12 files changed, 266 insertions, 174 deletions

diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index f0c2d3876dec..e363ae04aac6 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -58,16 +58,8 @@ static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct private_data *priv = policy->driver_data;
 	unsigned long freq = policy->freq_table[index].frequency;
-	int ret;
-
-	ret = dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000);
 
-	if (!ret) {
-		arch_set_freq_scale(policy->related_cpus, freq,
-				    policy->cpuinfo.max_freq);
-	}
-
-	return ret;
+	return dev_pm_opp_set_rate(priv->cpu_dev, freq * 1000);
 }
 
 /*
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 02ab56b2a0d8..db00693a586a 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -61,6 +61,12 @@ static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 
+static DEFINE_STATIC_KEY_FALSE(cpufreq_freq_invariance);
+bool cpufreq_supports_freq_invariance(void)
+{
+	return static_branch_likely(&cpufreq_freq_invariance);
+}
+
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -154,8 +160,9 @@ u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy)
 }
 EXPORT_SYMBOL_GPL(get_cpu_idle_time);
 
-__weak void arch_set_freq_scale(struct cpumask *cpus, unsigned long cur_freq,
-		unsigned long max_freq)
+__weak void arch_set_freq_scale(const struct cpumask *cpus,
+				unsigned long cur_freq,
+				unsigned long max_freq)
 {
 }
 EXPORT_SYMBOL_GPL(arch_set_freq_scale);
@@ -446,6 +453,10 @@ void cpufreq_freq_transition_end(struct cpufreq_policy *policy,
 
 	cpufreq_notify_post_transition(policy, freqs, transition_failed);
 
+	arch_set_freq_scale(policy->related_cpus,
+			    policy->cur,
+			    policy->cpuinfo.max_freq);
+
 	policy->transition_ongoing = false;
 	policy->transition_task = NULL;
 
@@ -703,8 +714,7 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 	freq = arch_freq_get_on_cpu(policy->cpu);
 	if (freq)
 		ret = sprintf(buf, "%u\n", freq);
-	else if (cpufreq_driver && cpufreq_driver->setpolicy &&
-			cpufreq_driver->get)
+	else if (cpufreq_driver->setpolicy && cpufreq_driver->get)
 		ret = sprintf(buf, "%u\n", cpufreq_driver->get(policy->cpu));
 	else
 		ret = sprintf(buf, "%u\n", policy->cur);
@@ -2057,9 +2067,26 @@ EXPORT_SYMBOL(cpufreq_unregister_notifier);
 unsigned int cpufreq_driver_fast_switch(struct cpufreq_policy *policy,
 					unsigned int target_freq)
 {
+	unsigned int freq;
+	int cpu;
+
 	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	freq = cpufreq_driver->fast_switch(policy, target_freq);
+
+	if (!freq)
+		return 0;
 
-	return cpufreq_driver->fast_switch(policy, target_freq);
+	policy->cur = freq;
+	arch_set_freq_scale(policy->related_cpus, freq,
+			    policy->cpuinfo.max_freq);
+	cpufreq_stats_record_transition(policy, freq);
+
+	if (trace_cpu_frequency_enabled()) {
+		for_each_cpu(cpu, policy->cpus)
+			trace_cpu_frequency(freq, cpu);
+	}
+
+	return freq;
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_fast_switch);
 
@@ -2711,6 +2738,15 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	/*
+	 * Mark support for the scheduler's frequency invariance engine for
+	 * drivers that implement target(), target_index() or fast_switch().
+	 */
+	if (!cpufreq_driver->setpolicy) {
+		static_branch_enable_cpuslocked(&cpufreq_freq_invariance);
+		pr_debug("supports frequency invariance");
+	}
+
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
@@ -2780,6 +2816,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	cpus_read_lock();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
+	static_branch_disable_cpuslocked(&cpufreq_freq_invariance);
 	cpuhp_remove_state_nocalls_cpuslocked(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 94d959a8e954..8e7d64f34041 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -19,64 +19,88 @@ struct cpufreq_stats {
 	unsigned int state_num;
 	unsigned int last_index;
 	u64 *time_in_state;
-	spinlock_t lock;
 	unsigned int *freq_table;
 	unsigned int *trans_table;
+
+	/* Deferred reset */
+	unsigned int reset_pending;
+	unsigned long long reset_time;
 };
 
