1 files changed, 445 insertions, 270 deletions

diff --git a/drivers/cpufreq/cppc_cpufreq.c b/drivers/cpufreq/cppc_cpufreq.c
index d4c27022b9c9..9eac77c4f294 100644
--- a/drivers/cpufreq/cppc_cpufreq.c
+++ b/drivers/cpufreq/cppc_cpufreq.c
@@ -16,52 +16,27 @@
 #include <linux/delay.h>
 #include <linux/cpu.h>
 #include <linux/cpufreq.h>
-#include <linux/dmi.h>
 #include <linux/irq_work.h>
 #include <linux/kthread.h>
 #include <linux/time.h>
 #include <linux/vmalloc.h>
 #include <uapi/linux/sched/types.h>
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 #include <acpi/cppc_acpi.h>
 
-/* Minimum struct length needed for the DMI processor entry we want */
-#define DMI_ENTRY_PROCESSOR_MIN_LENGTH	48
-
-/* Offset in the DMI processor structure for the max frequency */
-#define DMI_PROCESSOR_MAX_SPEED		0x14
-
-/*
- * This list contains information parsed from per CPU ACPI _CPC and _PSD
- * structures: e.g. the highest and lowest supported performance, capabilities,
- * desired performance, level requested etc. Depending on the share_type, not
- * all CPUs will have an entry in the list.
- */
-static LIST_HEAD(cpu_data_list);
-
-static bool boost_supported;
-
-struct cppc_workaround_oem_info {
-	char oem_id[ACPI_OEM_ID_SIZE + 1];
-	char oem_table_id[ACPI_OEM_TABLE_ID_SIZE + 1];
-	u32 oem_revision;
-};
-
-static struct cppc_workaround_oem_info wa_info[] = {
-	{
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP07   ",
-		.oem_revision	= 0,
-	}, {
-		.oem_id		= "HISI  ",
-		.oem_table_id	= "HIP08   ",
-		.oem_revision	= 0,
-	}
-};
+static struct cpufreq_driver cppc_cpufreq_driver;
 
 #ifdef CONFIG_ACPI_CPPC_CPUFREQ_FIE
+static enum {
+	FIE_UNSET = -1,
+	FIE_ENABLED,
+	FIE_DISABLED
+} fie_disabled = FIE_UNSET;
+
+module_param(fie_disabled, int, 0444);
+MODULE_PARM_DESC(fie_disabled, "Disable Frequency Invariance Engine (FIE)");
 
 /* Frequency invariance support */
 struct cppc_freq_invariance {
@@ -75,10 +50,7 @@ struct cppc_freq_invariance {
 static DEFINE_PER_CPU(struct cppc_freq_invariance, cppc_freq_inv);
 static struct kthread_worker *kworker_fie;
 
-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,
+static int cppc_perf_from_fbctrs(struct cppc_perf_fb_ctrs *fb_ctrs_t0,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t1);
 
 /**
@@ -114,8 +86,10 @@ 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);
+	perf = cppc_perf_from_fbctrs(&cppc_fi->prev_perf_fb_ctrs, &fb_ctrs);
+	if (!perf)
+		return;
+
 	cppc_fi->prev_perf_fb_ctrs = fb_ctrs;
 
 	perf <<= SCHED_CAPACITY_SHIFT;
@@ -157,7 +131,7 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy)
 	struct cppc_freq_invariance *cppc_fi;
 	int cpu, ret;
 
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled)
 		return;
 
 	for_each_cpu(cpu, policy->cpus) {
@@ -168,16 +142,15 @@ static void cppc_cpufreq_cpu_fie_init(struct cpufreq_policy *policy)
 		init_irq_work(&cppc_fi->irq_work, cppc_irq_work);
 
 		ret = cppc_get_perf_ctrs(cpu, &cppc_fi->prev_perf_fb_ctrs);
-		if (ret) {
-			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;
+		/*
+		 * Don't abort as the CPU was offline while the driver was
+		 * getting registered.
+		 */
+		if (ret && cpu_online(cpu)) {
+			pr_debug("%s: failed to read perf counters for cpu:%d: %d\n",
+				__func__, cpu, ret);
+			return;
 		}
 	}
 
