1 files changed, 373 insertions, 48 deletions

diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index a38219527637..cde1a4ecaa6e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -10,6 +10,8 @@
  * of the License.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
@@ -39,6 +41,10 @@
 #define ATOM_TURBO_RATIOS	0x66c
 #define ATOM_TURBO_VIDS		0x66d
 
+#ifdef CONFIG_ACPI
+#include <acpi/processor.h>
+#endif
+
 #define FRAC_BITS 8
 #define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
 #define fp_toint(X) ((X) >> FRAC_BITS)
@@ -64,6 +70,25 @@ static inline int ceiling_fp(int32_t x)
 	return ret;
 }
 
+/**
+ * struct sample -	Store performance sample
+ * @core_pct_busy:	Ratio of APERF/MPERF in percent, which is actual
+ *			performance during last sample period
+ * @busy_scaled:	Scaled busy value which is used to calculate next
+ *			P state. This can be different than core_pct_busy
+ *			to account for cpu idle period
+ * @aperf:		Difference of actual performance frequency clock count
+ *			read from APERF MSR between last and current sample
+ * @mperf:		Difference of maximum performance frequency clock count
+ *			read from MPERF MSR between last and current sample
+ * @tsc:		Difference of time stamp counter between last and
+ *			current sample
+ * @freq:		Effective frequency calculated from APERF/MPERF
+ * @time:		Current time from scheduler
+ *
+ * This structure is used in the cpudata structure to store performance sample
+ * data for choosing next P State.
+ */
 struct sample {
 	int32_t core_pct_busy;
 	int32_t busy_scaled;
@@ -74,6 +99,20 @@ struct sample {
 	u64 time;
 };
 
+/**
+ * struct pstate_data - Store P state data
+ * @current_pstate:	Current requested P state
+ * @min_pstate:		Min P state possible for this platform
+ * @max_pstate:		Max P state possible for this platform
+ * @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
+ * @turbo_pstate:	Max Turbo P state possible for this platform
+ *
+ * Stores the per cpu model P state limits and current P state.
+ */
 struct pstate_data {
 	int	current_pstate;
 	int	min_pstate;
@@ -83,6 +122,19 @@ struct pstate_data {
 	int	turbo_pstate;
 };
 
+/**
+ * struct vid_data -	Stores voltage information data
+ * @min:		VID data for this platform corresponding to
+ *			the lowest P state
+ * @max:		VID data corresponding to the highest P State.
+ * @turbo:		VID data for turbo P state
+ * @ratio:		Ratio of (vid max - vid min) /
+ *			(max P state - Min P State)
+ *
+ * Stores the voltage data for DVFS (Dynamic Voltage and Frequency Scaling)
+ * This data is used in Atom platforms, where in addition to target P state,
+ * the voltage data needs to be specified to select next P State.
+ */
 struct vid_data {
 	int min;
 	int max;
@@ -90,6 +142,18 @@ struct vid_data {
 	int32_t ratio;
 };
 
+/**
+ * struct _pid -	Stores PID data
+ * @setpoint:		Target set point for busyness or performance
+ * @integral:		Storage for accumulated error values
+ * @p_gain:		PID proportional gain
+ * @i_gain:		PID integral gain
+ * @d_gain:		PID derivative gain
+ * @deadband:		PID deadband
+ * @last_err:		Last error storage for integral part of PID calculation
+ *
+ * Stores PID coefficients and last error for PID controller.
+ */
 struct _pid {
 	int setpoint;
 	int32_t integral;
@@ -100,6 +164,25 @@ struct _pid {
 	int32_t last_err;
 };
 
+/**
+ * struct cpudata -	Per CPU instance data storage
+ * @cpu:		CPU number for this instance data
+ * @update_util:	CPUFreq utility callback information
+ * @pstate:		Stores P state limits for this CPU
+ * @vid:		Stores VID limits for this CPU
+ * @pid:		Stores PID parameters for this CPU
+ * @last_sample_time:	Last Sample time
+ * @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
+ * @acpi_perf_data:	Stores ACPI perf information read from _PSS
+ * @valid_pss_table:	Set to true for valid ACPI _PSS entries found
+ *
+ * This structure stores per CPU instance data for all CPUs.
+ */
 struct cpudata {
 	int cpu;
 