-static void cpufreq_stats_update(struct cpufreq_stats *stats)
+static void cpufreq_stats_update(struct cpufreq_stats *stats,
+				 unsigned long long time)
 {
 	unsigned long long cur_time = get_jiffies_64();
 
-	stats->time_in_state[stats->last_index] += cur_time - stats->last_time;
+	stats->time_in_state[stats->last_index] += cur_time - time;
 	stats->last_time = cur_time;
 }
 
-static void cpufreq_stats_clear_table(struct cpufreq_stats *stats)
+static void cpufreq_stats_reset_table(struct cpufreq_stats *stats)
 {
 	unsigned int count = stats->max_state;
 
-	spin_lock(&stats->lock);
 	memset(stats->time_in_state, 0, count * sizeof(u64));
 	memset(stats->trans_table, 0, count * count * sizeof(int));
 	stats->last_time = get_jiffies_64();
 	stats->total_trans = 0;
-	spin_unlock(&stats->lock);
+
+	/* Adjust for the time elapsed since reset was requested */
+	WRITE_ONCE(stats->reset_pending, 0);
+	cpufreq_stats_update(stats, READ_ONCE(stats->reset_time));
 }
 
 static ssize_t show_total_trans(struct cpufreq_policy *policy, char *buf)
 {
-	return sprintf(buf, "%d\n", policy->stats->total_trans);
+	struct cpufreq_stats *stats = policy->stats;
+
+	if (READ_ONCE(stats->reset_pending))
+		return sprintf(buf, "%d\n", 0);
+	else
+		return sprintf(buf, "%d\n", stats->total_trans);
 }
 cpufreq_freq_attr_ro(total_trans);
 
 static ssize_t show_time_in_state(struct cpufreq_policy *policy, char *buf)
 {
 	struct cpufreq_stats *stats = policy->stats;
+	bool pending = READ_ONCE(stats->reset_pending);
+	unsigned long long time;
 	ssize_t len = 0;
 	int i;
 
-	if (policy->fast_switch_enabled)
-		return 0;
-
-	spin_lock(&stats->lock);
-	cpufreq_stats_update(stats);
-	spin_unlock(&stats->lock);
-
 	for (i = 0; i < stats->state_num; i++) {
+		if (pending) {
+			if (i == stats->last_index)
+				time = get_jiffies_64() - READ_ONCE(stats->reset_time);
+			else
+				time = 0;
+		} else {
+			time = stats->time_in_state[i];
+			if (i == stats->last_index)
+				time += get_jiffies_64() - stats->last_time;
+		}
+
 		len += sprintf(buf + len, "%u %llu\n", stats->freq_table[i],
-			(unsigned long long)
-			jiffies_64_to_clock_t(stats->time_in_state[i]));
+			       jiffies_64_to_clock_t(time));
 	}
 	return len;
 }
 cpufreq_freq_attr_ro(time_in_state);
 
+/* We don't care what is written to the attribute */
 static ssize_t store_reset(struct cpufreq_policy *policy, const char *buf,
 			   size_t count)
 {
-	/* We don't care what is written to the attribute. */
-	cpufreq_stats_clear_table(policy->stats);
+	struct cpufreq_stats *stats = policy->stats;
+
+	/*
+	 * Defer resetting of stats to cpufreq_stats_record_transition() to
+	 * avoid races.
+	 */
+	WRITE_ONCE(stats->reset_time, get_jiffies_64());
+	WRITE_ONCE(stats->reset_pending, 1);
+
 	return count;
 }
 cpufreq_freq_attr_wo(reset);
@@ -84,11 +108,9 @@ cpufreq_freq_attr_wo(reset);
 static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 {
 	struct cpufreq_stats *stats = policy->stats;
+	bool pending = READ_ONCE(stats->reset_pending);
 	ssize_t len = 0;
-	int i, j;
-
-	if (policy->fast_switch_enabled)
-		return 0;
+	int i, j, count;
 