@@ -198,7 +171,7 @@ 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)
+	if (fie_disabled)
 		return;
 
 	/* policy->cpus will be empty here, use related_cpus instead */
@@ -222,35 +195,46 @@ static void __init cppc_freq_invariance_init(void)
 		 * Fake (unused) bandwidth; workaround to "fix"
 		 * priority inheritance.
 		 */
-		.sched_runtime	= 1000000,
-		.sched_deadline = 10000000,
-		.sched_period	= 10000000,
+		.sched_runtime	= NSEC_PER_MSEC,
+		.sched_deadline = 10 * NSEC_PER_MSEC,
+		.sched_period	= 10 * NSEC_PER_MSEC,
 	};
 	int ret;
 
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled != FIE_ENABLED && fie_disabled != FIE_DISABLED) {
+		fie_disabled = FIE_ENABLED;
+		if (cppc_perf_ctrs_in_pcc()) {
+			pr_info("FIE not enabled on systems with registers in PCC\n");
+			fie_disabled = FIE_DISABLED;
+		}
+	}
+
+	if (fie_disabled)
 		return;
 
-	kworker_fie = kthread_create_worker(0, "cppc_fie");
-	if (IS_ERR(kworker_fie))
+	kworker_fie = kthread_run_worker(0, "cppc_fie");
+	if (IS_ERR(kworker_fie)) {
+		pr_warn("%s: failed to create kworker_fie: %ld\n", __func__,
+			PTR_ERR(kworker_fie));
+		fie_disabled = FIE_DISABLED;
 		return;
+	}
 
 	ret = sched_setattr_nocheck(kworker_fie->task, &attr);
 	if (ret) {
 		pr_warn("%s: failed to set SCHED_DEADLINE: %d\n", __func__,
 			ret);
 		kthread_destroy_worker(kworker_fie);
-		return;
+		fie_disabled = FIE_DISABLED;
 	}
 }
 
 static void cppc_freq_invariance_exit(void)
 {
-	if (cppc_cpufreq_driver.get == hisi_cppc_cpufreq_get_rate)
+	if (fie_disabled)
 		return;
 
 	kthread_destroy_worker(kworker_fie);
-	kworker_fie = NULL;
 }
 
 #else
@@ -271,111 +255,17 @@ static inline void cppc_freq_invariance_exit(void)
 }
 #endif /* CONFIG_ACPI_CPPC_CPUFREQ_FIE */
 
-/* Callback function used to retrieve the max frequency from DMI */
-static void cppc_find_dmi_mhz(const struct dmi_header *dm, void *private)
-{
-	const u8 *dmi_data = (const u8 *)dm;
-	u16 *mhz = (u16 *)private;
-
-	if (dm->type == DMI_ENTRY_PROCESSOR &&
-	    dm->length >= DMI_ENTRY_PROCESSOR_MIN_LENGTH) {
-		u16 val = (u16)get_unaligned((const u16 *)
-				(dmi_data + DMI_PROCESSOR_MAX_SPEED));
-		*mhz = val > *mhz ? val : *mhz;
-	}
-}
-
-/* Look up the max frequency in DMI */
-static u64 cppc_get_dmi_max_khz(void)
-{
-	u16 mhz = 0;
-
-	dmi_walk(cppc_find_dmi_mhz, &mhz);
-
-	/*
-	 * Real stupid fallback value, just in case there is no
-	 * actual value set.
-	 */
-	mhz = mhz ? mhz : 1;
-
-	return (1000 * mhz);
-}
-
-/*
- * If CPPC lowest_freq and nominal_freq registers are exposed then we can
- * use them to convert perf to freq and vice versa
- *
- * If the perf/freq point lies between Nominal and Lowest, we can treat
- * (Low perf, Low freq) and (Nom Perf, Nom freq) as 2D co-ordinates of a line
- * and extrapolate the rest
- * For perf/freq > Nominal, we use the ratio perf:freq at Nominal for conversion
- */
-static unsigned int cppc_cpufreq_perf_to_khz(struct cppc_cpudata *cpu_data,
-					     unsigned int perf)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	static u64 max_khz;
-	u64 mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		if (perf >= caps->nominal_perf) {
-			mul = caps->nominal_freq;
-			div = caps->nominal_perf;
-		} else {
-			mul = caps->nominal_freq - caps->lowest_freq;
-			div = caps->nominal_perf - caps->lowest_perf;
-		}
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = max_khz;
-		div = caps->highest_perf;
-	}
-	return (u64)perf * mul / div;
-}
-
-static unsigned int cppc_cpufreq_khz_to_perf(struct cppc_cpudata *cpu_data,
-					     unsigned int freq)
-{
-	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
-	static u64 max_khz;
-	u64  mul, div;
-
-	if (caps->lowest_freq && caps->nominal_freq) {
-		if (freq >= caps->nominal_freq) {
-			mul = caps->nominal_perf;
-			div = caps->nominal_freq;
-		} else {
-			mul = caps->lowest_perf;
-			div = caps->lowest_freq;
-		}
-	} else {
-		if (!max_khz)
-			max_khz = cppc_get_dmi_max_khz();
-		mul = caps->highest_perf;
-		div = max_khz;
-	}
-
-	return (u64)freq * mul / div;
-}
-
 static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 				   unsigned int target_freq,
 				   unsigned int relation)
-
 {
 	struct cppc_cpudata *cpu_data = policy->driver_data;
 	unsigned int cpu = policy->cpu;
 	struct cpufreq_freqs freqs;
-	u32 desired_perf;
 	int ret = 0;
 
