Merging upstream version 6.9.2.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

11 files changed, 351 insertions, 102 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index 35efb53d54..94e55c4097 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -302,4 +302,33 @@ config QORIQ_CPUFREQ
 	  which are capable of changing the CPU's frequency dynamically.
 
 endif
+
+config ACPI_CPPC_CPUFREQ
+	tristate "CPUFreq driver based on the ACPI CPPC spec"
+	depends on ACPI_PROCESSOR
+	depends on ARM || ARM64 || RISCV
+	select ACPI_CPPC_LIB
+	help
+	  This adds a CPUFreq driver which uses CPPC methods
+	  as described in the ACPIv5.1 spec. CPPC stands for
+	  Collaborative Processor Performance Controls. It
+	  is based on an abstract continuous scale of CPU
+	  performance values which allows the remote power
+	  processor to flexibly optimize for power and
+	  performance. CPPC relies on power management firmware
+	  support for its operation.
+
+	  If in doubt, say N.
+
+config ACPI_CPPC_CPUFREQ_FIE
+	bool "Frequency Invariance support for CPPC cpufreq driver"
+	depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY
+	depends on ARM || ARM64 || RISCV
+	default y
+	help
+	  This extends frequency invariance support in the CPPC cpufreq driver,
+	  by using CPPC delivered and reference performance counters.
+
+	  If in doubt, say N.
+
 endmenu
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index a0ebad7766..96b404ce82 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -3,32 +3,6 @@
 # ARM CPU Frequency scaling drivers
 #
 
-config ACPI_CPPC_CPUFREQ
-	tristate "CPUFreq driver based on the ACPI CPPC spec"
-	depends on ACPI_PROCESSOR
-	select ACPI_CPPC_LIB
-	help
-	  This adds a CPUFreq driver which uses CPPC methods
-	  as described in the ACPIv5.1 spec. CPPC stands for
-	  Collaborative Processor Performance Controls. It
-	  is based on an abstract continuous scale of CPU
-	  performance values which allows the remote power
-	  processor to flexibly optimize for power and
-	  performance. CPPC relies on power management firmware
-	  support for its operation.
-
-	  If in doubt, say N.
-
-config ACPI_CPPC_CPUFREQ_FIE
-	bool "Frequency Invariance support for CPPC cpufreq driver"
-	depends on ACPI_CPPC_CPUFREQ && GENERIC_ARCH_TOPOLOGY
-	default y
-	help
-	  This extends frequency invariance support in the CPPC cpufreq driver,
-	  by using CPPC delivered and reference performance counters.
-
-	  If in doubt, say N.
-
 config ARM_ALLWINNER_SUN50I_CPUFREQ_NVMEM
 	tristate "Allwinner nvmem based SUN50I CPUFreq driver"
 	depends on ARCH_SUNXI
diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
index 07f3419954..28166df81c 100644
--- a/drivers/cpufreq/amd-pstate.c
+++ b/drivers/cpufreq/amd-pstate.c
@@ -37,6 +37,7 @@
 #include <linux/uaccess.h>
 #include <linux/static_call.h>
 #include <linux/amd-pstate.h>
+#include <linux/topology.h>
 
 #include <acpi/processor.h>
 #include <acpi/cppc_acpi.h>
@@ -49,6 +50,8 @@
 
 #define AMD_PSTATE_TRANSITION_LATENCY	20000
 #define AMD_PSTATE_TRANSITION_DELAY	1000
+#define CPPC_HIGHEST_PERF_PERFORMANCE	196
+#define CPPC_HIGHEST_PERF_DEFAULT	166
 
 /*
  * TODO: We need more time to fine tune processors with shared memory solution
@@ -64,6 +67,7 @@ static struct cpufreq_driver amd_pstate_driver;
 static struct cpufreq_driver amd_pstate_epp_driver;
 static int cppc_state = AMD_PSTATE_UNDEFINED;
 static bool cppc_enabled;
+static bool amd_pstate_prefcore = true;
 