 	len += scnprintf(buf + len, PAGE_SIZE - len, "   From  :    To\n");
 	len += scnprintf(buf + len, PAGE_SIZE - len, "         : ");
@@ -113,8 +135,13 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 		for (j = 0; j < stats->state_num; j++) {
 			if (len >= PAGE_SIZE)
 				break;
-			len += scnprintf(buf + len, PAGE_SIZE - len, "%9u ",
-					stats->trans_table[i*stats->max_state+j]);
+
+			if (pending)
+				count = 0;
+			else
+				count = stats->trans_table[i * stats->max_state + j];
+
+			len += scnprintf(buf + len, PAGE_SIZE - len, "%9u ", count);
 		}
 		if (len >= PAGE_SIZE)
 			break;
@@ -208,7 +235,6 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stats->state_num = i;
 	stats->last_time = get_jiffies_64();
 	stats->last_index = freq_table_get_index(stats, policy->cur);
-	spin_lock_init(&stats->lock);
 
 	policy->stats = stats;
 	ret = sysfs_create_group(&policy->kobj, &stats_attr_group);
@@ -228,23 +254,22 @@ void cpufreq_stats_record_transition(struct cpufreq_policy *policy,
 	struct cpufreq_stats *stats = policy->stats;
 	int old_index, new_index;
 
-	if (!stats) {
-		pr_debug("%s: No stats found\n", __func__);
+	if (unlikely(!stats))
 		return;
-	}
+
+	if (unlikely(READ_ONCE(stats->reset_pending)))
+		cpufreq_stats_reset_table(stats);
 
 	old_index = stats->last_index;
 	new_index = freq_table_get_index(stats, new_freq);
 
 	/* We can't do stats->time_in_state[-1]= .. */
-	if (old_index == -1 || new_index == -1 || old_index == new_index)
+	if (unlikely(old_index == -1 || new_index == -1 || old_index == new_index))
 		return;
 
-	spin_lock(&stats->lock);
-	cpufreq_stats_update(stats);
+	cpufreq_stats_update(stats, stats->last_time);
 
 	stats->last_index = new_index;
 	stats->trans_table[old_index * stats->max_state + new_index]++;
 	stats->total_trans++;
-	spin_unlock(&stats->lock);
 }
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index e0220a6fbc69..9a515c460a00 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -219,14 +219,13 @@ struct global_params {
  * @epp_policy:		Last saved policy used to set EPP/EPB
  * @epp_default:	Power on default HWP energy performance
  *			preference/bias
- * @epp_saved:		Saved EPP/EPB during system suspend or CPU offline
- *			operation
  * @epp_cached		Cached HWP energy-performance preference value
  * @hwp_req_cached:	Cached value of the last HWP Request MSR
  * @hwp_cap_cached:	Cached value of the last HWP Capabilities MSR
  * @last_io_update:	Last time when IO wake flag was set
  * @sched_flags:	Store scheduler flags for possible cross CPU update
  * @hwp_boost_min:	Last HWP boosted min performance
+ * @suspended:		Whether or not the driver has been suspended.
  *
  * This structure stores per CPU instance data for all CPUs.
  */
@@ -258,13 +257,13 @@ struct cpudata {
 	s16 epp_powersave;
 	s16 epp_policy;
 	s16 epp_default;
-	s16 epp_saved;
 	s16 epp_cached;
 	u64 hwp_req_cached;
 	u64 hwp_cap_cached;
 	u64 last_io_update;
 	unsigned int sched_flags;
 	u32 hwp_boost_min;
+	bool suspended;
 };
 
 static struct cpudata **all_cpu_data;
@@ -644,6 +643,8 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data, int *raw
 
 static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp)
 {
+	int ret;
+
 	/*
 	 * Use the cached HWP Request MSR value, because in the active mode the
 	 * register itself may be updated by intel_pstate_hwp_boost_up() or
@@ -659,7 +660,11 @@ static int intel_pstate_set_epp(struct cpudata *cpu, u32 epp)
 	 * function, so it cannot run in parallel with the update below.
 	 */
 	WRITE_ONCE(cpu->hwp_req_cached, value);
-	return wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+	ret = wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
+	if (!ret)
+		cpu->epp_cached = epp;
+
+	return ret;
 }
 
 static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
@@ -678,6 +683,14 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 		else if (epp == -EINVAL)
 			epp = epp_values[pref_index - 1];
 
