Merge branch 'cpufreq/cppc-fie' into cpufreq/arm/linux-next

8 files changed, 382 insertions, 136 deletions

diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index d1bbc16fba4b..7e7450453714 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -646,7 +646,11 @@ static u64 get_max_boost_ratio(unsigned int cpu)
 		return 0;
 	}
 
-	highest_perf = perf_caps.highest_perf;
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		highest_perf = amd_get_highest_perf();
+	else
+		highest_perf = perf_caps.highest_perf;
+
 	nominal_perf = perf_caps.nominal_perf;
 
 	if (!highest_perf || !nominal_perf) {
diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index 3848b4c222e1..d4c27022b9c9 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -74,13 +74,12 @@ struct cppc_freq_invariance {
 
 static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
 static struct kthread_worker *kworker_fie;
-static bool fie_disabled;
 
 static struct cpufreq_driver cppc_cpufreq_driver;
 static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu);
 static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t1);
+				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
+				 struct cppc_perf_fb_ctrs *fb_ctrs_t1);
 
 /**
  * cppc_scale_freq_workfn - CPPC arch_freq_scale updater for frequency invariance
@@ -115,13 +114,15 @@ static void cppc_scale_freq_workfn(struct kthread_work *work)
 		return;
 	}
 
+	perf = cppc_perf_from_fbctrs(cpu_data, &cppc_fi->prev_perf_fb_ctrs,
+				     &fb_ctrs);
 	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
-	perf = cppc_perf_from_fbctrs(cpu_data, cppc_fi->prev_perf_fb_ctrs,
-				     fb_ctrs);
 
 	perf <<= SCHED_CAPACITY_SHIFT;
 	local_freq_scale = div64_u64(perf, cpu_data->perf_caps.highest_perf);
-	if (WARN_ON(local_freq_scale > 1024))
+
+	/* This can happen due to counter's overflow */
+	if (unlikely(local_freq_scale > 1024))
 		local_freq_scale = 1024;
 
 	per_cpu(arch_freq_scale, cppc_fi->cpu) = local_freq_scale;
@@ -151,35 +152,63 @@ static struct scale_freq_data cppc_sftd = {
 	.set_freq_scale = cppc_scale_freq_tick,
 };
 
-static void cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
-					     struct cppc_cpudata *cpu_data)
+static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy)
 {
-	struct cppc_perf_fb_ctrs fb_ctrs = {0};
 	struct cppc_freq_invariance *cppc_fi;
-	int i, ret;
+	int cpu, ret;
 
 	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
 		return;
 
-	if (fie_disabled)
-		return;
-
-	for_each_cpu(i, policy->cpus) {
-		cppc_fi = &per_cpu(cppc_freq_inv, i);
-		cppc_fi->cpu = i;
-		cppc_fi->cpu_data = cpu_data;
+	for_each_cpu(cpu, policy->cpus) {
+		cppc_fi = &per_cpu(cppc_freq_inv, cpu);
+		cppc_fi->cpu = cpu;
+		cppc_fi->cpu_data = policy->driver_data;
 		kthread_init_work(&cppc_fi->work, cppc_scale_freq_workfn);
 		init_irq_work(&cppc_fi->irq_work, cppc_irq_work);
 
-		ret = cppc_get_perf_ctrs(i, &fb_ctrs);
+		ret = cppc_get_perf_ctrs(cpu, &cppc_fi->prev_perf_fb_ctrs);
 		if (ret) {
-			pr_warn("%s: failed to read perf counters: %d\n",
-				__func__, ret);
-			fie_disabled = true;
-		} else {
-			cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
+			pr_warn("%s: failed to read perf counters for cpu:%d: %d\n",
+				__func__, cpu, ret);
+
+			/*
+			 * Don't abort if the CPU was offline while the driver
+			 * was getting registered.
+			 */
+			if (cpu_online(cpu))
+				return;
 		}
 	}
+
+	/* Register for freq-invariance */
+	topology_set_scale_freq_source(&cppc_sftd, policy->cpus);
+}
+
+/*
+ * We free all the resources on policy's removal and not on CPU removal as the
+ * irq-work are per-cpu and the hotplug core takes care of flushing the pending
+ * irq-works (hint: smpcfd_dying_cpu()) on CPU hotplug. Even if the kthread-work
+ * fires on another CPU after the concerned CPU is removed, it won't harm.
+ *
+ * We just need to make sure to remove them all on policy->exit().
+ */
+static void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy)
+{
+	struct cppc_freq_invariance *cppc_fi;
+	int cpu;
+
+	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+		return;
+
+	/* policy->cpus will be empty here, use related_cpus instead */
+	topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, policy->related_cpus);
+
+	for_each_cpu(cpu, policy->related_cpus) {
+		cppc_fi = &per_cpu(cppc_freq_inv, cpu);
+		irq_work_sync(&cppc_fi->irq_work);
+		kthread_cancel_work_sync(&cppc_fi->work);
+	}
 }
 