-	desired_perf = cppc_cpufreq_khz_to_perf(cpu_data, target_freq);
-	/* Return if it is exactly the same perf */
-	if (desired_perf == cpu_data->perf_ctrls.desired_perf)
-		return ret;
-
-	cpu_data->perf_ctrls.desired_perf = desired_perf;
+	cpu_data->perf_ctrls.desired_perf =
+			cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
 	freqs.old = policy->cur;
 	freqs.new = target_freq;
 
@@ -390,12 +280,43 @@ static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
 	return ret;
 }
 
+static unsigned int cppc_cpufreq_fast_switch(struct cpufreq_policy *policy,
+					      unsigned int target_freq)
+{
+	struct cppc_cpudata *cpu_data = policy->driver_data;
+	unsigned int cpu = policy->cpu;
+	u32 desired_perf;
+	int ret;
+
+	desired_perf = cppc_khz_to_perf(&cpu_data->perf_caps, target_freq);
+	cpu_data->perf_ctrls.desired_perf = desired_perf;
+	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
+
+	if (ret) {
+		pr_debug("Failed to set target on CPU:%d. ret:%d\n",
+			 cpu, ret);
+		return 0;
+	}
+
+	return target_freq;
+}
+
 static int cppc_verify_policy(struct cpufreq_policy_data *policy)
 {
 	cpufreq_verify_within_cpu_limits(policy);
 	return 0;
 }
 
+static unsigned int __cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
+{
+	int transition_latency_ns = cppc_get_transition_latency(cpu);
+
+	if (transition_latency_ns < 0)
+		return CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS / NSEC_PER_USEC;
+
+	return transition_latency_ns / NSEC_PER_USEC;
+}
+
 /*
  * 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
@@ -418,17 +339,204 @@ static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 			return 10000;
 		}
 	}
-	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+	return __cppc_cpufreq_get_transition_delay_us(cpu);
 }
-
 #else
-
 static unsigned int cppc_cpufreq_get_transition_delay_us(unsigned int cpu)
 {
-	return cppc_get_transition_latency(cpu) / NSEC_PER_USEC;
+	return __cppc_cpufreq_get_transition_delay_us(cpu);
 }
 #endif
 