 /*
  * AMD Energy Preference Performance (EPP)
@@ -287,6 +291,21 @@ static inline int amd_pstate_enable(bool enable)
 	return static_call(amd_pstate_enable)(enable);
 }
 
+static u32 amd_pstate_highest_perf_set(struct amd_cpudata *cpudata)
+{
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	/*
+	 * For AMD CPUs with Family ID 19H and Model ID range 0x70 to 0x7f,
+	 * the highest performance level is set to 196.
+	 * https://bugzilla.kernel.org/show_bug.cgi?id=218759
+	 */
+	if (c->x86 == 0x19 && (c->x86_model >= 0x70 && c->x86_model <= 0x7f))
+		return CPPC_HIGHEST_PERF_PERFORMANCE;
+
+	return CPPC_HIGHEST_PERF_DEFAULT;
+}
+
 static int pstate_init_perf(struct amd_cpudata *cpudata)
 {
 	u64 cap1;
@@ -297,13 +316,14 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
-	/*
-	 * TODO: Introduce AMD specific power feature.
-	 *
-	 * CPPC entry doesn't indicate the highest performance in some ASICs.
+	/* For platforms that do not support the preferred core feature, the
+	 * highest_pef may be configured with 166 or 255, to avoid max frequency
+	 * calculated wrongly. we take the AMD_CPPC_HIGHEST_PERF(cap1) value as
+	 * the default max perf.
 	 */
-	highest_perf = amd_get_highest_perf();
-	if (highest_perf > AMD_CPPC_HIGHEST_PERF(cap1))
+	if (cpudata->hw_prefcore)
+		highest_perf = amd_pstate_highest_perf_set(cpudata);
+	else
 		highest_perf = AMD_CPPC_HIGHEST_PERF(cap1);
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -311,6 +331,7 @@ static int pstate_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->nominal_perf, AMD_CPPC_NOMINAL_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf, AMD_CPPC_LOWNONLIN_PERF(cap1));
 	WRITE_ONCE(cpudata->lowest_perf, AMD_CPPC_LOWEST_PERF(cap1));
+	WRITE_ONCE(cpudata->prefcore_ranking, AMD_CPPC_HIGHEST_PERF(cap1));
 	WRITE_ONCE(cpudata->min_limit_perf, AMD_CPPC_LOWEST_PERF(cap1));
 	return 0;
 }
@@ -324,8 +345,9 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	if (ret)
 		return ret;
 
-	highest_perf = amd_get_highest_perf();
-	if (highest_perf > cppc_perf.highest_perf)
+	if (cpudata->hw_prefcore)
+		highest_perf = amd_pstate_highest_perf_set(cpudata);
+	else
 		highest_perf = cppc_perf.highest_perf;
 
 	WRITE_ONCE(cpudata->highest_perf, highest_perf);
@@ -334,6 +356,7 @@ static int cppc_init_perf(struct amd_cpudata *cpudata)
 	WRITE_ONCE(cpudata->lowest_nonlinear_perf,
 		   cppc_perf.lowest_nonlinear_perf);
 	WRITE_ONCE(cpudata->lowest_perf, cppc_perf.lowest_perf);
+	WRITE_ONCE(cpudata->prefcore_ranking, cppc_perf.highest_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, cppc_perf.lowest_perf);
 
 	if (cppc_state == AMD_PSTATE_ACTIVE)
@@ -477,12 +500,19 @@ static int amd_pstate_verify(struct cpufreq_policy_data *policy)
 
 static int amd_pstate_update_min_max_limit(struct cpufreq_policy *policy)
 {
-	u32 max_limit_perf, min_limit_perf;
+	u32 max_limit_perf, min_limit_perf, lowest_perf;
 	struct amd_cpudata *cpudata = policy->driver_data;
 
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	lowest_perf = READ_ONCE(cpudata->lowest_perf);
+	if (min_limit_perf < lowest_perf)
+		min_limit_perf = lowest_perf;
+
+	if (max_limit_perf < min_limit_perf)
+		max_limit_perf = min_limit_perf;
+
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 	WRITE_ONCE(cpudata->max_limit_freq, policy->max);
@@ -706,6 +736,114 @@ static void amd_perf_ctl_reset(unsigned int cpu)
 	wrmsrl_on_cpu(cpu, MSR_AMD_PERF_CTL, 0);
 }
 