 static void __init cppc_freq_invariance_init(void)
@@ -202,9 +231,6 @@ static void __init cppc_freq_invariance_init(void)
 	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
 		return;
 
-	if (fie_disabled)
-		return;
-
 	kworker_fie = kthread_create_worker(0, "cppc_fie");
 	if (IS_ERR(kworker_fie))
 		return;
@@ -216,37 +242,23 @@ static void __init cppc_freq_invariance_init(void)
 		kthread_destroy_worker(kworker_fie);
 		return;
 	}
-
-	/* Register for freq-invariance */
-	topology_set_scale_freq_source(&cppc_sftd, cpu_present_mask);
 }
 
 static void cppc_freq_invariance_exit(void)
 {
-	struct cppc_freq_invariance *cppc_fi;
-	int i;
-
 	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
 		return;
 
-	if (fie_disabled)
-		return;
-
-	topology_clear_scale_freq_source(SCALE_FREQ_SOURCE_CPPC, cpu_present_mask);
-
-	for_each_possible_cpu(i) {
-		cppc_fi = &per_cpu(cppc_freq_inv, i);
-		irq_work_sync(&cppc_fi->irq_work);
-	}
-
 	kthread_destroy_worker(kworker_fie);
 	kworker_fie = NULL;
 }
 
 #else
-static inline void
-cppc_freq_invariance_policy_init(struct cpufreq_policy *policy,
-				 struct cppc_cpudata *cpu_data)
+static inline void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy)
+{
+}
+
+static inline void cppc_cpufreq_cpu_fie_exit(struct cpufreq_policy *policy)
 {
 }
 
@@ -384,27 +396,6 @@ static int cppc_verify_policy(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
-static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
-{
-	struct cppc_cpudata *cpu_data = policy->driver_data;
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	unsigned int cpu = policy->cpu;
-	int ret;
-
-	cpu_data->perf_ctrls.desired_perf = caps->lowest_perf;
-
-	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
-	if (ret)
-		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
-			 caps->lowest_perf, cpu, ret);
-
-	/* Remove CPU node from list and free driver data for policy */
-	free_cpumask_var(cpu_data->shared_cpu_map);
-	list_del(&cpu_data->node);
-	kfree(policy->driver_data);
-	policy->driver_data = NULL;
-}
-
 /*
  * The PCC subspace describes the rate at which platform can accept commands
  * on the shared PCC channel (including READs which do not count towards freq
@@ -479,6 +470,16 @@ out:
 	return NULL;
 }
 
+static void cppc_cpufreq_put_cpu_data(struct cpufreq_policy *policy)
+{
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+
+	list_del(&cpu_data->node);
+	free_cpumask_var(cpu_data->shared_cpu_map);
+	kfree(cpu_data);
+	policy->driver_data = NULL;
+}
+
 static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
 	unsigned int cpu = policy->cpu;
@@ -532,7 +533,8 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	default:
 		pr_debug("Unsupported CPU co-ord type: %d\n",
 			 policy->shared_type);
-		return -EFAULT;
+		ret = -EFAULT;
+		goto out;
 	}
 
 	/*
@@ -550,13 +552,37 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	if (ret) {
 		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
 			 caps->highest_perf, cpu, ret);
-	} else {
-		cppc_freq_invariance_policy_init(policy, cpu_data);
+		goto out;
 	}
 
+	cppc_cpufreq_cpu_fie_init(policy);
+	return 0;
+
+out:
+	cppc_cpufreq_put_cpu_data(policy);
 	return ret;
 }
 
