Merge branches 'pm-em' and 'powercap'

Merge Energy Model and power capping updates for 5.16-rc1:

 - Add support for inefficient operating performance points to the
   Energy Model and modify cpufreq to use them properly (Vincent
   Donnefort).

 - Rearrange the DTPM framework code to simplify it and make it easier
   to follow (Daniel Lezcano).

 - Fix power intialization in DTPM (Daniel Lezcano).

 - Add CPU load consideration when estimating the instaneous power
   consumption in DTPM (Daniel Lezcano).

* pm-em:
  cpufreq: mediatek-hw: Fix cpufreq_table_find_index_dl() call
  PM: EM: Mark inefficiencies in CPUFreq
  cpufreq: Use CPUFREQ_RELATION_E in DVFS governors
  cpufreq: Introducing CPUFREQ_RELATION_E
  cpufreq: Add an interface to mark inefficient frequencies
  cpufreq: Make policy min/max hard requirements
  PM: EM: Allow skipping inefficient states
  PM: EM: Extend em_perf_domain with a flag field
  PM: EM: Mark inefficient states
  PM: EM: Fix inefficient states detection

* powercap:
  powercap/drivers/dtpm: Fix power limit initialization
  powercap/drivers/dtpm: Scale the power with the load
  powercap/drivers/dtpm: Use container_of instead of a private data field
  powercap/drivers/dtpm: Simplify the dtpm table
  powercap/drivers/dtpm: Encapsulate even more the code

drivers/cpufreq/acpi-cpufreq.c

@@ -470,7 +470,8 @@ static unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
 	if (policy->cached_target_freq == target_freq)
 		index = policy->cached_resolved_idx;
 	else
-		index = cpufreq_table_find_index_dl(policy, target_freq);
+		index = cpufreq_table_find_index_dl(policy, target_freq,
+						    false);
 
 	entry = &policy->freq_table[index];
 	next_freq = entry->frequency;

drivers/cpufreq/amd_freq_sensitivity.c

@@ -91,7 +91,8 @@ static unsigned int amd_powersave_bias_target(struct cpufreq_policy *policy,
 			unsigned int index;
 
 			index = cpufreq_table_find_index_h(policy,
-							   policy->cur - 1);
+							   policy->cur - 1,
+							   relation & CPUFREQ_RELATION_E);
 			freq_next = policy->freq_table[index].frequency;
 		}
 

drivers/cpufreq/cpufreq.c

@@ -554,7 +554,7 @@ static unsigned int __resolve_freq(struct cpufreq_policy *policy,
 unsigned int cpufreq_driver_resolve_freq(struct cpufreq_policy *policy,
 					 unsigned int target_freq)
 {
-	return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_L);
+	return __resolve_freq(policy, target_freq, CPUFREQ_RELATION_LE);
 }
 EXPORT_SYMBOL_GPL(cpufreq_driver_resolve_freq);
 
@@ -2260,8 +2260,16 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 	    !(cpufreq_driver->flags & CPUFREQ_NEED_UPDATE_LIMITS))
 		return 0;
 
-	if (cpufreq_driver->target)
+	if (cpufreq_driver->target) {
+		/*
+		 * If the driver hasn't setup a single inefficient frequency,
+		 * it's unlikely it knows how to decode CPUFREQ_RELATION_E.
+		 */
+		if (!policy->efficiencies_available)
+			relation &= ~CPUFREQ_RELATION_E;
+
 		return cpufreq_driver->target(policy, target_freq, relation);
+	}
 
 	if (!cpufreq_driver->target_index)
 		return -EINVAL;
@@ -2523,8 +2531,15 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (ret)
 		return ret;
 
+	/*
+	 * Resolve policy min/max to available frequencies. It ensures
+	 * no frequency resolution will neither overshoot the requested maximum
+	 * nor undershoot the requested minimum.
+	 */
 	policy->min = new_data.min;
 	policy->max = new_data.max;
+	policy->min = __resolve_freq(policy, policy->min, CPUFREQ_RELATION_L);
+	policy->max = __resolve_freq(policy, policy->max, CPUFREQ_RELATION_H);
 	trace_cpu_frequency_limits(policy);
 
 	policy->cached_target_freq = UINT_MAX;

drivers/cpufreq/cpufreq_conservative.c

@@ -111,7 +111,8 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy)
 		if (requested_freq > policy->max)
 			requested_freq = policy->max;
 
-		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_H);
+		__cpufreq_driver_target(policy, requested_freq,
+					CPUFREQ_RELATION_HE);
 		dbs_info->requested_freq = requested_freq;
 		goto out;
 	}
@@ -134,7 +135,8 @@ static unsigned int cs_dbs_update(struct cpufreq_policy *policy)
 		else
 			requested_freq = policy->min;
 