+/*
+ * Set amd-pstate preferred core enable can't be done directly from cpufreq callbacks
+ * due to locking, so queue the work for later.
+ */
+static void amd_pstste_sched_prefcore_workfn(struct work_struct *work)
+{
+	sched_set_itmt_support();
+}
+static DECLARE_WORK(sched_prefcore_work, amd_pstste_sched_prefcore_workfn);
+
+/*
+ * Get the highest performance register value.
+ * @cpu: CPU from which to get highest performance.
+ * @highest_perf: Return address.
+ *
+ * Return: 0 for success, -EIO otherwise.
+ */
+static int amd_pstate_get_highest_perf(int cpu, u32 *highest_perf)
+{
+	int ret;
+
+	if (boot_cpu_has(X86_FEATURE_CPPC)) {
+		u64 cap1;
+
+		ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &cap1);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, AMD_CPPC_HIGHEST_PERF(cap1));
+	} else {
+		u64 cppc_highest_perf;
+
+		ret = cppc_get_highest_perf(cpu, &cppc_highest_perf);
+		if (ret)
+			return ret;
+		WRITE_ONCE(*highest_perf, cppc_highest_perf);
+	}
+
+	return (ret);
+}
+
+#define CPPC_MAX_PERF	U8_MAX
+
+static void amd_pstate_init_prefcore(struct amd_cpudata *cpudata)
+{
+	int ret, prio;
+	u32 highest_perf;
+
+	ret = amd_pstate_get_highest_perf(cpudata->cpu, &highest_perf);
+	if (ret)
+		return;
+
+	cpudata->hw_prefcore = true;
+	/* check if CPPC preferred core feature is enabled*/
+	if (highest_perf < CPPC_MAX_PERF)
+		prio = (int)highest_perf;
+	else {
+		pr_debug("AMD CPPC preferred core is unsupported!\n");
+		cpudata->hw_prefcore = false;
+		return;
+	}
+
+	if (!amd_pstate_prefcore)
+		return;
+
+	/*
+	 * The priorities can be set regardless of whether or not
+	 * sched_set_itmt_support(true) has been called and it is valid to
+	 * update them at any time after it has been called.
+	 */
+	sched_set_itmt_core_prio(prio, cpudata->cpu);
+
+	schedule_work(&sched_prefcore_work);
+}
+
+static void amd_pstate_update_limits(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct amd_cpudata *cpudata = policy->driver_data;
+	u32 prev_high = 0, cur_high = 0;
+	int ret;
+	bool highest_perf_changed = false;
+
+	mutex_lock(&amd_pstate_driver_lock);
+	if ((!amd_pstate_prefcore) || (!cpudata->hw_prefcore))
+		goto free_cpufreq_put;
+
+	ret = amd_pstate_get_highest_perf(cpu, &cur_high);
+	if (ret)
+		goto free_cpufreq_put;
+
+	prev_high = READ_ONCE(cpudata->prefcore_ranking);
+	if (prev_high != cur_high) {
+		highest_perf_changed = true;
+		WRITE_ONCE(cpudata->prefcore_ranking, cur_high);
+
+		if (cur_high < CPPC_MAX_PERF)
+			sched_set_itmt_core_prio((int)cur_high, cpu);
+	}
+
+free_cpufreq_put:
+	cpufreq_cpu_put(policy);
+
+	if (!highest_perf_changed)
+		cpufreq_update_policy(cpu);
+
+	mutex_unlock(&amd_pstate_driver_lock);
+}
+
 static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 {
 	int min_freq, max_freq, nominal_freq, lowest_nonlinear_freq, ret;
@@ -727,6 +865,8 @@ static int amd_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpudata->cpu = policy->cpu;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -877,6 +1017,28 @@ static ssize_t show_amd_pstate_highest_perf(struct cpufreq_policy *policy,
 	return sysfs_emit(buf, "%u\n", perf);
 }
 