+#if defined(CONFIG_ARM64) && defined(CONFIG_ENERGY_MODEL)
+
+static DEFINE_PER_CPU(unsigned int, efficiency_class);
+
+/* Create an artificial performance state every CPPC_EM_CAP_STEP capacity unit. */
+#define CPPC_EM_CAP_STEP	(20)
+/* Increase the cost value by CPPC_EM_COST_STEP every performance state. */
+#define CPPC_EM_COST_STEP	(1)
+/* Add a cost gap correspnding to the energy of 4 CPUs. */
+#define CPPC_EM_COST_GAP	(4 * SCHED_CAPACITY_SCALE * CPPC_EM_COST_STEP \
+				/ CPPC_EM_CAP_STEP)
+
+static unsigned int get_perf_level_count(struct cpufreq_policy *policy)
+{
+	struct cppc_perf_caps *perf_caps;
+	unsigned int min_cap, max_cap;
+	struct cppc_cpudata *cpu_data;
+	int cpu = policy->cpu;
+
+	cpu_data = policy->driver_data;
+	perf_caps = &cpu_data->perf_caps;
+	max_cap = arch_scale_cpu_capacity(cpu);
+	min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+			  perf_caps->highest_perf);
+	if ((min_cap == 0) || (max_cap < min_cap))
+		return 0;
+	return 1 + max_cap / CPPC_EM_CAP_STEP - min_cap / CPPC_EM_CAP_STEP;
+}
+
+/*
+ * The cost is defined as:
+ *   cost = power * max_frequency / frequency
+ */
+static inline unsigned long compute_cost(int cpu, int step)
+{
+	return CPPC_EM_COST_GAP * per_cpu(efficiency_class, cpu) +
+			step * CPPC_EM_COST_STEP;
+}
+
+static int cppc_get_cpu_power(struct device *cpu_dev,
+		unsigned long *power, unsigned long *KHz)
+{
+	unsigned long perf_step, perf_prev, perf, perf_check;
+	unsigned int min_step, max_step, step, step_check;
+	unsigned long prev_freq = *KHz;
+	unsigned int min_cap, max_cap;
+	struct cpufreq_policy *policy;
+
+	struct cppc_perf_caps *perf_caps;
+	struct cppc_cpudata *cpu_data;
+
+	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	if (!policy)
+		return -EINVAL;
+
+	cpu_data = policy->driver_data;
+	perf_caps = &cpu_data->perf_caps;
+	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
+	min_cap = div_u64((u64)max_cap * perf_caps->lowest_perf,
+			  perf_caps->highest_perf);
+	perf_step = div_u64((u64)CPPC_EM_CAP_STEP * perf_caps->highest_perf,
+			    max_cap);
+	min_step = min_cap / CPPC_EM_CAP_STEP;
+	max_step = max_cap / CPPC_EM_CAP_STEP;
+
+	perf_prev = cppc_khz_to_perf(perf_caps, *KHz);
+	step = perf_prev / perf_step;
+
+	if (step > max_step)
+		return -EINVAL;
+
+	if (min_step == max_step) {
+		step = max_step;
+		perf = perf_caps->highest_perf;
+	} else if (step < min_step) {
+		step = min_step;
+		perf = perf_caps->lowest_perf;
+	} else {
+		step++;
+		if (step == max_step)
+			perf = perf_caps->highest_perf;
+		else
+			perf = step * perf_step;
+	}
+
+	*KHz = cppc_perf_to_khz(perf_caps, perf);
+	perf_check = cppc_khz_to_perf(perf_caps, *KHz);
+	step_check = perf_check / perf_step;
+
+	/*
+	 * To avoid bad integer approximation, check that new frequency value
+	 * increased and that the new frequency will be converted to the
+	 * desired step value.
+	 */
+	while ((*KHz == prev_freq) || (step_check != step)) {
+		perf++;
+		*KHz = cppc_perf_to_khz(perf_caps, perf);
+		perf_check = cppc_khz_to_perf(perf_caps, *KHz);
+		step_check = perf_check / perf_step;
+	}
+
+	/*
+	 * With an artificial EM, only the cost value is used. Still the power
+	 * is populated such as 0 < power < EM_MAX_POWER. This allows to add
+	 * more sense to the artificial performance states.
+	 */
+	*power = compute_cost(cpu_dev->id, step);
+
+	return 0;
+}
+
+static int cppc_get_cpu_cost(struct device *cpu_dev, unsigned long KHz,
+		unsigned long *cost)
+{
+	unsigned long perf_step, perf_prev;
+	struct cppc_perf_caps *perf_caps;
+	struct cpufreq_policy *policy;
+	struct cppc_cpudata *cpu_data;
+	unsigned int max_cap;
+	int step;
+
+	policy = cpufreq_cpu_get_raw(cpu_dev->id);
+	if (!policy)
+		return -EINVAL;
+
+	cpu_data = policy->driver_data;
+	perf_caps = &cpu_data->perf_caps;
+	max_cap = arch_scale_cpu_capacity(cpu_dev->id);
+
+	perf_prev = cppc_khz_to_perf(perf_caps, KHz);
+	perf_step = CPPC_EM_CAP_STEP * perf_caps->highest_perf / max_cap;
+	step = perf_prev / perf_step;
+
+	*cost = compute_cost(cpu_dev->id, step);
+
+	return 0;
+}
+
+static void cppc_cpufreq_register_em(struct cpufreq_policy *policy)
+{
+	struct cppc_cpudata *cpu_data;
+	struct em_data_callback em_cb =
+		EM_ADV_DATA_CB(cppc_get_cpu_power, cppc_get_cpu_cost);
+
+	cpu_data = policy->driver_data;
+	em_dev_register_perf_domain(get_cpu_device(policy->cpu),
+			get_perf_level_count(policy), &em_cb,
+			cpu_data->shared_cpu_map, 0);
+}
+
+static void populate_efficiency_class(void)
+{
+	struct acpi_madt_generic_interrupt *gicc;
+	DECLARE_BITMAP(used_classes, 256) = {};
+	int class, cpu, index;
+
+	for_each_possible_cpu(cpu) {
+		gicc = acpi_cpu_get_madt_gicc(cpu);
+		class = gicc->efficiency_class;
+		bitmap_set(used_classes, class, 1);
+	}
+
+	if (bitmap_weight(used_classes, 256) <= 1) {
+		pr_debug("Efficiency classes are all equal (=%d). "
+			"No EM registered", class);
+		return;
+	}
+
+	/*
+	 * Squeeze efficiency class values on [0:#efficiency_class-1].
+	 * Values are per spec in [0:255].
+	 */
+	index = 0;
+	for_each_set_bit(class, used_classes, 256) {
+		for_each_possible_cpu(cpu) {
+			gicc = acpi_cpu_get_madt_gicc(cpu);
+			if (gicc->efficiency_class == class)
+				per_cpu(efficiency_class, cpu) = index;
+		}
+		index++;
+	}
+	cppc_cpufreq_driver.register_em = cppc_cpufreq_register_em;
+}
+
+#else
+static void populate_efficiency_class(void)
+{
+}
+#endif
 