+static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
+	unsigned int cpu = policy->cpu;
+	int ret;
+
+	cppc_cpufreq_cpu_fie_exit(policy);
+
+	cpu_data->perf_ctrls.desired_perf = caps->lowest_perf;
+
+	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
+	if (ret)
+		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
+			 caps->lowest_perf, cpu, ret);
+
+	cppc_cpufreq_put_cpu_data(policy);
+	return 0;
+}
+
 static inline u64 get_delta(u64 t1, u64 t0)
 {
 	if (t1 > t0 || t0 > ~(u32)0)
@@ -566,18 +592,18 @@ static inline u64 get_delta(u64 t1, u64 t0)
 }
 
 static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				 struct cppc_perf_fb_ctrs fb_ctrs_t1)
+				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
+				 struct cppc_perf_fb_ctrs *fb_ctrs_t1)
 {
 	u64 delta_reference, delta_delivered;
 	u64 reference_perf;
 
-	reference_perf = fb_ctrs_t0.reference_perf;
+	reference_perf = fb_ctrs_t0->reference_perf;
 
-	delta_reference = get_delta(fb_ctrs_t1.reference,
-				    fb_ctrs_t0.reference);
-	delta_delivered = get_delta(fb_ctrs_t1.delivered,
-				    fb_ctrs_t0.delivered);
+	delta_reference = get_delta(fb_ctrs_t1->reference,
+				    fb_ctrs_t0->reference);
+	delta_delivered = get_delta(fb_ctrs_t1->delivered,
+				    fb_ctrs_t0->delivered);
 
 	/* Check to avoid divide-by zero and invalid delivered_perf */
 	if (!delta_reference || !delta_delivered)
@@ -586,23 +612,12 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	return (reference_perf * delta_delivered) / delta_reference;
 }
 
-static int cppc_get_rate_from_fbctrs(struct cppc_cpudata *cpu_data,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t0,
-				     struct cppc_perf_fb_ctrs fb_ctrs_t1)
-{
-	u64 delivered_perf;
-
-	delivered_perf = cppc_perf_from_fbctrs(cpu_data, fb_ctrs_t0,
-					       fb_ctrs_t1);
-
-	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
-}
-
 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 = policy->driver_data;
+	u64 delivered_perf;
 	int ret;
 
 	cpufreq_cpu_put(policy);
@@ -617,7 +632,10 @@ static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 	if (ret)
 		return ret;
 
-	return cppc_get_rate_from_fbctrs(cpu_data, fb_ctrs_t0, fb_ctrs_t1);
+	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
+					       &fb_ctrs_t1);
+
+	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
 }
 
 static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
@@ -665,7 +683,7 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 	.target = cppc_cpufreq_set_target,
 	.get = cppc_cpufreq_get_rate,
 	.init = cppc_cpufreq_cpu_init,
-	.stop_cpu = cppc_cpufreq_stop_cpu,
+	.exit = cppc_cpufreq_cpu_exit,
 	.set_boost = cppc_cpufreq_set_boost,
 	.attr = cppc_cpufreq_attr,
 	.name = "cppc_cpufreq",
@@ -726,10 +744,11 @@ static int __init cppc_cpufreq_init(void)
 	INIT_LIST_HEAD(&cpu_data_list);
 
 	cppc_check_hisi_workaround();
+	cppc_freq_invariance_init();
 
 	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
-	if (!ret)
-		cppc_freq_invariance_init();
+	if (ret)
+		cppc_freq_invariance_exit();
 
 	return ret;
 }
@@ -748,8 +767,8 @@ static inline void free_cpu_data(void)
 
 static void __exit cppc_cpufreq_exit(void)
 {
-	cppc_freq_invariance_exit();
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
+	cppc_freq_invariance_exit();
 
 	free_cpu_data();
 }
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 802abc925b2a..cbab834c37a0 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1367,9 +1367,14 @@ static int cpufreq_online(unsigned int cpu)
 			goto out_free_policy;
 		}
 
+		/*
+		 * The initialization has succeeded and the policy is online.
+		 * If there is a problem with its frequency table, take it
+		 * offline and drop it.
+		 */
 		ret = cpufreq_table_validate_and_sort(policy);
 		if (ret)
-			goto out_exit_policy;
+			goto out_offline_policy;
 
 		/* related_cpus should at least include policy->cpus. */
 		cpumask_copy(policy->related_cpus, policy->cpus);
@@ -1515,6 +1520,10 @@ out_destroy_policy:
 
 	up_write(&policy->rwsem);
 