+static ssize_t show_amd_pstate_prefcore_ranking(struct cpufreq_policy *policy,
+						char *buf)
+{
+	u32 perf;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	perf = READ_ONCE(cpudata->prefcore_ranking);
+
+	return sysfs_emit(buf, "%u\n", perf);
+}
+
+static ssize_t show_amd_pstate_hw_prefcore(struct cpufreq_policy *policy,
+					   char *buf)
+{
+	bool hw_prefcore;
+	struct amd_cpudata *cpudata = policy->driver_data;
+
+	hw_prefcore = READ_ONCE(cpudata->hw_prefcore);
+
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(hw_prefcore));
+}
+
 static ssize_t show_energy_performance_available_preferences(
 				struct cpufreq_policy *policy, char *buf)
 {
@@ -1074,18 +1236,29 @@ static ssize_t status_store(struct device *a, struct device_attribute *b,
 	return ret < 0 ? ret : count;
 }
 
+static ssize_t prefcore_show(struct device *dev,
+			     struct device_attribute *attr, char *buf)
+{
+	return sysfs_emit(buf, "%s\n", str_enabled_disabled(amd_pstate_prefcore));
+}
+
 cpufreq_freq_attr_ro(amd_pstate_max_freq);
 cpufreq_freq_attr_ro(amd_pstate_lowest_nonlinear_freq);
 
 cpufreq_freq_attr_ro(amd_pstate_highest_perf);
+cpufreq_freq_attr_ro(amd_pstate_prefcore_ranking);
+cpufreq_freq_attr_ro(amd_pstate_hw_prefcore);
 cpufreq_freq_attr_rw(energy_performance_preference);
 cpufreq_freq_attr_ro(energy_performance_available_preferences);
 static DEVICE_ATTR_RW(status);
+static DEVICE_ATTR_RO(prefcore);
 
 static struct freq_attr *amd_pstate_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_prefcore_ranking,
+	&amd_pstate_hw_prefcore,
 	NULL,
 };
 
@@ -1093,6 +1266,8 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 	&amd_pstate_max_freq,
 	&amd_pstate_lowest_nonlinear_freq,
 	&amd_pstate_highest_perf,
+	&amd_pstate_prefcore_ranking,
+	&amd_pstate_hw_prefcore,
 	&energy_performance_preference,
 	&energy_performance_available_preferences,
 	NULL,
@@ -1100,6 +1275,7 @@ static struct freq_attr *amd_pstate_epp_attr[] = {
 
 static struct attribute *pstate_global_attributes[] = {
 	&dev_attr_status.attr,
+	&dev_attr_prefcore.attr,
 	NULL
 };
 
@@ -1151,6 +1327,8 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
 	cpudata->cpu = policy->cpu;
 	cpudata->epp_policy = 0;
 
+	amd_pstate_init_prefcore(cpudata);
+
 	ret = amd_pstate_init_perf(cpudata);
 	if (ret)
 		goto free_cpudata1;
@@ -1232,6 +1410,12 @@ static void amd_pstate_epp_update_limit(struct cpufreq_policy *policy)
 	max_limit_perf = div_u64(policy->max * cpudata->highest_perf, cpudata->max_freq);
 	min_limit_perf = div_u64(policy->min * cpudata->highest_perf, cpudata->max_freq);
 
+	if (min_limit_perf < min_perf)
+		min_limit_perf = min_perf;
+
+	if (max_limit_perf < min_limit_perf)
+		max_limit_perf = min_limit_perf;
+
 	WRITE_ONCE(cpudata->max_limit_perf, max_limit_perf);
 	WRITE_ONCE(cpudata->min_limit_perf, min_limit_perf);
 