 static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 {
@@ -454,12 +562,6 @@ static struct cppc_cpudata *cppc_cpufreq_get_cpu_data(unsigned int cpu)
 		goto free_mask;
 	}
 
-	/* Convert the lowest and nominal freq from MHz to KHz */
-	cpu_data->perf_caps.lowest_freq *= 1000;
-	cpu_data->perf_caps.nominal_freq *= 1000;
-
-	list_add(&cpu_data->node, &cpu_data_list);
-
 	return cpu_data;
 
 free_mask:
@@ -474,7 +576,6 @@ 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;
@@ -499,20 +600,17 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	 * Set min to lowest nonlinear perf to avoid any efficiency penalty (see
 	 * Section 8.4.7.1.1.5 of ACPI 6.1 spec)
 	 */
-	policy->min = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->lowest_nonlinear_perf);
-	policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-					       caps->nominal_perf);
+	policy->min = cppc_perf_to_khz(caps, caps->lowest_nonlinear_perf);
+	policy->max = cppc_perf_to_khz(caps, policy->boost_enabled ?
+						caps->highest_perf : caps->nominal_perf);
 
 	/*
 	 * Set cpuinfo.min_freq to Lowest to make the full range of performance
 	 * available if userspace wants to use any perf between lowest & lowest
 	 * nonlinear perf
 	 */
-	policy->cpuinfo.min_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->lowest_perf);
-	policy->cpuinfo.max_freq = cppc_cpufreq_perf_to_khz(cpu_data,
-							    caps->nominal_perf);
+	policy->cpuinfo.min_freq = cppc_perf_to_khz(caps, caps->lowest_perf);
+	policy->cpuinfo.max_freq = policy->max;
 
 	policy->transition_delay_us = cppc_cpufreq_get_transition_delay_us(cpu);
 	policy->shared_type = cpu_data->shared_type;
@@ -537,15 +635,18 @@ static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto out;
 	}
 