+out_offline_policy:
+	if (cpufreq_driver->offline)
+		cpufreq_driver->offline(policy);
+
 out_exit_policy:
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index da717f7cd9a9..1570d6f3e75d 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -211,7 +211,7 @@ void cpufreq_stats_free_table(struct cpufreq_policy *policy)
 
 void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 {
-	unsigned int i = 0, count = 0, ret = -ENOMEM;
+	unsigned int i = 0, count;
 	struct cpufreq_stats *stats;
 	unsigned int alloc_size;
 	struct cpufreq_frequency_table *pos;
@@ -253,8 +253,7 @@ void cpufreq_stats_create_table(struct cpufreq_policy *policy)
 	stats->last_index = freq_table_get_index(stats, policy->cur);
 
 	policy->stats = stats;
-	ret = sysfs_create_group(&policy->kobj, &stats_attr_group);
-	if (!ret)
+	if (!sysfs_create_group(&policy->kobj, &stats_attr_group))
 		return;
 
 	/* We failed, release resources */
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index f0401064d7aa..bb4549959b11 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -121,9 +121,10 @@ struct sample {
  * @max_pstate_physical:This is physical Max P state for a processor
  *			This can be higher than the max_pstate which can
  *			be limited by platform thermal design power limits
- * @scaling:		Scaling factor to  convert frequency to cpufreq
- *			frequency units
+ * @perf_ctl_scaling:	PERF_CTL P-state to frequency scaling factor
+ * @scaling:		Scaling factor between performance and frequency
  * @turbo_pstate:	Max Turbo P state possible for this platform
+ * @min_freq:		@min_pstate frequency in cpufreq units
  * @max_freq:		@max_pstate frequency in cpufreq units
  * @turbo_freq:		@turbo_pstate frequency in cpufreq units
  *
@@ -134,8 +135,10 @@ struct pstate_data {
 	int	min_pstate;
 	int	max_pstate;
 	int	max_pstate_physical;
+	int	perf_ctl_scaling;
 	int	scaling;
 	int	turbo_pstate;
+	unsigned int min_freq;
 	unsigned int max_freq;
 	unsigned int turbo_freq;
 };
@@ -366,7 +369,7 @@ static void intel_pstate_set_itmt_prio(int cpu)
 	}
 }
 
-static int intel_pstate_get_cppc_guranteed(int cpu)
+static int intel_pstate_get_cppc_guaranteed(int cpu)
 {
 	struct cppc_perf_caps cppc_perf;
 	int ret;
@@ -382,7 +385,7 @@ static int intel_pstate_get_cppc_guranteed(int cpu)
 }
 
 #else /* CONFIG_ACPI_CPPC_LIB */
-static void intel_pstate_set_itmt_prio(int cpu)
+static inline void intel_pstate_set_itmt_prio(int cpu)
 {
 }
 #endif /* CONFIG_ACPI_CPPC_LIB */
@@ -467,6 +470,20 @@ static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
 
 	acpi_processor_unregister_performance(policy->cpu);
 }
+
+static bool intel_pstate_cppc_perf_valid(u32 perf, struct cppc_perf_caps *caps)
+{
+	return perf && perf <= caps->highest_perf && perf >= caps->lowest_perf;
+}
+
+static bool intel_pstate_cppc_perf_caps(struct cpudata *cpu,
+					struct cppc_perf_caps *caps)
+{
+	if (cppc_get_perf_caps(cpu->cpu, caps))
+		return false;
+
+	return caps->highest_perf && caps->lowest_perf <= caps->highest_perf;
+}
 #else /* CONFIG_ACPI */
 static inline void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
 {
@@ -483,12 +500,146 @@ static inline bool intel_pstate_acpi_pm_profile_server(void)
 #endif /* CONFIG_ACPI */
 
 #ifndef CONFIG_ACPI_CPPC_LIB
-static int intel_pstate_get_cppc_guranteed(int cpu)
+static inline int intel_pstate_get_cppc_guaranteed(int cpu)
 {
 	return -ENOTSUPP;
 }
 #endif /* CONFIG_ACPI_CPPC_LIB */
 
