}
 
 	/* Set the rate of the source clock before changing the parent */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index ae9d1ce4f49c..35ce665edfd8 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -379,6 +379,7 @@ struct cpufreq_driver {
 	void		(*adjust_perf)(struct cpufreq_policy *policy,
 				       unsigned long min_perf,
 				       unsigned long target_perf,
+				       unsigned long max_perf,
 				       unsigned long capacity);
 
 	/*
@@ -624,6 +625,7 @@ unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 void cpufreq_driver_adjust_perf(struct cpufreq_policy *policy,
 				unsigned long min_perf,
 				unsigned long target_perf,
+				unsigned long max_perf,
 				unsigned long capacity);
 bool cpufreq_driver_has_adjust_perf(void);
 int cpufreq_driver_target(struct cpufreq_policy *policy,
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index dff4ee04694c..a1782755efcc 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -50,6 +50,7 @@ struct sugov_cpu {
 
 	unsigned long		util;
 	unsigned long		bw_min;
+	unsigned long		bw_max;
 
 	/* The field below is for single-CPU policies only: */
 #ifdef CONFIG_NO_HZ_COMMON
@@ -232,6 +233,7 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
 	util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
 	util = max(util, boost);
 	sg_cpu->bw_min = min;
+	sg_cpu->bw_max = max;
 	sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
 }
 
@@ -314,7 +316,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
  * A CPU running a task which woken up after an IO operation can have its
  * utilization boosted to speed up the completion of those IO operations.
  * The IO boost value is increased each time a task wakes up from IO, in
- * sugov_iowait_apply(), and it's instead decreased by this function,
+ * sugov_iowait_boost(), and it's instead decreased by this function,
  * each time an increase has not been requested (!iowait_boost_pending).
  *
  * A CPU which also appears to have been idle for at least one tick has also
@@ -484,7 +486,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
 		sg_cpu->util = prev_util;
 
 	cpufreq_driver_adjust_perf(sg_policy->policy, sg_cpu->bw_min,
-				   sg_cpu->util, max_cap);
+				   sg_cpu->util, sg_cpu->bw_max, max_cap);
 
 	sg_policy->need_freq_update = false;
 	sg_policy->last_freq_update_time = time;
@@ -590,7 +592,7 @@ static ssize_t rate_limit_us_show(struct gov_attr_set *attr_set, char *buf)
 {
 	struct sugov_tunables *tunables = to_sugov_tunables(attr_set);
 
-	return sprintf(buf, "%u\n", tunables->rate_limit_us);
+	return sysfs_emit(buf, "%u\n", tunables->rate_limit_us);
 }
 
 static ssize_t
diff --git a/rust/kernel/cpufreq.rs b/rust/kernel/cpufreq.rs
index 58ac04c650a1..affa2b9490ef 100644
--- a/rust/kernel/cpufreq.rs
+++ b/rust/kernel/cpufreq.rs
@@ -361,23 +361,28 @@ pub fn new() -> Self {
         }
     }
 
-    /// Adds a new entry to the table.
-    pub fn add(&mut self, freq: Hertz, flags: u32, driver_data: u32) -> Result {
+    /// Adds a raw frequency-table entry.
+    fn push(&mut self, frequency: u32, flags: u32, driver_data: u32) -> Result {
         // Adds the new entry at the end of the vector.
         Ok(self.entries.push(
             bindings::cpufreq_frequency_table {
                 flags,
                 driver_data,
-                frequency: freq.as_khz() as u32,
+                frequency,
             },
             GFP_KERNEL,
         )?)
     }
 
+    /// Adds a new entry to the table.
+    pub fn add(&mut self, freq: Hertz, flags: u32, driver_data: u32) -> Result {
+        self.push(freq.as_khz() as u32, flags, driver_data)
+    }
+
     /// Consumes the [`TableBuilder`] and returns [`TableBox`].
     pub fn to_table(mut self) -> Result<TableBox> {
         // Add last entry to the table.
-        self.add(Hertz(c_ulong::MAX), 0, 0)?;
+        self.push(bindings::CPUFREQ_TABLE_END as u32, 0, 0)?;
 
         TableBox::new(self.entries)
     }
@@ -792,7 +797,13 @@ fn fast_switch(_policy: &mut Policy, _target_freq: u32) -> u32 {
     }
 
     /// Driver's `adjust_perf` callback.
-    fn adjust_perf(_policy: &mut Policy, _min_perf: usize, _target_perf: usize, _capacity: usize) {
+    fn adjust_perf(
+        _policy: &mut Policy,
+        _min_perf: usize,
+        _target_perf: usize,
+        _max_perf: usize,
+        _capacity: usize,
+    ) {
         build_error!(VTABLE_DEFAULT_ERROR)
     }
 
@@ -817,7 +828,9 @@ fn update_limits(_policy: &mut Policy) {
     }
 
     /// Driver's `bios_limit` callback.
-    fn bios_limit(_policy: &mut Policy, _limit: &mut u32) -> Result {
+    ///
+    /// Returns HW/BIOS max frequency limitations for the CPU.
+    fn bios_limit(_policy: &mut Policy) -> Result<u32> {
         build_error!(VTABLE_DEFAULT_ERROR)
     }
 
@@ -1263,12 +1276,13 @@ impl<T: Driver> Registration<T> {
         ptr: *mut bindings::cpufreq_policy,
         min_perf: c_ulong,
         target_perf: c_ulong,
+        max_perf: c_ulong,
         capacity: c_ulong,
     ) {
         // SAFETY: The `ptr` is guaranteed to be valid by the contract with the C code for the
         // lifetime of `policy`.
         let policy = unsafe { Policy::from_raw_mut(ptr) };
-        T::adjust_perf(policy, min_perf, target_perf, capacity);
+        T::adjust_perf(policy, min_perf, target_perf, max_perf, capacity);
     }
 