+		/*
+		 * To avoid confusion, refuse to set EPP to any values different
+		 * from 0 (performance) if the current policy is "performance",
+		 * because those values would be overridden.
+		 */
+		if (epp > 0 && cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE)
+			return -EBUSY;
+
 		ret = intel_pstate_set_epp(cpu_data, epp);
 	} else {
 		if (epp == -EINVAL)
@@ -762,10 +775,8 @@ static ssize_t store_energy_performance_preference(
 			cpufreq_stop_governor(policy);
 			ret = intel_pstate_set_epp(cpu, epp);
 			err = cpufreq_start_governor(policy);
-			if (!ret) {
-				cpu->epp_cached = epp;
+			if (!ret)
 				ret = err;
-			}
 		}
 	}
 
@@ -825,7 +836,7 @@ static void intel_pstate_get_hwp_max(unsigned int cpu, int *phy_max,
 
 	rdmsrl_on_cpu(cpu, MSR_HWP_CAPABILITIES, &cap);
 	WRITE_ONCE(all_cpu_data[cpu]->hwp_cap_cached, cap);
-	if (global.no_turbo)
+	if (global.no_turbo || global.turbo_disabled)
 		*current_max = HWP_GUARANTEED_PERF(cap);
 	else
 		*current_max = HWP_HIGHEST_PERF(cap);
@@ -859,12 +870,6 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 
 	cpu_data->epp_policy = cpu_data->policy;
 
-	if (cpu_data->epp_saved >= 0) {
-		epp = cpu_data->epp_saved;
-		cpu_data->epp_saved = -EINVAL;
-		goto update_epp;
-	}
-
 	if (cpu_data->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		epp = intel_pstate_get_epp(cpu_data, value);
 		cpu_data->epp_powersave = epp;
@@ -891,7 +896,6 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 
 		epp = cpu_data->epp_powersave;
 	}
-update_epp:
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		value &= ~GENMASK_ULL(31, 24);
 		value |= (u64)epp << 24;
@@ -903,14 +907,24 @@ skip_epp:
 	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
 }
 
-static void intel_pstate_hwp_force_min_perf(int cpu)
+static void intel_pstate_hwp_offline(struct cpudata *cpu)
 {
-	u64 value;
+	u64 value = READ_ONCE(cpu->hwp_req_cached);
 	int min_perf;
 
-	value = all_cpu_data[cpu]->hwp_req_cached;
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
+		/*
+		 * In case the EPP has been set to "performance" by the
+		 * active mode "performance" scaling algorithm, replace that
+		 * temporary value with the cached EPP one.
+		 */
+		value &= ~GENMASK_ULL(31, 24);
+		value |= HWP_ENERGY_PERF_PREFERENCE(cpu->epp_cached);
+		WRITE_ONCE(cpu->hwp_req_cached, value);
+	}
+
 	value &= ~GENMASK_ULL(31, 0);
-	min_perf = HWP_LOWEST_PERF(all_cpu_data[cpu]->hwp_cap_cached);
+	min_perf = HWP_LOWEST_PERF(cpu->hwp_cap_cached);
 
 	/* Set hwp_max = hwp_min */
 	value |= HWP_MAX_PERF(min_perf);
@@ -920,19 +934,7 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
 
-	wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value);
-}
-
-static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy)
-{
-	struct cpudata *cpu_data = all_cpu_data[policy->cpu];
-
-	if (!hwp_active)
-		return 0;
-
-	cpu_data->epp_saved = intel_pstate_get_epp(cpu_data, 0);
-
-	return 0;
+	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, value);
 }
 
 #define POWER_CTL_EE_ENABLE	1
@@ -959,8 +961,28 @@ static void set_power_ctl_ee_state(bool input)
 
 static void intel_pstate_hwp_enable(struct cpudata *cpudata);
 
+static void intel_pstate_hwp_reenable(struct cpudata *cpu)
+{
+	intel_pstate_hwp_enable(cpu);
+	wrmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, READ_ONCE(cpu->hwp_req_cached));
+}
+
+static int intel_pstate_suspend(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d suspending\n", cpu->cpu);
+
+	cpu->suspended = true;
+
+	return 0;
+}
+
 static int intel_pstate_resume(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d resuming\n", cpu->cpu);
 
 	/* Only restore if the system default is changed */
 	if (power_ctl_ee_state == POWER_CTL_EE_ENABLE)
@@ -968,18 +990,16 @@ static int intel_pstate_resume(struct cpufreq_policy *policy)
 	else if (power_ctl_ee_state == POWER_CTL_EE_DISABLE)
 		set_power_ctl_ee_state(false);
 