@@ -1432,6 +1616,7 @@ static struct cpufreq_driver amd_pstate_driver = {
 	.suspend	= amd_pstate_cpu_suspend,
 	.resume		= amd_pstate_cpu_resume,
 	.set_boost	= amd_pstate_set_boost,
+	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate",
 	.attr		= amd_pstate_attr,
 };
@@ -1446,6 +1631,7 @@ static struct cpufreq_driver amd_pstate_epp_driver = {
 	.online		= amd_pstate_epp_cpu_online,
 	.suspend	= amd_pstate_epp_suspend,
 	.resume		= amd_pstate_epp_resume,
+	.update_limits	= amd_pstate_update_limits,
 	.name		= "amd-pstate-epp",
 	.attr		= amd_pstate_epp_attr,
 };
@@ -1567,7 +1753,17 @@ static int __init amd_pstate_param(char *str)
 
 	return amd_pstate_set_driver(mode_idx);
 }
+
+static int __init amd_prefcore_param(char *str)
+{
+	if (!strcmp(str, "disable"))
+		amd_pstate_prefcore = false;
+
+	return 0;
+}
+
 early_param("amd_pstate", amd_pstate_param);
+early_param("amd_prefcore", amd_prefcore_param);
 
 MODULE_AUTHOR("Huang Rui <ray.huang@amd.com>");
 MODULE_DESCRIPTION("AMD Processor P-state Frequency Driver");
diff --git a/drivers/cpufreq/brcmstb-avs-cpufreq.c b/drivers/cpufreq/brcmstb-avs-cpufreq.c
index ea8438550b..1a1857b0a6 100644
--- a/drivers/cpufreq/brcmstb-avs-cpufreq.c
+++ b/drivers/cpufreq/brcmstb-avs-cpufreq.c
@@ -481,12 +481,9 @@ static bool brcm_avs_is_firmware_loaded(struct private_data *priv)
 static unsigned int brcm_avs_cpufreq_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct private_data *priv;
-
 	if (!policy)
 		return 0;
-
-	priv = policy->driver_data;
+	struct private_data *priv = policy->driver_data;
 
 	cpufreq_cpu_put(policy);
 
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 15f1d41920..64420d9cfd 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -741,15 +741,10 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cppc_perf_fb_ctrs fb_ctrs_t0 = {0}, fb_ctrs_t1 = {0};
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data;
+	struct cppc_cpudata *cpu_data = policy->driver_data;
 	u64 delivered_perf;
 	int ret;
 
-	if (!policy)
-		return -ENODEV;
-
-	cpu_data = policy->driver_data;
-
 	cpufreq_cpu_put(policy);
 
 	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
@@ -827,15 +822,10 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data;
+	struct cppc_cpudata *cpu_data = policy->driver_data;
 	u64 desired_perf;
 	int ret;
 
-	if (!policy)
-		return -ENODEV;
-
-	cpu_data = policy->driver_data;
-
 	cpufreq_cpu_put(policy);
 
 	ret = cppc_get_desired_perf(cpu, &desired_perf);
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index bd1e1357ce..b993a49808 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -156,6 +156,7 @@ static const struct of_device_id blocklist[] __initconst = {
 	{ .compatible = "qcom,sc7280", },
 	{ .compatible = "qcom,sc8180x", },
 	{ .compatible = "qcom,sc8280xp", },
+	{ .compatible = "qcom,sdm670", },
 	{ .compatible = "qcom,sdm845", },
 	{ .compatible = "qcom,sdx75", },
 	{ .compatible = "qcom,sm6115", },
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 86f1bc7754..66e10a19d7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -576,17 +576,26 @@ unsigned int cpufreq_policy_transition_delay_us(struct cpufreq_policy *policy)
 
 	latency = policy->cpuinfo.transition_latency / NSEC_PER_USEC;
 	if (latency) {
+		unsigned int max_delay_us = 2 * MSEC_PER_SEC;
+
+		/*
+		 * If the platform already has high transition_latency, use it
+		 * as-is.
+		 */
+		if (latency > max_delay_us)
+			return latency;
+
 		/*
-		 * For platforms that can change the frequency very fast (< 10
+		 * For platforms that can change the frequency very fast (< 2
 		 * us), the above formula gives a decent transition delay. But
 		 * for platforms where transition_latency is in milliseconds, it
 		 * ends up giving unrealistic values.
 		 *
-		 * Cap the default transition delay to 10 ms, which seems to be
+		 * Cap the default transition delay to 2 ms, which seems to be
 		 * a reasonable amount of time after which we should reevaluate
 		 * the frequency.
 		 */
-		return min(latency * LATENCY_MULTIPLIER, (unsigned int)10000);
+		return min(latency * LATENCY_MULTIPLIER, max_delay_us);
 	}
 
