Merge back cpufreq material for v5.2.

7 files changed, 148 insertions, 42 deletions

diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index a303fd0e108c..c73d3a62799a 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -181,7 +181,7 @@ void acpi_processor_ppc_has_changed(struct acpi_processor *pr, int event_flag)
 			acpi_processor_ppc_ost(pr->handle, 0);
 	}
 	if (ret >= 0)
-		cpufreq_update_policy(pr->id);
+		cpufreq_update_limits(pr->id);
 }
 
 int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
diff --git a/drivers/cpufreq/amd_freq_sensitivity.c b/drivers/cpufreq/amd_freq_sensitivity.c
index 4ac7c3cf34be..6927a8c0e748 100644
--- a/drivers/cpufreq/amd_freq_sensitivity.c
+++ b/drivers/cpufreq/amd_freq_sensitivity.c
@@ -124,7 +124,7 @@ static int __init amd_freq_sensitivity_init(void)
 			PCI_DEVICE_ID_AMD_KERNCZ_SMBUS, NULL);
 
 	if (!pcidev) {
-		if (!static_cpu_has(X86_FEATURE_PROC_FEEDBACK))
+		if (!boot_cpu_has(X86_FEATURE_PROC_FEEDBACK))
 			return -ENODEV;
 	}
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index e10922709d13..f3f79266ab48 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -34,11 +34,6 @@
 
 static LIST_HEAD(cpufreq_policy_list);
 
-static inline bool policy_is_inactive(struct cpufreq_policy *policy)
-{
-	return cpumask_empty(policy->cpus);
-}
-
 /* Macros to iterate over CPU policies */
 #define for_each_suitable_policy(__policy, __active)			 \
 	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list) \
@@ -250,6 +245,51 @@ void cpufreq_cpu_put(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
 
+/**
+ * cpufreq_cpu_release - Unlock a policy and decrement its usage counter.
+ * @policy: cpufreq policy returned by cpufreq_cpu_acquire().
+ */
+void cpufreq_cpu_release(struct cpufreq_policy *policy)
+{
+	if (WARN_ON(!policy))
+		return;
+
+	lockdep_assert_held(&policy->rwsem);
+
+	up_write(&policy->rwsem);
+
+	cpufreq_cpu_put(policy);
+}
+
+/**
+ * cpufreq_cpu_acquire - Find policy for a CPU, mark it as busy and lock it.
+ * @cpu: CPU to find the policy for.
+ *
+ * Call cpufreq_cpu_get() to get a reference on the cpufreq policy for @cpu and
+ * if the policy returned by it is not NULL, acquire its rwsem for writing.
+ * Return the policy if it is active or release it and return NULL otherwise.
+ *
+ * The policy returned by this function has to be released with the help of
+ * cpufreq_cpu_release() in order to release its rwsem and balance its usage
+ * counter properly.
+ */
+struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+
+	if (!policy)
+		return NULL;
+
+	down_write(&policy->rwsem);
+
+	if (policy_is_inactive(policy)) {
+		cpufreq_cpu_release(policy);
+		return NULL;
+	}
+
+	return policy;
+}
+
 /*********************************************************************
  *            EXTERNALLY AFFECTING FREQUENCY CHANGES                 *
  *********************************************************************/
@@ -669,9 +709,6 @@ static ssize_t show_scaling_cur_freq(struct cpufreq_policy *policy, char *buf)
 	return ret;
 }
 
-static int cpufreq_set_policy(struct cpufreq_policy *policy,
-				struct cpufreq_policy *new_policy);
-
 /**
  * cpufreq_per_cpu_attr_write() / store_##file_name() - sysfs write access
  */
@@ -2229,8 +2266,8 @@ EXPORT_SYMBOL(cpufreq_get_policy);
  *
  * The cpuinfo part of @policy is not updated by this function.
  */
-static int cpufreq_set_policy(struct cpufreq_policy *policy,
-			      struct cpufreq_policy *new_policy)
+int cpufreq_set_policy(struct cpufreq_policy *policy,
+		       struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
 	int ret;
@@ -2337,17 +2374,12 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
  */
 void cpufreq_update_policy(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
 	struct cpufreq_policy new_policy;
 
 	if (!policy)
 		return;
 