-	if (!hwp_active)
-		return 0;
-
-	mutex_lock(&intel_pstate_limits_lock);
+	if (cpu->suspended && hwp_active) {
+		mutex_lock(&intel_pstate_limits_lock);
 
-	if (policy->cpu == 0)
-		intel_pstate_hwp_enable(all_cpu_data[policy->cpu]);
+		/* Re-enable HWP, because "online" has not done that. */
+		intel_pstate_hwp_reenable(cpu);
 
-	all_cpu_data[policy->cpu]->epp_policy = 0;
-	intel_pstate_hwp_set(policy->cpu);
+		mutex_unlock(&intel_pstate_limits_lock);
+	}
 
-	mutex_unlock(&intel_pstate_limits_lock);
+	cpu->suspended = false;
 
 	return 0;
 }
@@ -1428,7 +1448,6 @@ static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
-	cpudata->epp_policy = 0;
 	if (cpudata->epp_default == -EINVAL)
 		cpudata->epp_default = intel_pstate_get_epp(cpudata, 0);
 }
@@ -2097,25 +2116,31 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 		all_cpu_data[cpunum] = cpu;
 
-		cpu->epp_default = -EINVAL;
-		cpu->epp_powersave = -EINVAL;
-		cpu->epp_saved = -EINVAL;
-	}
+		cpu->cpu = cpunum;
 
-	cpu = all_cpu_data[cpunum];
+		cpu->epp_default = -EINVAL;
 
-	cpu->cpu = cpunum;
+		if (hwp_active) {
+			const struct x86_cpu_id *id;
 
-	if (hwp_active) {
-		const struct x86_cpu_id *id;
+			intel_pstate_hwp_enable(cpu);
 
-		intel_pstate_hwp_enable(cpu);
-
-		id = x86_match_cpu(intel_pstate_hwp_boost_ids);
-		if (id && intel_pstate_acpi_pm_profile_server())
-			hwp_boost = true;
+			id = x86_match_cpu(intel_pstate_hwp_boost_ids);
+			if (id && intel_pstate_acpi_pm_profile_server())
+				hwp_boost = true;
+		}
+	} else if (hwp_active) {
+		/*
+		 * Re-enable HWP in case this happens after a resume from ACPI
+		 * S3 if the CPU was offline during the whole system/resume
+		 * cycle.
+		 */
+		intel_pstate_hwp_reenable(cpu);
 	}
 
+	cpu->epp_powersave = -EINVAL;
+	cpu->epp_policy = 0;
+
 	intel_pstate_get_cpu_pstates(cpu);
 
 	pr_debug("controlling: cpu %d\n", cpunum);
@@ -2296,28 +2321,61 @@ static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
-static void intel_cpufreq_stop_cpu(struct cpufreq_policy *policy)
+static int intel_pstate_cpu_offline(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d going offline\n", cpu->cpu);
+
+	if (cpu->suspended)
+		return 0;
+
+	/*
+	 * If the CPU is an SMT thread and it goes offline with the performance
+	 * settings different from the minimum, it will prevent its sibling
+	 * from getting to lower performance levels, so force the minimum
+	 * performance on CPU offline to prevent that from happening.
+	 */
 	if (hwp_active)
-		intel_pstate_hwp_force_min_perf(policy->cpu);
+		intel_pstate_hwp_offline(cpu);
 	else
-		intel_pstate_set_min_pstate(all_cpu_data[policy->cpu]);
+		intel_pstate_set_min_pstate(cpu);
+
+	intel_pstate_exit_perf_limits(policy);
+
+	return 0;
+}
+
+static int intel_pstate_cpu_online(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+
+	pr_debug("CPU %d going online\n", cpu->cpu);
+
+	intel_pstate_init_acpi_perf_limits(policy);
+
+	if (hwp_active) {
+		/*
+		 * Re-enable HWP and clear the "suspended" flag to let "resume"
+		 * know that it need not do that.
+		 */
+		intel_pstate_hwp_reenable(cpu);
+		cpu->suspended = false;
+	}
+
+	return 0;
 }
 
 static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 {
-	pr_debug("CPU %d exiting\n", policy->cpu);
+	pr_debug("CPU %d stopping\n", policy->cpu);
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
-	if (hwp_active)
-		intel_pstate_hwp_save_state(policy);
-
-	intel_cpufreq_stop_cpu(policy);
 }
 
 static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
 {
-	intel_pstate_exit_perf_limits(policy);
+	pr_debug("CPU %d exiting\n", policy->cpu);
 
 	policy->fast_switch_possible = false;
 