@@ -115,9 +198,26 @@ struct cpudata {
 	u64	prev_tsc;
 	u64	prev_cummulative_iowait;
 	struct sample sample;
+#ifdef CONFIG_ACPI
+	struct acpi_processor_performance acpi_perf_data;
+	bool valid_pss_table;
+#endif
 };
 
 static struct cpudata **all_cpu_data;
+
+/**
+ * struct pid_adjust_policy - Stores static PID configuration data
+ * @sample_rate_ms:	PID calculation sample rate in ms
+ * @sample_rate_ns:	Sample rate calculation in ns
+ * @deadband:		PID deadband
+ * @setpoint:		PID Setpoint
+ * @p_gain_pct:		PID proportional gain
+ * @i_gain_pct:		PID integral gain
+ * @d_gain_pct:		PID derivative gain
+ *
+ * Stores per CPU model static PID configuration data.
+ */
 struct pstate_adjust_policy {
 	int sample_rate_ms;
 	s64 sample_rate_ns;
@@ -128,6 +228,20 @@ struct pstate_adjust_policy {
 	int i_gain_pct;
 };
 
+/**
+ * struct pstate_funcs - Per CPU model specific callbacks
+ * @get_max:		Callback to get maximum non turbo effective P state
+ * @get_max_physical:	Callback to get maximum non turbo physical P state
+ * @get_min:		Callback to get minimum P state
+ * @get_turbo:		Callback to get turbo P state
+ * @get_scaling:	Callback to get frequency scaling factor
+ * @get_val:		Callback to convert P state to actual MSR write value
+ * @get_vid:		Callback to get VID data for Atom platforms
+ * @get_target_pstate:	Callback to a function to calculate next P state to use
+ *
+ * Core and Atom CPU models have different way to get P State limits. This
+ * structure is used to store those callbacks.
+ */
 struct pstate_funcs {
 	int (*get_max)(void);
 	int (*get_max_physical)(void);
@@ -139,6 +253,11 @@ struct pstate_funcs {
 	int32_t (*get_target_pstate)(struct cpudata *);
 };
 
+/**
+ * struct cpu_defaults- Per CPU model default config data
+ * @pid_policy:	PID config data
+ * @funcs:		Callback function data
+ */
 struct cpu_defaults {
 	struct pstate_adjust_policy pid_policy;
 	struct pstate_funcs funcs;
@@ -151,6 +270,37 @@ static struct pstate_adjust_policy pid_params;
 static struct pstate_funcs pstate_funcs;
 static int hwp_active;
 
+#ifdef CONFIG_ACPI
+static bool acpi_ppc;
+#endif
+
+/**
+ * struct perf_limits - Store user and policy limits
+ * @no_turbo:		User requested turbo state from intel_pstate sysfs
+ * @turbo_disabled:	Platform turbo status either from msr
+ *			MSR_IA32_MISC_ENABLE or when maximum available pstate
+ *			matches the maximum turbo pstate
+ * @max_perf_pct:	Effective maximum performance limit in percentage, this
+ *			is minimum of either limits enforced by cpufreq policy
+ *			or limits from user set limits via intel_pstate sysfs
+ * @min_perf_pct:	Effective minimum performance limit in percentage, this
+ *			is maximum of either limits enforced by cpufreq policy
+ *			or limits from user set limits via intel_pstate sysfs
+ * @max_perf:		This is a scaled value between 0 to 255 for max_perf_pct
+ *			This value is used to limit max pstate
+ * @min_perf:		This is a scaled value between 0 to 255 for min_perf_pct
+ *			This value is used to limit min pstate
+ * @max_policy_pct:	The maximum performance in percentage enforced by
+ *			cpufreq setpolicy interface
+ * @max_sysfs_pct:	The maximum performance in percentage enforced by
+ *			intel pstate sysfs interface
+ * @min_policy_pct:	The minimum performance in percentage enforced by
+ *			cpufreq setpolicy interface
+ * @min_sysfs_pct:	The minimum performance in percentage enforced by
+ *			intel pstate sysfs interface
+ *
+ * Storage for user and policy defined limits.
+ */
 struct perf_limits {
 	int no_turbo;
 	int turbo_disabled;
@@ -196,6 +346,124 @@ static struct perf_limits *limits = &performance_limits;
 static struct perf_limits *limits = &powersave_limits;
 #endif
 