 	return LATENCY_MULTIPLIER;
@@ -1670,13 +1679,10 @@ static void __cpufreq_offline(unsigned int cpu, struct cpufreq_policy *policy)
 	 */
 	if (cpufreq_driver->offline) {
 		cpufreq_driver->offline(policy);
-		return;
-	}
-
-	if (cpufreq_driver->exit)
+	} else if (cpufreq_driver->exit) {
 		cpufreq_driver->exit(policy);
-
-	policy->freq_table = NULL;
+		policy->freq_table = NULL;
+	}
 }
 
 static int cpufreq_offline(unsigned int cpu)
@@ -1734,7 +1740,7 @@ static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	}
 
 	/* We did light-weight exit earlier, do full tear down now */
-	if (cpufreq_driver->offline && cpufreq_driver->exit)
+	if (cpufreq_driver->offline)
 		cpufreq_driver->exit(policy);
 
 	up_write(&policy->rwsem);
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index c52d19d675..a7c38b8b3e 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -22,7 +22,6 @@
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(100000)
 #define MICRO_FREQUENCY_UP_THRESHOLD		(95)
-#define MICRO_FREQUENCY_MIN_SAMPLE_RATE		(10000)
 #define MIN_FREQUENCY_UP_THRESHOLD		(1)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
index 33728c242f..c20d3ecc5a 100644
--- a/drivers/cpufreq/imx6q-cpufreq.c
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -14,6 +14,8 @@
 #include <linux/pm_opp.h>
 #include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
 
 #define PU_SOC_VOLTAGE_NORMAL	1250000
 #define PU_SOC_VOLTAGE_HIGH	1275000
@@ -225,8 +227,6 @@ static void imx6x_disable_freq_in_opp(struct device *dev, unsigned long freq)
 
 static int imx6q_opp_check_speed_grading(struct device *dev)
 {
-	struct device_node *np;
-	void __iomem *base;
 	u32 val;
 	int ret;
 
@@ -235,16 +235,11 @@ static int imx6q_opp_check_speed_grading(struct device *dev)
 		if (ret)
 			return ret;
 	} else {
-		np = of_find_compatible_node(NULL, NULL, "fsl,imx6q-ocotp");
-		if (!np)
-			return -ENOENT;
+		struct regmap *ocotp;
 
-		base = of_iomap(np, 0);
-		of_node_put(np);
-		if (!base) {
-			dev_err(dev, "failed to map ocotp\n");
-			return -EFAULT;
-		}
+		ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6q-ocotp");
+		if (IS_ERR(ocotp))
+			return -ENOENT;
 
 		/*
 		 * SPEED_GRADING[1:0] defines the max speed of ARM:
@@ -254,8 +249,7 @@ static int imx6q_opp_check_speed_grading(struct device *dev)
 		 * 2b'00: 792000000Hz;
 		 * We need to set the max speed of ARM according to fuse map.
 		 */
-		val = readl_relaxed(base + OCOTP_CFG3);
-		iounmap(base);
+		regmap_read(ocotp, OCOTP_CFG3, &val);
 	}
 
 	val >>= OCOTP_CFG3_SPEED_SHIFT;
@@ -290,25 +284,16 @@ static int imx6ul_opp_check_speed_grading(struct device *dev)
 		if (ret)
 			return ret;
 	} else {
-		struct device_node *np;
-		void __iomem *base;
-
-		np = of_find_compatible_node(NULL, NULL, "fsl,imx6ul-ocotp");
-		if (!np)
-			np = of_find_compatible_node(NULL, NULL,
-						     "fsl,imx6ull-ocotp");
-		if (!np)
-			return -ENOENT;
+		struct regmap *ocotp;
 