-	down_write(&policy->rwsem);
-
-	if (policy_is_inactive(policy))
-		goto unlock;
-
 	/*
 	 * BIOS might change freq behind our back
 	 * -> ask driver for current freq and notify governors about a change
@@ -2364,12 +2396,26 @@ void cpufreq_update_policy(unsigned int cpu)
 	cpufreq_set_policy(policy, &new_policy);
 
 unlock:
-	up_write(&policy->rwsem);
-
-	cpufreq_cpu_put(policy);
+	cpufreq_cpu_release(policy);
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
 
+/**
+ * cpufreq_update_limits - Update policy limits for a given CPU.
+ * @cpu: CPU to update the policy limits for.
+ *
+ * Invoke the driver's ->update_limits callback if present or call
+ * cpufreq_update_policy() for @cpu.
+ */
+void cpufreq_update_limits(unsigned int cpu)
+{
+	if (cpufreq_driver->update_limits)
+		cpufreq_driver->update_limits(cpu);
+	else
+		cpufreq_update_policy(cpu);
+}
+EXPORT_SYMBOL_GPL(cpufreq_update_limits);
+
 /*********************************************************************
  *               BOOST						     *
  *********************************************************************/
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 2986119dd31f..34b54df41aaa 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -179,6 +179,7 @@ struct vid_data {
  *			based on the MSR_IA32_MISC_ENABLE value and whether or
  *			not the maximum reported turbo P-state is different from
  *			the maximum reported non-turbo one.
+ * @turbo_disabled_mf:	The @turbo_disabled value reflected by cpuinfo.max_freq.
  * @min_perf_pct:	Minimum capacity limit in percent of the maximum turbo
  *			P-state capacity.
  * @max_perf_pct:	Maximum capacity limit in percent of the maximum turbo
@@ -187,6 +188,7 @@ struct vid_data {
 struct global_params {
 	bool no_turbo;
 	bool turbo_disabled;
+	bool turbo_disabled_mf;
 	int max_perf_pct;
 	int min_perf_pct;
 };
@@ -525,7 +527,7 @@ static s16 intel_pstate_get_epb(struct cpudata *cpu_data)
 	u64 epb;
 	int ret;
 
-	if (!static_cpu_has(X86_FEATURE_EPB))
+	if (!boot_cpu_has(X86_FEATURE_EPB))
 		return -ENXIO;
 
 	ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
@@ -539,7 +541,7 @@ static s16 intel_pstate_get_epp(struct cpudata *cpu_data, u64 hwp_req_data)
 {
 	s16 epp;
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		/*
 		 * When hwp_req_data is 0, means that caller didn't read
 		 * MSR_HWP_REQUEST, so need to read and get EPP.
@@ -564,7 +566,7 @@ static int intel_pstate_set_epb(int cpu, s16 pref)
 	u64 epb;
 	int ret;
 
-	if (!static_cpu_has(X86_FEATURE_EPB))
+	if (!boot_cpu_has(X86_FEATURE_EPB))
 		return -ENXIO;
 
 	ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
@@ -612,7 +614,7 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 	if (epp < 0)
 		return epp;
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		if (epp == HWP_EPP_PERFORMANCE)
 			return 1;
 		if (epp <= HWP_EPP_BALANCE_PERFORMANCE)
@@ -621,7 +623,7 @@ static int intel_pstate_get_energy_pref_index(struct cpudata *cpu_data)
 			return 3;
 		else
 			return 4;
-	} else if (static_cpu_has(X86_FEATURE_EPB)) {
+	} else if (boot_cpu_has(X86_FEATURE_EPB)) {
 		/*
 		 * Range:
 		 *	0x00-0x03	:	Performance
@@ -649,7 +651,7 @@ static int intel_pstate_set_energy_pref_index(struct cpudata *cpu_data,
 
 	mutex_lock(&intel_pstate_limits_lock);
 