     /// Driver's `get_intermediate` callback.
@@ -1352,9 +1366,12 @@ impl<T: Driver> Registration<T> {
 
         from_result(|| {
             let mut policy = PolicyCpu::from_cpu(cpu_id)?;
-
+            let val = T::bios_limit(&mut policy)?;
             // SAFETY: `limit` is guaranteed by the C code to be valid.
-            T::bios_limit(&mut policy, &mut (unsafe { *limit })).map(|()| 0)
+            unsafe {
+                *limit = val;
+            }
+            Ok(0)
         })
     }
 
diff --git a/tools/testing/selftests/cpufreq/governor.sh b/tools/testing/selftests/cpufreq/governor.sh
index fe37df79c087..cf59e63f8e14 100755
--- a/tools/testing/selftests/cpufreq/governor.sh
+++ b/tools/testing/selftests/cpufreq/governor.sh
@@ -16,6 +16,12 @@ source cpufreq.sh
 CUR_GOV=
 CUR_FREQ=
 
+# Per-policy backup, keyed by policy so multiple policies can be saved at once
+# (backup_governor/restore_governor also keep CUR_GOV/CUR_FREQ for callers that
+# read them directly).
+declare -A SAVED_GOVERNORS
+declare -A SAVED_FREQS
+
 # Find governor's directory path
 # $1: policy, $2: governor
 find_gov_directory()
@@ -39,11 +45,13 @@ find_current_governor()
 backup_governor()
 {
 	CUR_GOV=$(find_current_governor $1)
+	SAVED_GOVERNORS[$1]=$CUR_GOV
 
 	printf "Governor backup done for $1: $CUR_GOV\n"
 
 	if [ $CUR_GOV == "userspace" ]; then
 		CUR_FREQ=$(find_current_freq $1)
+		SAVED_FREQS[$1]=$CUR_FREQ
 		printf "Governor frequency backup done for $1: $CUR_FREQ\n"
 	fi
 
@@ -53,11 +61,13 @@ backup_governor()
 # $1: policy
 restore_governor()
 {
+	CUR_GOV=${SAVED_GOVERNORS[$1]}
 	__switch_governor $1 $CUR_GOV
 
 	printf "Governor restored for $1 to $CUR_GOV\n"
 
 	if [ $CUR_GOV == "userspace" ]; then
+		CUR_FREQ=${SAVED_FREQS[$1]}
 		set_cpu_frequency $1 $CUR_FREQ
 		printf "Governor frequency restored for $1: $CUR_FREQ\n"
 	fi
@@ -65,6 +75,17 @@ restore_governor()
 	printf "\n"
 }
 
+# Save/restore governors for every policy at once
+save_all_governors()
+{
+	for_each_policy backup_governor
+}
+
+restore_all_governors()
+{
+	for_each_policy restore_governor
+}
+
 # param:
 # $1: policy, $2: governor
 __switch_governor()
@@ -100,11 +121,6 @@ switch_governor()
 # $1: policy, $2: governor
 switch_show_governor()
 {
-	cur_gov=find_current_governor
-	if [ $cur_gov == "userspace" ]; then
-		cur_freq=find_current_freq
-	fi
-
 	# switch governor
 	__switch_governor $1 $2
 
diff --git a/tools/testing/selftests/cpufreq/special-tests.sh b/tools/testing/selftests/cpufreq/special-tests.sh
index 8d40505dc468..e87ed7c8e5e5 100755
--- a/tools/testing/selftests/cpufreq/special-tests.sh
+++ b/tools/testing/selftests/cpufreq/special-tests.sh
@@ -40,7 +40,9 @@ simple_lockdep()
 {
 	printf "** Test: Running ${FUNCNAME[0]} **\n"
 
+	save_all_governors
 	for_each_policy __simple_lockdep
+	restore_all_governors
 }
 
 # Test 2
@@ -56,7 +58,10 @@ concurrent_lockdep()
 {
 	printf "** Test: Running ${FUNCNAME[0]} **\n"
 
+	save_all_governors
 	for_each_policy_concurrent __concurrent_lockdep
+	wait
+	restore_all_governors
 }
 
 # Test 3
@@ -65,20 +70,26 @@ quick_shuffle()
 	# this is called concurrently from governor_race
 	for I in `seq 1000`
 	do
-		echo ondemand | sudo tee $CPUFREQROOT/policy*/scaling_governor &
-		echo userspace | sudo tee $CPUFREQROOT/policy*/scaling_governor &
+		echo ondemand | tee $CPUFREQROOT/policy*/scaling_governor &
+		echo userspace | tee $CPUFREQROOT/policy*/scaling_governor &
 	done
+	wait
 }
 
 governor_race()
 {
 	printf "** Test: Running ${FUNCNAME[0]} **\n"
 
+	save_all_governors
+
 	# run 8 concurrent instances
 	for I in `seq 8`
 	do
 		quick_shuffle &
 	done
+	wait
+
+	restore_all_governors
 }
 
 # Test 4
@@ -112,5 +123,8 @@ hotplug_with_updates_cpu()
 
 hotplug_with_updates()
 {
+	save_all_governors
 	for_each_non_boot_cpu hotplug_with_updates_cpu
+	wait
+	restore_all_governors
 }