+#ifdef CONFIG_ACPI
+
+static bool intel_pstate_get_ppc_enable_status(void)
+{
+	if (acpi_gbl_FADT.preferred_profile == PM_ENTERPRISE_SERVER ||
+	    acpi_gbl_FADT.preferred_profile == PM_PERFORMANCE_SERVER)
+		return true;
+
+	return acpi_ppc;
+}
+
+/*
+ * The max target pstate ratio is a 8 bit value in both PLATFORM_INFO MSR and
+ * in TURBO_RATIO_LIMIT MSR, which pstate driver stores in max_pstate and
+ * max_turbo_pstate fields. The PERF_CTL MSR contains 16 bit value for P state
+ * ratio, out of it only high 8 bits are used. For example 0x1700 is setting
+ * target ratio 0x17. The _PSS control value stores in a format which can be
+ * directly written to PERF_CTL MSR. But in intel_pstate driver this shift
+ * occurs during write to PERF_CTL (E.g. for cores core_set_pstate()).
+ * This function converts the _PSS control value to intel pstate driver format
+ * for comparison and assignment.
+ */
+static int convert_to_native_pstate_format(struct cpudata *cpu, int index)
+{
+	return cpu->acpi_perf_data.states[index].control >> 8;
+}
+
+static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu;
+	int turbo_pss_ctl;
+	int ret;
+	int i;
+
+	if (hwp_active)
+		return;
+
+	if (!intel_pstate_get_ppc_enable_status())
+		return;
+
+	cpu = all_cpu_data[policy->cpu];
+
+	ret = acpi_processor_register_performance(&cpu->acpi_perf_data,
+						  policy->cpu);
+	if (ret)
+		return;
+
+	/*
+	 * Check if the control value in _PSS is for PERF_CTL MSR, which should
+	 * guarantee that the states returned by it map to the states in our
+	 * list directly.
+	 */
+	if (cpu->acpi_perf_data.control_register.space_id !=
+						ACPI_ADR_SPACE_FIXED_HARDWARE)
+		goto err;
+
+	/*
+	 * If there is only one entry _PSS, simply ignore _PSS and continue as
+	 * usual without taking _PSS into account
+	 */
+	if (cpu->acpi_perf_data.state_count < 2)
+		goto err;
+
+	pr_debug("CPU%u - ACPI _PSS perf data\n", policy->cpu);
+	for (i = 0; i < cpu->acpi_perf_data.state_count; i++) {
+		pr_debug("     %cP%d: %u MHz, %u mW, 0x%x\n",
+			 (i == cpu->acpi_perf_data.state ? '*' : ' '), i,
+			 (u32) cpu->acpi_perf_data.states[i].core_frequency,
+			 (u32) cpu->acpi_perf_data.states[i].power,
+			 (u32) cpu->acpi_perf_data.states[i].control);
+	}
+
+	/*
+	 * The _PSS table doesn't contain whole turbo frequency range.
+	 * This just contains +1 MHZ above the max non turbo frequency,
+	 * with control value corresponding to max turbo ratio. But
+	 * when cpufreq set policy is called, it will call with this
+	 * max frequency, which will cause a reduced performance as
+	 * this driver uses real max turbo frequency as the max
+	 * frequency. So correct this frequency in _PSS table to
+	 * correct max turbo frequency based on the turbo ratio.
+	 * Also need to convert to MHz as _PSS freq is in MHz.
+	 */
+	turbo_pss_ctl = convert_to_native_pstate_format(cpu, 0);
+	if (turbo_pss_ctl > cpu->pstate.max_pstate)
+		cpu->acpi_perf_data.states[0].core_frequency =
+					policy->cpuinfo.max_freq / 1000;
+	cpu->valid_pss_table = true;
+	pr_info("_PPC limits will be enforced\n");
+
+	return;
+
+ err:
+	cpu->valid_pss_table = false;
+	acpi_processor_unregister_performance(policy->cpu);
+}
+
+static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu;
+
+	cpu = all_cpu_data[policy->cpu];
+	if (!cpu->valid_pss_table)
+		return;
+
+	acpi_processor_unregister_performance(policy->cpu);
+}
+
+#else
+static void intel_pstate_init_acpi_perf_limits(struct cpufreq_policy *policy)
+{
+}
+
+static void intel_pstate_exit_perf_limits(struct cpufreq_policy *policy)
+{
+}
+#endif
+
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
 	pid->setpoint = int_tofp(setpoint);
@@ -206,17 +474,17 @@ static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 
 static inline void pid_p_gain_set(struct _pid *pid, int percent)
 {
-	pid->p_gain = div_fp(int_tofp(percent), int_tofp(100));
+	pid->p_gain = div_fp(percent, 100);
 }
 