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		u64 value;
 
 		ret = rdmsrl_on_cpu(cpu_data->cpu, MSR_HWP_REQUEST, &value);
@@ -824,7 +826,7 @@ static void intel_pstate_hwp_set(unsigned int cpu)
 		epp = cpu_data->epp_powersave;
 	}
 update_epp:
-	if (static_cpu_has(X86_FEATURE_HWP_EPP)) {
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP)) {
 		value &= ~GENMASK_ULL(31, 24);
 		value |= (u64)epp << 24;
 	} else {
@@ -849,7 +851,7 @@ static void intel_pstate_hwp_force_min_perf(int cpu)
 	value |= HWP_MIN_PERF(min_perf);
 
 	/* Set EPP/EPB to min */
-	if (static_cpu_has(X86_FEATURE_HWP_EPP))
+	if (boot_cpu_has(X86_FEATURE_HWP_EPP))
 		value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE);
 	else
 		intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE);
@@ -897,6 +899,48 @@ static void intel_pstate_update_policies(void)
 		cpufreq_update_policy(cpu);
 }
 
+static void intel_pstate_update_max_freq(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_acquire(cpu);
+	struct cpufreq_policy new_policy;
+	struct cpudata *cpudata;
+
+	if (!policy)
+		return;
+
+	cpudata = all_cpu_data[cpu];
+	policy->cpuinfo.max_freq = global.turbo_disabled_mf ?
+			cpudata->pstate.max_freq : cpudata->pstate.turbo_freq;
+
+	memcpy(&new_policy, policy, sizeof(*policy));
+	new_policy.max = min(policy->user_policy.max, policy->cpuinfo.max_freq);
+	new_policy.min = min(policy->user_policy.min, new_policy.max);
+
+	cpufreq_set_policy(policy, &new_policy);
+
+	cpufreq_cpu_release(policy);
+}
+
+static void intel_pstate_update_limits(unsigned int cpu)
+{
+	mutex_lock(&intel_pstate_driver_lock);
+
+	update_turbo_state();
+	/*
+	 * If turbo has been turned on or off globally, policy limits for
+	 * all CPUs need to be updated to reflect that.
+	 */
+	if (global.turbo_disabled_mf != global.turbo_disabled) {
+		global.turbo_disabled_mf = global.turbo_disabled;
+		for_each_possible_cpu(cpu)
+			intel_pstate_update_max_freq(cpu);
+	} else {
+		cpufreq_update_policy(cpu);
+	}
+
+	mutex_unlock(&intel_pstate_driver_lock);
+}
+
 /************************** sysfs begin ************************/
 #define show_one(file_name, object)					\
 	static ssize_t show_##file_name					\
@@ -1197,7 +1241,7 @@ static void __init intel_pstate_sysfs_expose_params(void)
 static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
 	/* First disable HWP notification interrupt as we don't process them */
-	if (static_cpu_has(X86_FEATURE_HWP_NOTIFY))
+	if (boot_cpu_has(X86_FEATURE_HWP_NOTIFY))
 		wrmsrl_on_cpu(cpudata->cpu, MSR_HWP_INTERRUPT, 0x00);
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
@@ -2138,6 +2182,7 @@ static int __intel_pstate_cpu_init(struct cpufreq_policy *policy)
 	/* cpuinfo and default policy values */
 	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * cpu->pstate.scaling;
 	update_turbo_state();
+	global.turbo_disabled_mf = global.turbo_disabled;
 	policy->cpuinfo.max_freq = global.turbo_disabled ?
 			cpu->pstate.max_pstate : cpu->pstate.turbo_pstate;
 	policy->cpuinfo.max_freq *= cpu->pstate.scaling;
@@ -2182,6 +2227,7 @@ static struct cpufreq_driver intel_pstate = {
 	.init		= intel_pstate_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_pstate_stop_cpu,
+	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_pstate",
 };
 
@@ -2316,6 +2362,7 @@ static struct cpufreq_driver intel_cpufreq = {
 	.init		= intel_cpufreq_cpu_init,
 	.exit		= intel_pstate_cpu_exit,
 	.stop_cpu	= intel_cpufreq_stop_cpu,
+	.update_limits	= intel_pstate_update_limits,
 	.name		= "intel_cpufreq",
 };
 