-		__cpufreq_driver_target(policy, requested_freq, CPUFREQ_RELATION_L);
+		__cpufreq_driver_target(policy, requested_freq,
+					CPUFREQ_RELATION_LE);
 		dbs_info->requested_freq = requested_freq;
 	}
 

drivers/cpufreq/cpufreq_ondemand.c

@@ -83,9 +83,11 @@ static unsigned int generic_powersave_bias_target(struct cpufreq_policy *policy,
 	freq_avg = freq_req - freq_reduc;
 
 	/* Find freq bounds for freq_avg in freq_table */
-	index = cpufreq_table_find_index_h(policy, freq_avg);
+	index = cpufreq_table_find_index_h(policy, freq_avg,
+					   relation & CPUFREQ_RELATION_E);
 	freq_lo = freq_table[index].frequency;
-	index = cpufreq_table_find_index_l(policy, freq_avg);
+	index = cpufreq_table_find_index_l(policy, freq_avg,
+					   relation & CPUFREQ_RELATION_E);
 	freq_hi = freq_table[index].frequency;
 
 	/* Find out how long we have to be in hi and lo freqs */
@@ -118,12 +120,12 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 
 	if (od_tuners->powersave_bias)
 		freq = od_ops.powersave_bias_target(policy, freq,
-				CPUFREQ_RELATION_H);
+						    CPUFREQ_RELATION_HE);
 	else if (policy->cur == policy->max)
 		return;
 
 	__cpufreq_driver_target(policy, freq, od_tuners->powersave_bias ?
-			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
+			CPUFREQ_RELATION_LE : CPUFREQ_RELATION_HE);
 }
 
 /*
@@ -161,9 +163,9 @@ static void od_update(struct cpufreq_policy *policy)
 		if (od_tuners->powersave_bias)
 			freq_next = od_ops.powersave_bias_target(policy,
 								 freq_next,
-								 CPUFREQ_RELATION_L);
+								 CPUFREQ_RELATION_LE);
 
-		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_C);
+		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_CE);
 	}
 }
 
@@ -182,7 +184,7 @@ static unsigned int od_dbs_update(struct cpufreq_policy *policy)
 	 */
 	if (sample_type == OD_SUB_SAMPLE && policy_dbs->sample_delay_ns > 0) {
 		__cpufreq_driver_target(policy, dbs_info->freq_lo,
-					CPUFREQ_RELATION_H);
+					CPUFREQ_RELATION_HE);
 		return dbs_info->freq_lo_delay_us;
 	}
 

drivers/cpufreq/mediatek-cpufreq-hw.c

@@ -109,7 +109,7 @@ static unsigned int mtk_cpufreq_hw_fast_switch(struct cpufreq_policy *policy,
 	struct mtk_cpufreq_data *data = policy->driver_data;
 	unsigned int index;
 
-	index = cpufreq_table_find_index_dl(policy, target_freq);
+	index = cpufreq_table_find_index_dl(policy, target_freq, false);
 
 	writel_relaxed(index, data->reg_bases[REG_FREQ_PERF_STATE]);
 

drivers/cpufreq/powernv-cpufreq.c

@@ -934,7 +934,7 @@ static void powernv_cpufreq_work_fn(struct work_struct *work)
 		policy = cpufreq_cpu_get(cpu);
 		if (!policy)
 			continue;
-		index = cpufreq_table_find_index_c(policy, policy->cur);
+		index = cpufreq_table_find_index_c(policy, policy->cur, false);
 		powernv_cpufreq_target_index(policy, index);
 		cpumask_andnot(&mask, &mask, policy->cpus);
 		cpufreq_cpu_put(policy);
@@ -1022,7 +1022,7 @@ static unsigned int powernv_fast_switch(struct cpufreq_policy *policy,
 	int index;
 	struct powernv_smp_call_data freq_data;
 
-	index = cpufreq_table_find_index_dl(policy, target_freq);
+	index = cpufreq_table_find_index_dl(policy, target_freq, false);
 	freq_data.pstate_id = powernv_freqs[index].driver_data;
 	freq_data.gpstate_id = powernv_freqs[index].driver_data;
 	set_pstate(&freq_data);

drivers/cpufreq/s5pv210-cpufreq.c

@@ -243,7 +243,7 @@ static int s5pv210_target(struct cpufreq_policy *policy, unsigned int index)
 	new_freq = s5pv210_freq_table[index].frequency;
 