+static void intel_pstate_hybrid_hwp_perf_ctl_parity(struct cpudata *cpu)
+{
+	pr_debug("CPU%d: Using PERF_CTL scaling for HWP\n", cpu->cpu);
+
+	cpu->pstate.scaling = cpu->pstate.perf_ctl_scaling;
+}
+
+/**
+ * intel_pstate_hybrid_hwp_calibrate - Calibrate HWP performance levels.
+ * @cpu: Target CPU.
+ *
+ * On hybrid processors, HWP may expose more performance levels than there are
+ * P-states accessible through the PERF_CTL interface.  If that happens, the
+ * scaling factor between HWP performance levels and CPU frequency will be less
+ * than the scaling factor between P-state values and CPU frequency.
+ *
+ * In that case, the scaling factor between HWP performance levels and CPU
+ * frequency needs to be determined which can be done with the help of the
+ * observation that certain HWP performance levels should correspond to certain
+ * P-states, like for example the HWP highest performance should correspond
+ * to the maximum turbo P-state of the CPU.
+ */
+static void intel_pstate_hybrid_hwp_calibrate(struct cpudata *cpu)
+{
+	int perf_ctl_max_phys = cpu->pstate.max_pstate_physical;
+	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
+	int perf_ctl_turbo = pstate_funcs.get_turbo();
+	int turbo_freq = perf_ctl_turbo * perf_ctl_scaling;
+	int perf_ctl_max = pstate_funcs.get_max();
+	int max_freq = perf_ctl_max * perf_ctl_scaling;
+	int scaling = INT_MAX;
+	int freq;
+
+	pr_debug("CPU%d: perf_ctl_max_phys = %d\n", cpu->cpu, perf_ctl_max_phys);
+	pr_debug("CPU%d: perf_ctl_max = %d\n", cpu->cpu, perf_ctl_max);
+	pr_debug("CPU%d: perf_ctl_turbo = %d\n", cpu->cpu, perf_ctl_turbo);
+	pr_debug("CPU%d: perf_ctl_scaling = %d\n", cpu->cpu, perf_ctl_scaling);
+
+	pr_debug("CPU%d: HWP_CAP guaranteed = %d\n", cpu->cpu, cpu->pstate.max_pstate);
+	pr_debug("CPU%d: HWP_CAP highest = %d\n", cpu->cpu, cpu->pstate.turbo_pstate);
+
+#ifdef CONFIG_ACPI
+	if (IS_ENABLED(CONFIG_ACPI_CPPC_LIB)) {
+		struct cppc_perf_caps caps;
+
+		if (intel_pstate_cppc_perf_caps(cpu, &caps)) {
+			if (intel_pstate_cppc_perf_valid(caps.nominal_perf, &caps)) {
+				pr_debug("CPU%d: Using CPPC nominal\n", cpu->cpu);
+
+				/*
+				 * If the CPPC nominal performance is valid, it
+				 * can be assumed to correspond to cpu_khz.
+				 */
+				if (caps.nominal_perf == perf_ctl_max_phys) {
+					intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
+					return;
+				}
+				scaling = DIV_ROUND_UP(cpu_khz, caps.nominal_perf);
+			} else if (intel_pstate_cppc_perf_valid(caps.guaranteed_perf, &caps)) {
+				pr_debug("CPU%d: Using CPPC guaranteed\n", cpu->cpu);
+
+				/*
+				 * If the CPPC guaranteed performance is valid,
+				 * it can be assumed to correspond to max_freq.
+				 */
+				if (caps.guaranteed_perf == perf_ctl_max) {
+					intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
+					return;
+				}
+				scaling = DIV_ROUND_UP(max_freq, caps.guaranteed_perf);
+			}
+		}
+	}
+#endif
+	/*
+	 * If using the CPPC data to compute the HWP-to-frequency scaling factor
+	 * doesn't work, use the HWP_CAP gauranteed perf for this purpose with
+	 * the assumption that it corresponds to max_freq.
+	 */
+	if (scaling > perf_ctl_scaling) {
+		pr_debug("CPU%d: Using HWP_CAP guaranteed\n", cpu->cpu);
+
+		if (cpu->pstate.max_pstate == perf_ctl_max) {
+			intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
+			return;
+		}
+		scaling = DIV_ROUND_UP(max_freq, cpu->pstate.max_pstate);
+		if (scaling > perf_ctl_scaling) {
+			/*
+			 * This should not happen, because it would mean that
+			 * the number of HWP perf levels was less than the
+			 * number of P-states, so use the PERF_CTL scaling in
+			 * that case.
+			 */
+			pr_debug("CPU%d: scaling (%d) out of range\n", cpu->cpu,
+				scaling);
+
+			intel_pstate_hybrid_hwp_perf_ctl_parity(cpu);
+			return;
+		}
+	}
+
+	/*
+	 * If the product of the HWP performance scaling factor obtained above
+	 * and the HWP_CAP highest performance is greater than the maximum turbo
+	 * frequency corresponding to the pstate_funcs.get_turbo() return value,
+	 * the scaling factor is too high, so recompute it so that the HWP_CAP
+	 * highest performance corresponds to the maximum turbo frequency.
+	 */
+	if (turbo_freq < cpu->pstate.turbo_pstate * scaling) {
+		pr_debug("CPU%d: scaling too high (%d)\n", cpu->cpu, scaling);
+
+		cpu->pstate.turbo_freq = turbo_freq;
+		scaling = DIV_ROUND_UP(turbo_freq, cpu->pstate.turbo_pstate);
+	}
+
+	cpu->pstate.scaling = scaling;
+
+	pr_debug("CPU%d: HWP-to-frequency scaling factor: %d\n", cpu->cpu, 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 = DIV_ROUND_UP(freq, scaling);
+
+	cpu->pstate.min_freq = cpu->pstate.min_pstate * perf_ctl_scaling;
+	/*
+	 * Cast the min P-state value retrieved via pstate_funcs.get_min() to
+	 * the effective range of HWP performance levels.
+	 */
+	cpu->pstate.min_pstate = DIV_ROUND_UP(cpu->pstate.min_freq, scaling);
+}
+
 static inline void update_turbo_state(void)
 {
 	u64 misc_en;
@@ -795,19 +946,22 @@ cpufreq_freq_attr_rw(energy_performance_preference);
 