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index fb77b39a4ce3..3c12e03fa343 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1178,7 +1178,7 @@ static int powernowk8_init(void)
 	unsigned int i, supported_cpus = 0;
 	int ret;
 
-	if (static_cpu_has(X86_FEATURE_HW_PSTATE)) {
+	if (boot_cpu_has(X86_FEATURE_HW_PSTATE)) {
 		__request_acpi_cpufreq();
 		return -ENODEV;
 	}
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index b160e98076e3..684caf067003 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -178,6 +178,11 @@ static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { }
 #endif
 
+static inline bool policy_is_inactive(struct cpufreq_policy *policy)
+{
+	return cpumask_empty(policy->cpus);
+}
+
 static inline bool policy_is_shared(struct cpufreq_policy *policy)
 {
 	return cpumask_weight(policy->cpus) > 1;
@@ -193,8 +198,14 @@ unsigned int cpufreq_quick_get_max(unsigned int cpu);
 void disable_cpufreq(void);
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
+
+struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu);
+void cpufreq_cpu_release(struct cpufreq_policy *policy);
 int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
+int cpufreq_set_policy(struct cpufreq_policy *policy,
+		       struct cpufreq_policy *new_policy);
 void cpufreq_update_policy(unsigned int cpu);
+void cpufreq_update_limits(unsigned int cpu);
 bool have_governor_per_policy(void);
 struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
@@ -322,6 +333,9 @@ struct cpufreq_driver {
 	/* should be defined, if possible */
 	unsigned int	(*get)(unsigned int cpu);
 
+	/* Called to update policy limits on firmware notifications. */
+	void		(*update_limits)(unsigned int cpu);
+
 	/* optional */
 	int		(*bios_limit)(int cpu, unsigned int *limit);
 
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 5c41ea367422..b3a878aa593d 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -13,6 +13,8 @@
 #include <linux/sched/cpufreq.h>
 #include <trace/events/power.h>
 
+#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
+
 struct sugov_tunables {
 	struct gov_attr_set	attr_set;
 	unsigned int		rate_limit_us;
@@ -51,7 +53,6 @@ struct sugov_cpu {
 	u64			last_update;
 
 	unsigned long		bw_dl;
-	unsigned long		min;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -291,8 +292,8 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
  *
  * The IO wait boost of a task is disabled after a tick since the last update
  * of a CPU. If a new IO wait boost is requested after more then a tick, then
- * we enable the boost starting from the minimum frequency, which improves
- * energy efficiency by ignoring sporadic wakeups from IO.
+ * we enable the boost starting from IOWAIT_BOOST_MIN, which improves energy
+ * efficiency by ignoring sporadic wakeups from IO.
  */
 static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 			       bool set_iowait_boost)
@@ -303,7 +304,7 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
 	if (delta_ns <= TICK_NSEC)
 		return false;
 
-	sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
+	sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
 	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
 	return true;
@@ -317,8 +318,9 @@ static bool sugov_iowait_reset(struct sugov_cpu *sg_cpu, u64 time,
  *
  * Each time a task wakes up after an IO operation, the CPU utilization can be
  * boosted to a certain utilization which doubles at each "frequent and
- * successive" wakeup from IO, ranging from the utilization of the minimum
- * OPP to the utilization of the maximum OPP.
+ * successive" wakeup from IO, ranging from IOWAIT_BOOST_MIN to the utilization
+ * of the maximum OPP.
+ *
  * To keep doubling, an IO boost has to be requested at least once per tick,
  * otherwise we restart from the utilization of the minimum OPP.
  */
@@ -349,7 +351,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
 	}
 
 	/* First wakeup after IO: start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->min;
+	sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
 }
 
 /**
@@ -389,7 +391,7 @@ static unsigned long sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
 		 * No boost pending; reduce the boost value.
 		 */
 		sg_cpu->iowait_boost >>= 1;
-		if (sg_cpu->iowait_boost < sg_cpu->min) {
+		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
 			return util;
 		}
@@ -826,9 +828,6 @@ static int sugov_start(struct cpufreq_policy *policy)
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->min			=
-			(SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
-			policy->cpuinfo.max_freq;
 	}
 
 	for_each_cpu(cpu, policy->cpus) {