 static inline void pid_i_gain_set(struct _pid *pid, int percent)
 {
-	pid->i_gain = div_fp(int_tofp(percent), int_tofp(100));
+	pid->i_gain = div_fp(percent, 100);
 }
 
 static inline void pid_d_gain_set(struct _pid *pid, int percent)
 {
-	pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
+	pid->d_gain = div_fp(percent, 100);
 }
 
 static signed int pid_calc(struct _pid *pid, int32_t busy)
@@ -318,6 +586,14 @@ static void intel_pstate_hwp_set(const struct cpumask *cpumask)
 	}
 }
 
+static int intel_pstate_hwp_set_policy(struct cpufreq_policy *policy)
+{
+	if (hwp_active)
+		intel_pstate_hwp_set(policy->cpus);
+
+	return 0;
+}
+
 static void intel_pstate_hwp_set_online_cpus(void)
 {
 	get_online_cpus();
@@ -394,7 +670,7 @@ static ssize_t show_turbo_pct(struct kobject *kobj,
 
 	total = cpu->pstate.turbo_pstate - cpu->pstate.min_pstate + 1;
 	no_turbo = cpu->pstate.max_pstate - cpu->pstate.min_pstate + 1;
-	turbo_fp = div_fp(int_tofp(no_turbo), int_tofp(total));
+	turbo_fp = div_fp(no_turbo, total);
 	turbo_pct = 100 - fp_toint(mul_fp(turbo_fp, int_tofp(100)));
 	return sprintf(buf, "%u\n", turbo_pct);
 }
@@ -436,7 +712,7 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 
 	update_turbo_state();
 	if (limits->turbo_disabled) {
-		pr_warn("intel_pstate: Turbo disabled by BIOS or unavailable on processor\n");
+		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
 		return -EPERM;
 	}
 
@@ -465,8 +741,7 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 				   limits->max_perf_pct);
 	limits->max_perf_pct = max(limits->min_perf_pct,
 				   limits->max_perf_pct);
-	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
-				  int_tofp(100));
+	limits->max_perf = div_fp(limits->max_perf_pct, 100);
 
 	if (hwp_active)
 		intel_pstate_hwp_set_online_cpus();
@@ -490,8 +765,7 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 				   limits->min_perf_pct);
 	limits->min_perf_pct = min(limits->max_perf_pct,
 				   limits->min_perf_pct);
-	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
-				  int_tofp(100));
+	limits->min_perf = div_fp(limits->min_perf_pct, 100);
 
 	if (hwp_active)
 		intel_pstate_hwp_set_online_cpus();
@@ -678,6 +952,11 @@ static int core_get_max_pstate(void)
 			if (err)
 				goto skip_tar;
 
+			/* For level 1 and 2, bits[23:16] contain the ratio */
+			if (tdp_ctrl)
+				tdp_ratio >>= 16;
+
+			tdp_ratio &= 0xff; /* ratios are only 8 bits long */
 			if (tdp_ratio - 1 == tar) {
 				max_pstate = tar;
 				pr_debug("max_pstate=TAC %x\n", max_pstate);
@@ -876,8 +1155,8 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 	struct sample *sample = &cpu->sample;
 	int64_t core_pct;
 
-	core_pct = int_tofp(sample->aperf) * int_tofp(100);
-	core_pct = div64_u64(core_pct, int_tofp(sample->mperf));
+	core_pct = sample->aperf * int_tofp(100);
+	core_pct = div64_u64(core_pct, sample->mperf);
 
 	sample->core_pct_busy = (int32_t)core_pct;
 }
@@ -922,8 +1201,15 @@ static inline bool intel_pstate_sample(struct cpudata *cpu, u64 time)
 
 static inline int32_t get_avg_frequency(struct cpudata *cpu)
 {
-	return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf *
-		cpu->pstate.scaling, cpu->sample.mperf);
+	return fp_toint(mul_fp(cpu->sample.core_pct_busy,
+			       int_tofp(cpu->pstate.max_pstate_physical *
+						cpu->pstate.scaling / 100)));
+}
+
+static inline int32_t get_avg_pstate(struct cpudata *cpu)
+{
+	return div64_u64(cpu->pstate.max_pstate_physical * cpu->sample.aperf,
+			 cpu->sample.mperf);
 }
 
 static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
@@ -958,7 +1244,7 @@ static inline int32_t get_target_pstate_use_cpu_load(struct cpudata *cpu)
 	cpu_load = div64_u64(int_tofp(100) * mperf, sample->tsc);
 	cpu->sample.busy_scaled = cpu_load;
 