+	policy->fast_switch_possible = cppc_allow_fast_switch();
+	policy->dvfs_possible_from_any_cpu = true;
+
 	/*
 	 * If 'highest_perf' is greater than 'nominal_perf', we assume CPU Boost
 	 * is supported.
 	 */
 	if (caps->highest_perf > caps->nominal_perf)
-		boost_supported = true;
+		policy->boost_supported = true;
 
 	/* Set policy->cur to max now. The governors will adjust later. */
-	policy->cur = cppc_cpufreq_perf_to_khz(cpu_data, caps->highest_perf);
+	policy->cur = cppc_perf_to_khz(caps, caps->highest_perf);
 	cpu_data->perf_ctrls.desired_perf =  caps->highest_perf;
 
 	ret = cppc_set_perf(cpu, &cpu_data->perf_ctrls);
@@ -563,7 +664,7 @@ out:
 	return ret;
 }
 
-static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+static void 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;
@@ -580,7 +681,6 @@ static int cppc_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 			 caps->lowest_perf, cpu, ret);
 
 	cppc_cpufreq_put_cpu_data(policy);
-	return 0;
 }
 
 static inline u64 get_delta(u64 t1, u64 t0)
@@ -591,8 +691,7 @@ static inline u64 get_delta(u64 t1, u64 t0)
 	return (u32)t1 - (u32)t0;
 }
 
-static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
-				 struct cppc_perf_fb_ctrs *fb_ctrs_t0,
+static int cppc_perf_from_fbctrs(struct cppc_perf_fb_ctrs *fb_ctrs_t0,
 				 struct cppc_perf_fb_ctrs *fb_ctrs_t1)
 {
 	u64 delta_reference, delta_delivered;
@@ -605,37 +704,71 @@ static int cppc_perf_from_fbctrs(struct cppc_cpudata *cpu_data,
 	delta_delivered = get_delta(fb_ctrs_t1->delivered,
 				    fb_ctrs_t0->delivered);
 
-	/* Check to avoid divide-by zero and invalid delivered_perf */
+	/*
+	 * Avoid divide-by zero and unchanged feedback counters.
+	 * Leave it for callers to handle.
+	 */
 	if (!delta_reference || !delta_delivered)
-		return cpu_data->perf_ctrls.desired_perf;
+		return 0;
 
 	return (reference_perf * delta_delivered) / delta_reference;
 }
 
+static int cppc_get_perf_ctrs_sample(int cpu,
+				     struct cppc_perf_fb_ctrs *fb_ctrs_t0,
+				     struct cppc_perf_fb_ctrs *fb_ctrs_t1)
+{
+	int ret;
+
+	ret = cppc_get_perf_ctrs(cpu, fb_ctrs_t0);
+	if (ret)
+		return ret;
+
+	udelay(2); /* 2usec delay between sampling */
+
+	return cppc_get_perf_ctrs(cpu, fb_ctrs_t1);
+}
+
 static unsigned int cppc_cpufreq_get_rate(unsigned int cpu)
 {
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(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;
+	struct cppc_cpudata *cpu_data;
 	u64 delivered_perf;
 	int ret;
 
-	cpufreq_cpu_put(policy);
+	if (!policy)
+		return 0;
 
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t0);
-	if (ret)
-		return ret;
+	cpu_data = policy->driver_data;
 
-	udelay(2); /* 2usec delay between sampling */
+	ret = cppc_get_perf_ctrs_sample(cpu, &fb_ctrs_t0, &fb_ctrs_t1);
+	if (ret) {
+		if (ret == -EFAULT)
+			/* Any of the associated CPPC regs is 0. */
+			goto out_invalid_counters;
+		else
+			return 0;
+	}
 
-	ret = cppc_get_perf_ctrs(cpu, &fb_ctrs_t1);
-	if (ret)
-		return ret;
+	delivered_perf = cppc_perf_from_fbctrs(&fb_ctrs_t0, &fb_ctrs_t1);
+	if (!delivered_perf)
+		goto out_invalid_counters;
 