 static ssize_t show_base_frequency(struct cpufreq_policy *policy, char *buf)
 {
-	struct cpudata *cpu;
-	u64 cap;
-	int ratio;
+	struct cpudata *cpu = all_cpu_data[policy->cpu];
+	int ratio, freq;
 
-	ratio = intel_pstate_get_cppc_guranteed(policy->cpu);
+	ratio = intel_pstate_get_cppc_guaranteed(policy->cpu);
 	if (ratio <= 0) {
+		u64 cap;
+
 		rdmsrl_on_cpu(policy->cpu, MSR_HWP_CAPABILITIES, &cap);
 		ratio = HWP_GUARANTEED_PERF(cap);
 	}
 
-	cpu = all_cpu_data[policy->cpu];
+	freq = ratio * cpu->pstate.scaling;
+	if (cpu->pstate.scaling != cpu->pstate.perf_ctl_scaling)
+		freq = rounddown(freq, cpu->pstate.perf_ctl_scaling);
 
-	return sprintf(buf, "%d\n", ratio * cpu->pstate.scaling);
+	return sprintf(buf, "%d\n", freq);
 }
 
 cpufreq_freq_attr_ro(base_frequency);
@@ -831,9 +985,20 @@ 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 * cpu->pstate.scaling;
-	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+
+	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);
+	}
 }
 
 static void intel_pstate_hwp_set(unsigned int cpu)
@@ -1365,8 +1530,6 @@ define_one_global_rw(energy_efficiency);
 static struct attribute *intel_pstate_attributes[] = {
 	&status.attr,
 	&no_turbo.attr,
-	&turbo_pct.attr,
-	&num_pstates.attr,
 	NULL
 };
 
@@ -1391,6 +1554,14 @@ static void __init intel_pstate_sysfs_expose_params(void)
 	if (WARN_ON(rc))
 		return;
 
+	if (!boot_cpu_has(X86_FEATURE_HYBRID_CPU)) {
+		rc = sysfs_create_file(intel_pstate_kobject, &turbo_pct.attr);
+		WARN_ON(rc);
+
+		rc = sysfs_create_file(intel_pstate_kobject, &num_pstates.attr);
+		WARN_ON(rc);
+	}
+
 	/*
 	 * If per cpu limits are enforced there are no global limits, so
 	 * return without creating max/min_perf_pct attributes
@@ -1417,6 +1588,11 @@ static void __init intel_pstate_sysfs_remove(void)
 
 	sysfs_remove_group(intel_pstate_kobject, &intel_pstate_attr_group);
 