-	return cpu->pstate.current_pstate - pid_calc(&cpu->pid, cpu_load);
+	return get_avg_pstate(cpu) - pid_calc(&cpu->pid, cpu_load);
 }
 
 static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
@@ -966,8 +1252,6 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
 	u64 duration_ns;
 
-	intel_pstate_calc_busy(cpu);
-
 	/*
 	 * core_busy is the ratio of actual performance to max
 	 * max_pstate is the max non turbo pstate available
@@ -980,8 +1264,8 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	 * specified pstate.
 	 */
 	core_busy = cpu->sample.core_pct_busy;
-	max_pstate = int_tofp(cpu->pstate.max_pstate_physical);
-	current_pstate = int_tofp(cpu->pstate.current_pstate);
+	max_pstate = cpu->pstate.max_pstate_physical;
+	current_pstate = cpu->pstate.current_pstate;
 	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 
 	/*
@@ -992,9 +1276,12 @@ static inline int32_t get_target_pstate_use_performance(struct cpudata *cpu)
 	 */
 	duration_ns = cpu->sample.time - cpu->last_sample_time;
 	if ((s64)duration_ns > pid_params.sample_rate_ns * 3) {
-		sample_ratio = div_fp(int_tofp(pid_params.sample_rate_ns),
-				      int_tofp(duration_ns));
+		sample_ratio = div_fp(pid_params.sample_rate_ns, duration_ns);
 		core_busy = mul_fp(core_busy, sample_ratio);
+	} else {
+		sample_ratio = div_fp(100 * cpu->sample.mperf, cpu->sample.tsc);
+		if (sample_ratio < int_tofp(1))
+			core_busy = 0;
 	}
 
 	cpu->sample.busy_scaled = core_busy;
@@ -1047,8 +1334,11 @@ static void intel_pstate_update_util(struct update_util_data *data, u64 time,
 	if ((s64)delta_ns >= pid_params.sample_rate_ns) {
 		bool sample_taken = intel_pstate_sample(cpu, time);
 
-		if (sample_taken && !hwp_active)
-			intel_pstate_adjust_busy_pstate(cpu);
+		if (sample_taken) {
+			intel_pstate_calc_busy(cpu);
+			if (!hwp_active)
+				intel_pstate_adjust_busy_pstate(cpu);
+		}
 	}
 }
 
@@ -1107,21 +1397,16 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	intel_pstate_busy_pid_reset(cpu);
 
-	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
+	pr_debug("controlling: cpu %d\n", cpunum);
 
 	return 0;
 }
 
 static unsigned int intel_pstate_get(unsigned int cpu_num)
 {
-	struct sample *sample;
-	struct cpudata *cpu;
+	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	cpu = all_cpu_data[cpu_num];
-	if (!cpu)
-		return 0;
-	sample = &cpu->sample;
-	return get_avg_frequency(cpu);
+	return cpu ? get_avg_frequency(cpu) : 0;
 }
 
 static void intel_pstate_set_update_util_hook(unsigned int cpu_num)
@@ -1140,22 +1425,50 @@ static void intel_pstate_clear_update_util_hook(unsigned int cpu)
 	synchronize_sched();
 }
 
+static void intel_pstate_set_performance_limits(struct perf_limits *limits)
+{
+	limits->no_turbo = 0;
+	limits->turbo_disabled = 0;
+	limits->max_perf_pct = 100;
+	limits->max_perf = int_tofp(1);
+	limits->min_perf_pct = 100;
+	limits->min_perf = int_tofp(1);
+	limits->max_policy_pct = 100;
+	limits->max_sysfs_pct = 100;
+	limits->min_policy_pct = 0;
+	limits->min_sysfs_pct = 0;
+}
+
 static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 {
+	struct cpudata *cpu;
+
 	if (!policy->cpuinfo.max_freq)
 		return -ENODEV;
 
 	intel_pstate_clear_update_util_hook(policy->cpu);
 