@@ -2378,6 +2436,12 @@ 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->epp_cached = intel_pstate_get_epp(cpu, 0);
+	}
+
 	return 0;
 }
 
@@ -2385,11 +2449,13 @@ static struct cpufreq_driver intel_pstate = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
 	.setpolicy	= intel_pstate_set_policy,
-	.suspend	= intel_pstate_hwp_save_state,
+	.suspend	= intel_pstate_suspend,
 	.resume		= intel_pstate_resume,
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
+	.offline	= intel_pstate_cpu_offline,
+	.online		= intel_pstate_cpu_online,
 	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_pstate",
 };
@@ -2585,7 +2651,7 @@ static int intel_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY_HWP;
 		rdmsrl_on_cpu(cpu->cpu, MSR_HWP_REQUEST, &value);
 		WRITE_ONCE(cpu->hwp_req_cached, value);
-		cpu->epp_cached = (value & GENMASK_ULL(31, 24)) >> 24;
+		cpu->epp_cached = intel_pstate_get_epp(cpu, value);
 	} else {
 		turbo_max = cpu->pstate.turbo_pstate;
 		policy->transition_delay_us = INTEL_CPUFREQ_TRANSITION_DELAY;
@@ -2644,7 +2710,10 @@ static struct cpufreq_driver intel_cpufreq = {
 	.fast_switch	= intel_cpufreq_fast_switch,
 	.init		= intel_cpufreq_cpu_init,
 	.exit		= intel_cpufreq_cpu_exit,
-	.stop_cpu	= intel_cpufreq_stop_cpu,
+	.offline	= intel_pstate_cpu_offline,
+	.online		= intel_pstate_cpu_online,
+	.suspend	= intel_pstate_suspend,
+	.resume		= intel_pstate_resume,
 	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_cpufreq",
 };
@@ -2667,9 +2736,6 @@ static void intel_pstate_driver_cleanup(void)
 	}
 	put_online_cpus();
 
-	if (intel_pstate_driver == &intel_pstate)
-		intel_pstate_sysfs_hide_hwp_dynamic_boost();
-
 	intel_pstate_driver = NULL;
 }
 
@@ -2695,14 +2761,6 @@ static int intel_pstate_register_driver(struct cpufreq_driver *driver)
 	return 0;
 }
 
-static int intel_pstate_unregister_driver(void)
-{
-	cpufreq_unregister_driver(intel_pstate_driver);
-	intel_pstate_driver_cleanup();
-
-	return 0;
-}
-
 static ssize_t intel_pstate_show_status(char *buf)
 {
 	if (!intel_pstate_driver)
@@ -2714,20 +2772,24 @@ static ssize_t intel_pstate_show_status(char *buf)
 
 static int intel_pstate_update_status(const char *buf, size_t size)
 {
-	int ret;
+	if (size == 3 && !strncmp(buf, "off", size)) {
+		if (!intel_pstate_driver)
+			return -EINVAL;
+
+		if (hwp_active)
+			return -EBUSY;
 
-	if (size == 3 && !strncmp(buf, "off", size))
-		return intel_pstate_driver ?
-			intel_pstate_unregister_driver() : -EINVAL;
+		cpufreq_unregister_driver(intel_pstate_driver);
+		intel_pstate_driver_cleanup();
+		return 0;
+	}
 
 	if (size == 6 && !strncmp(buf, "active", size)) {
 		if (intel_pstate_driver) {
 			if (intel_pstate_driver == &intel_pstate)
 				return 0;
 
-			ret = intel_pstate_unregister_driver();
-			if (ret)
-				return ret;
+			cpufreq_unregister_driver(intel_pstate_driver);
 		}
 
 		return intel_pstate_register_driver(&intel_pstate);
@@ -2738,9 +2800,8 @@ static int intel_pstate_update_status(const char *buf, size_t size)
 			if (intel_pstate_driver == &intel_cpufreq)
 				return 0;
 