-		base = of_iomap(np, 0);
-		of_node_put(np);
-		if (!base) {
-			dev_err(dev, "failed to map ocotp\n");
-			return -EFAULT;
-		}
+		ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6ul-ocotp");
+		if (IS_ERR(ocotp))
+			ocotp = syscon_regmap_lookup_by_compatible("fsl,imx6ull-ocotp");
+
+		if (IS_ERR(ocotp))
+			return -ENOENT;
 
-		val = readl_relaxed(base + OCOTP_CFG3);
-		iounmap(base);
+		regmap_read(ocotp, OCOTP_CFG3, &val);
 	}
 
 	/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 79619227ea..dbbf299f42 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -25,6 +25,7 @@
 #include <linux/acpi.h>
 #include <linux/vmalloc.h>
 #include <linux/pm_qos.h>
+#include <linux/bitfield.h>
 #include <trace/events/power.h>
 
 #include <asm/cpu.h>
@@ -201,8 +202,6 @@ struct global_params {
  * @prev_aperf:		Last APERF value read from APERF MSR
  * @prev_mperf:		Last MPERF value read from MPERF MSR
  * @prev_tsc:		Last timestamp counter (TSC) value
- * @prev_cummulative_iowait: IO Wait time difference from last and
- *			current sample
  * @sample:		Storage for storing last Sample data
  * @min_perf_ratio:	Minimum capacity in terms of PERF or HWP ratios
  * @max_perf_ratio:	Maximum capacity in terms of PERF or HWP ratios
@@ -241,7 +240,6 @@ struct cpudata {
 	u64	prev_aperf;
 	u64	prev_mperf;
 	u64	prev_tsc;
-	u64	prev_cummulative_iowait;
 	struct sample sample;
 	int32_t	min_perf_ratio;
 	int32_t	max_perf_ratio;
@@ -3407,14 +3405,31 @@ static bool intel_pstate_hwp_is_enabled(void)
 	return !!(value & 0x1);
 }
 
-static const struct x86_cpu_id intel_epp_balance_perf[] = {
+#define POWERSAVE_MASK			GENMASK(7, 0)
+#define BALANCE_POWER_MASK		GENMASK(15, 8)
+#define BALANCE_PERFORMANCE_MASK	GENMASK(23, 16)
+#define PERFORMANCE_MASK		GENMASK(31, 24)
+
+#define HWP_SET_EPP_VALUES(powersave, balance_power, balance_perf, performance) \
+	(FIELD_PREP_CONST(POWERSAVE_MASK, powersave) |\
+	 FIELD_PREP_CONST(BALANCE_POWER_MASK, balance_power) |\
+	 FIELD_PREP_CONST(BALANCE_PERFORMANCE_MASK, balance_perf) |\
+	 FIELD_PREP_CONST(PERFORMANCE_MASK, performance))
+
+#define HWP_SET_DEF_BALANCE_PERF_EPP(balance_perf) \
+	(HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE, HWP_EPP_BALANCE_POWERSAVE,\
+	 balance_perf, HWP_EPP_PERFORMANCE))
+
+static const struct x86_cpu_id intel_epp_default[] = {
 	/*
 	 * Set EPP value as 102, this is the max suggested EPP
 	 * which can result in one core turbo frequency for
 	 * AlderLake Mobile CPUs.
 	 */
-	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, 102),
-	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, 32),
+	X86_MATCH_INTEL_FAM6_MODEL(ALDERLAKE_L, HWP_SET_DEF_BALANCE_PERF_EPP(102)),
+	X86_MATCH_INTEL_FAM6_MODEL(SAPPHIRERAPIDS_X, HWP_SET_DEF_BALANCE_PERF_EPP(32)),
+	X86_MATCH_INTEL_FAM6_MODEL(METEORLAKE_L, HWP_SET_EPP_VALUES(HWP_EPP_POWERSAVE,
+							HWP_EPP_BALANCE_POWERSAVE, 115, 16)),
 	{}
 };
 