-	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE &&
-	    policy->max >= policy->cpuinfo.max_freq) {
-		pr_debug("intel_pstate: set performance\n");
+	cpu = all_cpu_data[0];
+	if (cpu->pstate.max_pstate_physical > cpu->pstate.max_pstate) {
+		if (policy->max < policy->cpuinfo.max_freq &&
+		    policy->max > cpu->pstate.max_pstate * cpu->pstate.scaling) {
+			pr_debug("policy->max > max non turbo frequency\n");
+			policy->max = policy->cpuinfo.max_freq;
+		}
+	}
+
+	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
 		limits = &performance_limits;
-		goto out;
+		if (policy->max >= policy->cpuinfo.max_freq) {
+			pr_debug("set performance\n");
+			intel_pstate_set_performance_limits(limits);
+			goto out;
+		}
+	} else {
+		pr_debug("set powersave\n");
+		limits = &powersave_limits;
 	}
 
-	pr_debug("intel_pstate: set powersave\n");
-	limits = &powersave_limits;
 	limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
 	limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
 	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
@@ -1176,16 +1489,13 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 	/* Make sure min_perf_pct <= max_perf_pct */
 	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
 
-	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
-				  int_tofp(100));
-	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
-				  int_tofp(100));
+	limits->min_perf = div_fp(limits->min_perf_pct, 100);
+	limits->max_perf = div_fp(limits->max_perf_pct, 100);
 
  out:
 	intel_pstate_set_update_util_hook(policy->cpu);
 
-	if (hwp_active)
-		intel_pstate_hwp_set(policy->cpus);
+	intel_pstate_hwp_set_policy(policy);
 
 	return 0;
 }
@@ -1206,7 +1516,7 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 	int cpu_num = policy->cpu;
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
+	pr_debug("CPU %d exiting\n", cpu_num);
 
 	intel_pstate_clear_update_util_hook(cpu_num);
 
@@ -1239,18 +1549,28 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	policy->cpuinfo.max_freq =
 		cpu->pstate.turbo_pstate * cpu->pstate.scaling;
+	intel_pstate_init_acpi_perf_limits(policy);
 	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
 	cpumask_set_cpu(policy->cpu, policy->cpus);
 
 	return 0;
 }
 
+static int intel_pstate_cpu_exit(struct cpufreq_policy *policy)
+{
+	intel_pstate_exit_perf_limits(policy);
+
+	return 0;
+}
+
 static struct cpufreq_driver intel_pstate_driver = {
 	.flags		= CPUFREQ_CONST_LOOPS,
 	.verify		= intel_pstate_verify_policy,
 	.setpolicy	= intel_pstate_set_policy,
+	.resume		= intel_pstate_hwp_set_policy,
 	.get		= intel_pstate_get,
 	.init		= intel_pstate_cpu_init,
+	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
 	.name		= "intel_pstate",
 };
@@ -1294,8 +1614,7 @@ static void copy_cpu_funcs(struct pstate_funcs *funcs)
 
 }
 
-#if IS_ENABLED(CONFIG_ACPI)
-#include <acpi/processor.h>
+#ifdef CONFIG_ACPI
 
 static bool intel_pstate_no_acpi_pss(void)
 {
@@ -1451,7 +1770,7 @@ hwp_cpu_matched:
 	if (intel_pstate_platform_pwr_mgmt_exists())
 		return -ENODEV;
 
-	pr_info("Intel P-state driver initializing.\n");
+	pr_info("Intel P-state driver initializing\n");
 
 	all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
 	if (!all_cpu_data)
@@ -1468,7 +1787,7 @@ hwp_cpu_matched:
 	intel_pstate_sysfs_expose_params();
 
 	if (hwp_active)
-		pr_info("intel_pstate: HWP enabled\n");
+		pr_info("HWP enabled\n");
 
 	return rc;
 out:
@@ -1494,13 +1813,19 @@ static int __init intel_pstate_setup(char *str)
 	if (!strcmp(str, "disable"))
 		no_load = 1;
 	if (!strcmp(str, "no_hwp")) {
-		pr_info("intel_pstate: HWP disabled\n");
+		pr_info("HWP disabled\n");
 		no_hwp = 1;
 	}
 	if (!strcmp(str, "force"))
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))
 		hwp_only = 1;
+
+#ifdef CONFIG_ACPI
+	if (!strcmp(str, "support_acpi_ppc"))
+		acpi_ppc = true;
+#endif
+
 	return 0;
 }
 early_param("intel_pstate", intel_pstate_setup);