 	/* Finding current running level index */
-	priv_index = cpufreq_table_find_index_h(policy, old_freq);
+	priv_index = cpufreq_table_find_index_h(policy, old_freq, false);
 
 	arm_volt = dvs_conf[index].arm_volt;
 	int_volt = dvs_conf[index].int_volt;

drivers/powercap/dtpm.c

@@ -116,8 +116,6 @@ static void __dtpm_sub_power(struct dtpm *dtpm)
 		parent->power_limit -= dtpm->power_limit;
 		parent = parent->parent;
 	}
-
-	__dtpm_rebalance_weight(root);
 }
 
 static void __dtpm_add_power(struct dtpm *dtpm)
@@ -130,45 +128,45 @@ static void __dtpm_add_power(struct dtpm *dtpm)
 		parent->power_limit += dtpm->power_limit;
 		parent = parent->parent;
 	}
+}
+
+static int __dtpm_update_power(struct dtpm *dtpm)
+{
+	int ret;
+
+	__dtpm_sub_power(dtpm);
+
+	ret = dtpm->ops->update_power_uw(dtpm);
+	if (ret)
+		pr_err("Failed to update power for '%s': %d\n",
+		       dtpm->zone.name, ret);
 
-	__dtpm_rebalance_weight(root);
+	if (!test_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags))
+		dtpm->power_limit = dtpm->power_max;
+
+	__dtpm_add_power(dtpm);
+
+	if (root)
+		__dtpm_rebalance_weight(root);
+
+	return ret;
 }
 
 /**
  * dtpm_update_power - Update the power on the dtpm
  * @dtpm: a pointer to a dtpm structure to update
- * @power_min: a u64 representing the new power_min value
- * @power_max: a u64 representing the new power_max value
  *
  * Function to update the power values of the dtpm node specified in
  * parameter. These new values will be propagated to the tree.
  *
  * Return: zero on success, -EINVAL if the values are inconsistent
  */
-int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max)
+int dtpm_update_power(struct dtpm *dtpm)
 {
-	int ret = 0;
+	int ret;
 
 	mutex_lock(&dtpm_lock);
-
-	if (power_min == dtpm->power_min && power_max == dtpm->power_max)
-		goto unlock;
-
-	if (power_max < power_min) {
-		ret = -EINVAL;
-		goto unlock;
-	}
-
-	__dtpm_sub_power(dtpm);
-
-	dtpm->power_min = power_min;
-	dtpm->power_max = power_max;
-	if (!test_bit(DTPM_POWER_LIMIT_FLAG, &dtpm->flags))
-		dtpm->power_limit = power_max;
-
-	__dtpm_add_power(dtpm);
-
-unlock:
+	ret = __dtpm_update_power(dtpm);
 	mutex_unlock(&dtpm_lock);
 
 	return ret;
@@ -359,24 +357,18 @@ static struct powercap_zone_ops zone_ops = {
 };
 
 /**
- * dtpm_alloc - Allocate and initialize a dtpm struct
- * @name: a string specifying the name of the node
- *
- * Return: a struct dtpm pointer, NULL in case of error
+ * dtpm_init - Allocate and initialize a dtpm struct
+ * @dtpm: The dtpm struct pointer to be initialized
+ * @ops: The dtpm device specific ops, NULL for a virtual node
  */
-struct dtpm *dtpm_alloc(struct dtpm_ops *ops)
+void dtpm_init(struct dtpm *dtpm, struct dtpm_ops *ops)
 {
-	struct dtpm *dtpm;
-
-	dtpm = kzalloc(sizeof(*dtpm), GFP_KERNEL);
 	if (dtpm) {
 		INIT_LIST_HEAD(&dtpm->children);
 		INIT_LIST_HEAD(&dtpm->sibling);
 		dtpm->weight = 1024;
 		dtpm->ops = ops;
 	}
-
-	return dtpm;
 }
 
 /**
@@ -436,6 +428,7 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 
 	if (dtpm->ops && !(dtpm->ops->set_power_uw &&
 			   dtpm->ops->get_power_uw &&
+			   dtpm->ops->update_power_uw &&
 			   dtpm->ops->release))
 		return -EINVAL;
 
@@ -455,7 +448,10 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 		root = dtpm;
 	}
 
-	__dtpm_add_power(dtpm);
+	if (dtpm->ops && !dtpm->ops->update_power_uw(dtpm)) {
+		__dtpm_add_power(dtpm);
+		dtpm->power_limit = dtpm->power_max;
+	}
 
 	pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n",
 		dtpm->zone.name, dtpm->power_min, dtpm->power_max);
@@ -465,9 +461,9 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 	return 0;
 }
 
-static int __init dtpm_init(void)
+static int __init init_dtpm(void)
 {
-	struct dtpm_descr **dtpm_descr;
+	struct dtpm_descr *dtpm_descr;
 
 	pct = powercap_register_control_type(NULL, "dtpm", NULL);
 	if (IS_ERR(pct)) {
@@ -476,8 +472,8 @@ static int __init dtpm_init(void)
 	}
 
 	for_each_dtpm_table(dtpm_descr)
-		(*dtpm_descr)->init(*dtpm_descr);
+		dtpm_descr->init();
 
 	return 0;
 }
-late_initcall(dtpm_init);
+late_initcall(init_dtpm);