-	delivered_perf = cppc_perf_from_fbctrs(cpu_data, &fb_ctrs_t0,
-					       &fb_ctrs_t1);
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 
-	return cppc_cpufreq_perf_to_khz(cpu_data, delivered_perf);
+out_invalid_counters:
+	/*
+	 * Feedback counters could be unchanged or 0 when a cpu enters a
+	 * low-power idle state, e.g. clock-gated or power-gated.
+	 * Use desired perf for reflecting frequency.  Get the latest register
+	 * value first as some platforms may update the actual delivered perf
+	 * there; if failed, resort to the cached desired perf.
+	 */
+	if (cppc_get_desired_perf(cpu, &delivered_perf))
+		delivered_perf = cpu_data->perf_ctrls.desired_perf;
+
+	return cppc_perf_to_khz(&cpu_data->perf_caps, delivered_perf);
 }
 
 static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
@@ -644,17 +777,10 @@ static int cppc_cpufreq_set_boost(struct cpufreq_policy *policy, int state)
 	struct cppc_perf_caps *caps = &cpu_data->perf_caps;
 	int ret;
 
-	if (!boost_supported) {
-		pr_err("BOOST not supported by CPU or firmware\n");
-		return -EINVAL;
-	}
-
 	if (state)
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->highest_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->highest_perf);
 	else
-		policy->max = cppc_cpufreq_perf_to_khz(cpu_data,
-						       caps->nominal_perf);
+		policy->max = cppc_perf_to_khz(caps, caps->nominal_perf);
 	policy->cpuinfo.max_freq = policy->max;
 
 	ret = freq_qos_update_request(policy->max_freq_req, policy->max);
@@ -670,18 +796,128 @@ static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
 
 	return cpufreq_show_cpus(cpu_data->shared_cpu_map, buf);
 }
+
+static ssize_t show_auto_select(struct cpufreq_policy *policy, char *buf)
+{
+	bool val;
+	int ret;
+
+	ret = cppc_get_auto_sel(policy->cpu, &val);
+
+	/* show "<unsupported>" when this register is not supported by cpc */
+	if (ret == -EOPNOTSUPP)
+		return sysfs_emit(buf, "<unsupported>\n");
+
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%d\n", val);
+}
+
+static ssize_t store_auto_select(struct cpufreq_policy *policy,
+				 const char *buf, size_t count)
+{
+	bool val;
+	int ret;
+
+	ret = kstrtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	ret = cppc_set_auto_sel(policy->cpu, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t show_auto_act_window(struct cpufreq_policy *policy, char *buf)
+{
+	u64 val;
+	int ret;
+
+	ret = cppc_get_auto_act_window(policy->cpu, &val);
+
+	/* show "<unsupported>" when this register is not supported by cpc */
+	if (ret == -EOPNOTSUPP)
+		return sysfs_emit(buf, "<unsupported>\n");
+
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu\n", val);
+}
+
+static ssize_t store_auto_act_window(struct cpufreq_policy *policy,
+				     const char *buf, size_t count)
+{
+	u64 usec;
+	int ret;
+
+	ret = kstrtou64(buf, 0, &usec);
+	if (ret)
+		return ret;
+
+	ret = cppc_set_auto_act_window(policy->cpu, usec);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
+static ssize_t show_energy_performance_preference_val(struct cpufreq_policy *policy, char *buf)
+{
+	u64 val;
+	int ret;
+
+	ret = cppc_get_epp_perf(policy->cpu, &val);
+
+	/* show "<unsupported>" when this register is not supported by cpc */
+	if (ret == -EOPNOTSUPP)
+		return sysfs_emit(buf, "<unsupported>\n");
+
+	if (ret)
+		return ret;
+
+	return sysfs_emit(buf, "%llu\n", val);
+}
+
+static ssize_t store_energy_performance_preference_val(struct cpufreq_policy *policy,
+						       const char *buf, size_t count)
+{
+	u64 val;
+	int ret;
+
+	ret = kstrtou64(buf, 0, &val);
+	if (ret)
+		return ret;
+
+	ret = cppc_set_epp(policy->cpu, val);
+	if (ret)
+		return ret;
+
+	return count;
+}
+
 cpufreq_freq_attr_ro(freqdomain_cpus);
+cpufreq_freq_attr_rw(auto_select);
+cpufreq_freq_attr_rw(auto_act_window);
+cpufreq_freq_attr_rw(energy_performance_preference_val);
 