+	if (!boot_cpu_has(X86_FEATURE_HYBRID_CPU)) {
+		sysfs_remove_file(intel_pstate_kobject, &num_pstates.attr);
+		sysfs_remove_file(intel_pstate_kobject, &turbo_pct.attr);
+	}
+
 	if (!per_cpu_limits) {
 		sysfs_remove_file(intel_pstate_kobject, &max_perf_pct.attr);
 		sysfs_remove_file(intel_pstate_kobject, &min_perf_pct.attr);
@@ -1713,19 +1889,33 @@ static void intel_pstate_max_within_limits(struct cpudata *cpu)
 
 static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
+	bool hybrid_cpu = boot_cpu_has(X86_FEATURE_HYBRID_CPU);
+	int perf_ctl_max_phys = pstate_funcs.get_max_physical();
+	int perf_ctl_scaling = hybrid_cpu ? cpu_khz / perf_ctl_max_phys :
+					    pstate_funcs.get_scaling();
+
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
-	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical();
-	cpu->pstate.scaling = pstate_funcs.get_scaling();
+	cpu->pstate.max_pstate_physical = perf_ctl_max_phys;
+	cpu->pstate.perf_ctl_scaling = perf_ctl_scaling;
 
 	if (hwp_active && !hwp_mode_bdw) {
 		__intel_pstate_get_hwp_cap(cpu);
+
+		if (hybrid_cpu)
+			intel_pstate_hybrid_hwp_calibrate(cpu);
+		else
+			cpu->pstate.scaling = perf_ctl_scaling;
 	} else {
+		cpu->pstate.scaling = perf_ctl_scaling;
 		cpu->pstate.max_pstate = pstate_funcs.get_max();
 		cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
 	}
 
-	cpu->pstate.max_freq = cpu->pstate.max_pstate * cpu->pstate.scaling;
-	cpu->pstate.turbo_freq = cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	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;
+	}
 
 	if (pstate_funcs.get_aperf_mperf_shift)
 		cpu->aperf_mperf_shift = pstate_funcs.get_aperf_mperf_shift();
@@ -2087,6 +2277,8 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	X86_MATCH(ATOM_GOLDMONT,	core_funcs),
 	X86_MATCH(ATOM_GOLDMONT_PLUS,	core_funcs),
 	X86_MATCH(SKYLAKE_X,		core_funcs),
+	X86_MATCH(COMETLAKE,		core_funcs),
+	X86_MATCH(ICELAKE_X,		core_funcs),
 	{}
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
@@ -2195,23 +2387,34 @@ static void intel_pstate_update_perf_limits(struct cpudata *cpu,
 					    unsigned int policy_min,
 					    unsigned int policy_max)
 {
-	int scaling = cpu->pstate.scaling;
+	int perf_ctl_scaling = cpu->pstate.perf_ctl_scaling;
 	int32_t max_policy_perf, min_policy_perf;
 
+	max_policy_perf = policy_max / perf_ctl_scaling;
+	if (policy_max == policy_min) {
+		min_policy_perf = max_policy_perf;
+	} else {
+		min_policy_perf = policy_min / perf_ctl_scaling;
+		min_policy_perf = clamp_t(int32_t, min_policy_perf,
+					  0, max_policy_perf);
+	}
+
 	/*
 	 * HWP needs some special consideration, because HWP_REQUEST uses
 	 * abstract values to represent performance rather than pure ratios.
 	 */
-	if (hwp_active)
+	if (hwp_active) {
 		intel_pstate_get_hwp_cap(cpu);
 
-	max_policy_perf = policy_max / scaling;
-	if (policy_max == policy_min) {
-		min_policy_perf = max_policy_perf;
-	} else {
-		min_policy_perf = policy_min / scaling;
-		min_policy_perf = clamp_t(int32_t, min_policy_perf,
-					  0, max_policy_perf);
+		if (cpu->pstate.scaling != perf_ctl_scaling) {
+			int scaling = cpu->pstate.scaling;
+			int freq;
+
+			freq = max_policy_perf * perf_ctl_scaling;
+			max_policy_perf = DIV_ROUND_UP(freq, scaling);
+			freq = min_policy_perf * perf_ctl_scaling;
+			min_policy_perf = DIV_ROUND_UP(freq, scaling);
+		}
 	}
 
 	pr_debug("cpu:%d min_policy_perf:%d max_policy_perf:%d\n",
@@ -2329,7 +2532,7 @@ static int intel_pstate_verify_policy(struct cpufreq_policy_data *policy)
 	return 0;
 }
 
-static int intel_pstate_cpu_offline(struct cpufreq_policy *policy)
+static int intel_cpufreq_cpu_offline(struct cpufreq_policy *policy)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 
@@ -2374,11 +2577,11 @@ static int intel_pstate_cpu_online(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
+static int intel_pstate_cpu_offline(struct cpufreq_policy *policy)
 {
-	pr_debug("CPU %d stopping\n", policy->cpu);
-
 	intel_pstate_clear_update_util_hook(policy->cpu);
+
+	return intel_cpufreq_cpu_offline(policy);
 }
 
 static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
@@ -2405,7 +2608,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	cpu->min_perf_ratio = 0;
 