-			ret = intel_pstate_unregister_driver();
-			if (ret)
-				return ret;
+			cpufreq_unregister_driver(intel_pstate_driver);
+			intel_pstate_sysfs_hide_hwp_dynamic_boost();
 		}
 
 		return intel_pstate_register_driver(&intel_cpufreq);
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index bb61677c11c7..ef0a3216a386 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -129,7 +129,7 @@ static unsigned int cpufreq_p4_get_frequency(struct cpuinfo_x86 *c)
 			return speedstep_get_frequency(SPEEDSTEP_CPU_PCORE);
 		case 0x0D: /* Pentium M (Dothan) */
 			p4clockmod_driver.flags |= CPUFREQ_CONST_LOOPS;
-			/* fall through */
+			fallthrough;
 		case 0x09: /* Pentium M (Banias) */
 			return speedstep_get_frequency(SPEEDSTEP_CPU_PM);
 		}
diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c
index 17fbb8cf36a1..9ed5341dc515 100644
--- a/drivers/cpufreq/qcom-cpufreq-hw.c
+++ b/drivers/cpufreq/qcom-cpufreq-hw.c
@@ -91,8 +91,6 @@ static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy,
 	if (icc_scaling_enabled)
 		qcom_cpufreq_set_bw(policy, freq);
 
-	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
 	return 0;
 }
 
@@ -122,16 +120,11 @@ static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 	struct qcom_cpufreq_data *data = policy->driver_data;
 	const struct qcom_cpufreq_soc_data *soc_data = data->soc_data;
 	unsigned int index;
-	unsigned long freq;
 
 	index = policy->cached_resolved_idx;
 	writel_relaxed(index, data->base + soc_data->reg_perf_state);
 
-	freq = policy->freq_table[index].frequency;
-	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
-
-	return freq;
+	return policy->freq_table[index].frequency;
 }
 
 static int qcom_cpufreq_hw_read_lut(struct device *cpu_dev,
diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
index fb42e3390377..6dd1311660b5 100644
--- a/drivers/cpufreq/scmi-cpufreq.c
+++ b/drivers/cpufreq/scmi-cpufreq.c
@@ -48,16 +48,11 @@ static unsigned int scmi_cpufreq_get_rate(unsigned int cpu)
 static int
 scmi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	int ret;
 	struct scmi_data *priv = policy->driver_data;
 	struct scmi_perf_ops *perf_ops = handle->perf_ops;
 	u64 freq = policy->freq_table[index].frequency;
 
-	ret = perf_ops->freq_set(handle, priv->domain_id, freq * 1000, false);
-	if (!ret)
-		arch_set_freq_scale(policy->related_cpus, freq,
-				    policy->cpuinfo.max_freq);
-	return ret;
+	return perf_ops->freq_set(handle, priv->domain_id, freq * 1000, false);
 }
 
 static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy,
@@ -67,11 +62,8 @@ static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	struct scmi_perf_ops *perf_ops = handle->perf_ops;
 
 	if (!perf_ops->freq_set(handle, priv->domain_id,
-				target_freq * 1000, true)) {
-		arch_set_freq_scale(policy->related_cpus, target_freq,
-				    policy->cpuinfo.max_freq);
+				target_freq * 1000, true))
 		return target_freq;
-	}
 
 	return 0;
 }
diff --git a/drivers/cpufreq/scpi-cpufreq.c b/drivers/cpufreq/scpi-cpufreq.c
index b0f5388b8854..43db05b949d9 100644
--- a/drivers/cpufreq/scpi-cpufreq.c
+++ b/drivers/cpufreq/scpi-cpufreq.c
@@ -47,9 +47,8 @@ static unsigned int scpi_cpufreq_get_rate(unsigned int cpu)
 static int
 scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 {
-	unsigned long freq = policy->freq_table[index].frequency;
+	u64 rate = policy->freq_table[index].frequency * 1000;
 	struct scpi_data *priv = policy->driver_data;
-	u64 rate = freq * 1000;
 	int ret;
 
 	ret = clk_set_rate(priv->clk, rate);
@@ -60,9 +59,6 @@ scpi_cpufreq_set_target(struct cpufreq_policy *policy, unsigned int index)
 	if (clk_get_rate(priv->clk) != rate)
 		return -EIO;
 
-	arch_set_freq_scale(policy->related_cpus, freq,
-			    policy->cpuinfo.max_freq);
-
 	return 0;
 }
 