 static struct freq_attr *cppc_cpufreq_attr[] = {
 	&freqdomain_cpus,
+	&auto_select,
+	&auto_act_window,
+	&energy_performance_preference_val,
 	NULL,
 };
 
 static struct cpufreq_driver cppc_cpufreq_driver = {
-	.flags = CPUFREQ_CONST_LOOPS,
+	.flags = CPUFREQ_CONST_LOOPS | CPUFREQ_NEED_UPDATE_LIMITS,
 	.verify = cppc_verify_policy,
 	.target = cppc_cpufreq_set_target,
 	.get = cppc_cpufreq_get_rate,
+	.fast_switch = cppc_cpufreq_fast_switch,
 	.init = cppc_cpufreq_cpu_init,
 	.exit = cppc_cpufreq_cpu_exit,
 	.set_boost = cppc_cpufreq_set_boost,
@@ -689,62 +925,15 @@ static struct cpufreq_driver cppc_cpufreq_driver = {
 	.name = "cppc_cpufreq",
 };
 
-/*
- * HISI platform does not support delivered performance counter and
- * reference performance counter. It can calculate the performance using the
- * platform specific mechanism. We reuse the desired performance register to
- * store the real performance calculated by the platform.
- */
-static unsigned int hisi_cppc_cpufreq_get_rate(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	struct cppc_cpudata *cpu_data = policy->driver_data;
-	u64 desired_perf;
-	int ret;
-
-	cpufreq_cpu_put(policy);
-
-	ret = cppc_get_desired_perf(cpu, &desired_perf);
-	if (ret < 0)
-		return -EIO;
-
-	return cppc_cpufreq_perf_to_khz(cpu_data, desired_perf);
-}
-
-static void cppc_check_hisi_workaround(void)
-{
-	struct acpi_table_header *tbl;
-	acpi_status status = AE_OK;
-	int i;
-
-	status = acpi_get_table(ACPI_SIG_PCCT, 0, &tbl);
-	if (ACPI_FAILURE(status) || !tbl)
-		return;
-
-	for (i = 0; i < ARRAY_SIZE(wa_info); i++) {
-		if (!memcmp(wa_info[i].oem_id, tbl->oem_id, ACPI_OEM_ID_SIZE) &&
-		    !memcmp(wa_info[i].oem_table_id, tbl->oem_table_id, ACPI_OEM_TABLE_ID_SIZE) &&
-		    wa_info[i].oem_revision == tbl->oem_revision) {
-			/* Overwrite the get() callback */
-			cppc_cpufreq_driver.get = hisi_cppc_cpufreq_get_rate;
-			break;
-		}
-	}
-
-	acpi_put_table(tbl);
-}
-
 static int __init cppc_cpufreq_init(void)
 {
 	int ret;
 
-	if ((acpi_disabled) || !acpi_cpc_valid())
+	if (!acpi_cpc_valid())
 		return -ENODEV;
 
-	INIT_LIST_HEAD(&cpu_data_list);
-
-	cppc_check_hisi_workaround();
 	cppc_freq_invariance_init();
+	populate_efficiency_class();
 
 	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
 	if (ret)
@@ -753,24 +942,10 @@ static int __init cppc_cpufreq_init(void)
 	return ret;
 }
 
-static inline void free_cpu_data(void)
-{
-	struct cppc_cpudata *iter, *tmp;
-
-	list_for_each_entry_safe(iter, tmp, &cpu_data_list, node) {
-		free_cpumask_var(iter->shared_cpu_map);
-		list_del(&iter->node);
-		kfree(iter);
-	}
-
-}
-
 static void __exit cppc_cpufreq_exit(void)
 {
 	cpufreq_unregister_driver(&cppc_cpufreq_driver);
 	cppc_freq_invariance_exit();
-
-	free_cpu_data();
 }
 
 module_exit(cppc_cpufreq_exit);