@@ -3512,11 +3527,24 @@ hwp_cpu_matched:
 	intel_pstate_sysfs_expose_params();
 
 	if (hwp_active) {
-		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_balance_perf);
+		const struct x86_cpu_id *id = x86_match_cpu(intel_epp_default);
 		const struct x86_cpu_id *hybrid_id = x86_match_cpu(intel_hybrid_scaling_factor);
 
-		if (id)
-			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] = id->driver_data;
+		if (id) {
+			epp_values[EPP_INDEX_POWERSAVE] =
+					FIELD_GET(POWERSAVE_MASK, id->driver_data);
+			epp_values[EPP_INDEX_BALANCE_POWERSAVE] =
+					FIELD_GET(BALANCE_POWER_MASK, id->driver_data);
+			epp_values[EPP_INDEX_BALANCE_PERFORMANCE] =
+					FIELD_GET(BALANCE_PERFORMANCE_MASK, id->driver_data);
+			epp_values[EPP_INDEX_PERFORMANCE] =
+					FIELD_GET(PERFORMANCE_MASK, id->driver_data);
+			pr_debug("Updated EPPs powersave:%x balanced power:%x balanced perf:%x performance:%x\n",
+				 epp_values[EPP_INDEX_POWERSAVE],
+				 epp_values[EPP_INDEX_BALANCE_POWERSAVE],
+				 epp_values[EPP_INDEX_BALANCE_PERFORMANCE],
+				 epp_values[EPP_INDEX_PERFORMANCE]);
+		}
 
 		if (hybrid_id) {
 			hybrid_scaling_factor = hybrid_id->driver_data;
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index 4ee23f4ebf..3b4f6bfb2f 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -30,6 +30,7 @@ struct scmi_data {
 
 static struct scmi_protocol_handle *ph;
 static const struct scmi_perf_proto_ops *perf_ops;
+static struct cpufreq_driver scmi_cpufreq_driver;
 
 static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 {
@@ -144,6 +145,35 @@ scmi_get_cpu_power(struct device *cpu_dev, unsigned long *power,
 	return 0;
 }
 
+static int
+scmi_get_rate_limit(u32 domain, bool has_fast_switch)
+{
+	int ret, rate_limit;
+
+	if (has_fast_switch) {
+		/*
+		 * Fast channels are used whenever available,
+		 * so use their rate_limit value if populated.
+		 */
+		ret = perf_ops->fast_switch_rate_limit(ph, domain,
+						       &rate_limit);
+		if (!ret && rate_limit)
+			return rate_limit;
+	}
+
+	ret = perf_ops->rate_limit_get(ph, domain, &rate_limit);
+	if (ret)
+		return 0;
+
+	return rate_limit;
+}
+
+static struct freq_attr *scmi_cpufreq_hw_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+	NULL,
+};
+
 static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret, nr_opp, domain;
@@ -250,6 +280,20 @@ static int scmi_cpufreq_init(struct cpufreq_policy *policy)
 	policy->fast_switch_possible =
 		perf_ops->fast_switch_possible(ph, domain);
 
+	policy->transition_delay_us =
+		scmi_get_rate_limit(domain, policy->fast_switch_possible);
+
+	if (policy_has_boost_freq(policy)) {
+		ret = cpufreq_enable_boost_support();
+		if (ret) {
+			dev_warn(cpu_dev, "failed to enable boost: %d\n", ret);
+			goto out_free_opp;
+		} else {
+			scmi_cpufreq_hw_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+			scmi_cpufreq_driver.boost_enabled = true;
+		}
+	}
+
 	return 0;
 
 out_free_opp:
@@ -308,7 +352,7 @@ static struct cpufreq_driver scmi_cpufreq_driver = {
 		  CPUFREQ_NEED_INITIAL_FREQ_CHECK |
 		  CPUFREQ_IS_COOLING_DEV,
 	.verify	= cpufreq_generic_frequency_table_verify,
-	.attr	= cpufreq_generic_attr,
+	.attr	= scmi_cpufreq_hw_attr,
 	.target_index	= scmi_cpufreq_set_target,
 	.fast_switch	= scmi_cpufreq_fast_switch,
 	.get	= scmi_cpufreq_get_rate,