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index 5c4f8f07c5a6..a13a2d1e444e 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -366,7 +366,7 @@ enum speedstep_processor speedstep_detect_processor(void)
 			} else
 				return SPEEDSTEP_CPU_PIII_C;
 		}
-		/* fall through */
+		fallthrough;
 	default:
 		return 0;
 	}
diff --git a/drivers/cpufreq/tegra194-cpufreq.c b/drivers/cpufreq/tegra194-cpufreq.c
index bae527e507e0..e1d931c457a7 100644
--- a/drivers/cpufreq/tegra194-cpufreq.c
+++ b/drivers/cpufreq/tegra194-cpufreq.c
@@ -56,9 +56,11 @@ struct read_counters_work {
 
 static struct workqueue_struct *read_counters_wq;
 
-static enum cluster get_cpu_cluster(u8 cpu)
+static void get_cpu_cluster(void *cluster)
 {
-	return MPIDR_AFFINITY_LEVEL(cpu_logical_map(cpu), 1);
+	u64 mpidr = read_cpuid_mpidr() & MPIDR_HWID_BITMASK;
+
+	*((uint32_t *)cluster) = MPIDR_AFFINITY_LEVEL(mpidr, 1);
 }
 
 /*
@@ -186,8 +188,10 @@ static unsigned int tegra194_get_speed(u32 cpu)
 static int tegra194_cpufreq_init(struct cpufreq_policy *policy)
 {
 	struct tegra194_cpufreq_data *data = cpufreq_get_driver_data();
-	int cl = get_cpu_cluster(policy->cpu);
 	u32 cpu;
+	u32 cl;
+
+	smp_call_function_single(policy->cpu, get_cpu_cluster, &cl, true);
 
 	if (cl >= data->num_clusters)
 		return -EINVAL;
diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
index ab0de27539ad..8f9fdd864391 100644
--- a/drivers/cpufreq/ti-cpufreq.c
+++ b/drivers/cpufreq/ti-cpufreq.c
@@ -86,11 +86,11 @@ static unsigned long dra7_efuse_xlate(struct ti_cpufreq_data *opp_data,
 	case DRA76_EFUSE_HAS_PLUS_MPU_OPP:
 	case DRA76_EFUSE_HAS_ALL_MPU_OPP:
 		calculated_efuse |= DRA76_EFUSE_PLUS_MPU_OPP;
-		/* Fall through */
+		fallthrough;
 	case DRA7_EFUSE_HAS_ALL_MPU_OPP:
 	case DRA7_EFUSE_HAS_HIGH_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_HIGH_MPU_OPP;
-		/* Fall through */
+		fallthrough;
 	case DRA7_EFUSE_HAS_OD_MPU_OPP:
 		calculated_efuse |= DRA7_EFUSE_OD_MPU_OPP;
 	}
diff --git a/drivers/cpufreq/vexpress-spc-cpufreq.c b/drivers/cpufreq/vexpress-spc-cpufreq.c
index 4e8b1dee7c9a..e89b905754d2 100644
--- a/drivers/cpufreq/vexpress-spc-cpufreq.c
+++ b/drivers/cpufreq/vexpress-spc-cpufreq.c
@@ -182,7 +182,6 @@ static int ve_spc_cpufreq_set_target(struct cpufreq_policy *policy,
 {
 	u32 cpu = policy->cpu, cur_cluster, new_cluster, actual_cluster;
 	unsigned int freqs_new;
-	int ret;
 
 	cur_cluster = cpu_to_cluster(cpu);
 	new_cluster = actual_cluster = per_cpu(physical_cluster, cpu);
@@ -197,15 +196,8 @@ static int ve_spc_cpufreq_set_target(struct cpufreq_policy *policy,
 			new_cluster = A15_CLUSTER;
 	}
 
-	ret = ve_spc_cpufreq_set_rate(cpu, actual_cluster, new_cluster,
-				      freqs_new);
-
-	if (!ret) {
-		arch_set_freq_scale(policy->related_cpus, freqs_new,
-				    policy->cpuinfo.max_freq);
-	}
-
-	return ret;
+	return ve_spc_cpufreq_set_rate(cpu, actual_cluster, new_cluster,
+				       freqs_new);
 }
 
 static inline u32 get_table_count(struct cpufreq_frequency_table *table)