 	/* cpuinfo and default policy values */
-	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
+	policy->cpuinfo.min_freq = cpu->pstate.min_freq;
 	update_turbo_state();
 	global.turbo_disabled_mf = global.turbo_disabled;
 	policy->cpuinfo.max_freq = global.turbo_disabled ?
@@ -2451,7 +2654,6 @@ static struct cpufreq_driver intel_pstate = {
 	.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,
@@ -2753,7 +2955,7 @@ static struct cpufreq_driver intel_cpufreq = {
 	.fast_switch	= intel_cpufreq_fast_switch,
 	.init		= intel_cpufreq_cpu_init,
 	.exit		= intel_cpufreq_cpu_exit,
-	.offline	= intel_pstate_cpu_offline,
+	.offline	= intel_cpufreq_cpu_offline,
 	.online		= intel_pstate_cpu_online,
 	.suspend	= intel_pstate_suspend,
 	.resume		= intel_pstate_resume,
@@ -3033,6 +3235,14 @@ static const struct x86_cpu_id hwp_support_ids[] __initconst = {
 	{}
 };
 
+static bool intel_pstate_hwp_is_enabled(void)
+{
+	u64 value;
+
+	rdmsrl(MSR_PM_ENABLE, value);
+	return !!(value & 0x1);
+}
+
 static int __init intel_pstate_init(void)
 {
 	const struct x86_cpu_id *id;
@@ -3051,8 +3261,12 @@ static int __init intel_pstate_init(void)
 		 * Avoid enabling HWP for processors without EPP support,
 		 * because that means incomplete HWP implementation which is a
 		 * corner case and supporting it is generally problematic.
+		 *
+		 * If HWP is enabled already, though, there is no choice but to
+		 * deal with it.
 		 */
-		if (!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) {
+		if ((!no_hwp && boot_cpu_has(X86_FEATURE_HWP_EPP)) ||
+		    intel_pstate_hwp_is_enabled()) {
 			hwp_active++;
 			hwp_mode_bdw = id->driver_data;
 			intel_pstate.attr = hwp_cpufreq_attrs;
@@ -3123,6 +3337,8 @@ hwp_cpu_matched:
 		}
 
 		pr_info("HWP enabled\n");
+	} else if (boot_cpu_has(X86_FEATURE_HYBRID_CPU)) {
+		pr_warn("Problematic setup: Hybrid processor with disabled HWP\n");
 	}
 
 	return 0;
diff --git a/drivers/cpufreq/loongson2_cpufreq.c b/drivers/cpufreq/loongson2_cpufreq.c
index d05e761d9572..afc59b292153 100644
--- a/drivers/cpufreq/loongson2_cpufreq.c
+++ b/drivers/cpufreq/loongson2_cpufreq.c
@@ -16,7 +16,6 @@
 #include <linux/cpufreq.h>
 #include <linux/module.h>
 #include <linux/err.h>
-#include <linux/sched.h>	/* set_cpus_allowed() */
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 
diff --git a/drivers/cpufreq/sc520_freq.c b/drivers/cpufreq/sc520_freq.c
index 73a208559fe2..330c8d6cf93c 100644
--- a/drivers/cpufreq/sc520_freq.c
+++ b/drivers/cpufreq/sc520_freq.c
@@ -42,6 +42,7 @@ static unsigned int sc520_freq_get_cpu_frequency(unsigned int cpu)
 	default:
 		pr_err("error: cpuctl register has unexpected value %02x\n",
 		       clockspeed_reg);
+		fallthrough;
 	case 0x01:
 		return 100000;
 	case 0x02:
diff --git a/drivers/cpufreq/sh-cpufreq.c b/drivers/cpufreq/sh-cpufreq.c
index 0ac265d47ef0..1a251e635ebd 100644
--- a/drivers/cpufreq/sh-cpufreq.c
+++ b/drivers/cpufreq/sh-cpufreq.c
@@ -23,7 +23,6 @@
 #include <linux/cpumask.h>
 #include <linux/cpu.h>
 #include <linux/smp.h>
-#include <linux/sched.h>	/* set_cpus_allowed() */
 #include <linux/clk.h>
 #include <linux/percpu.h>
 #include <linux/sh_clk.h>