Merge tag 'devfreq-next-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux

Pull devfreq changes for 5.19-rc1 from Chanwoo Choi:

"1. Update devfreq core

 - Add cpu based scaling support to passive governor. Some device like
   cache might require the dynamic frequency scaling. But, it has very
   tightly to cpu frequency. So that use passive governor to scale
   the frequency according to current cpu frequency.

  To decide the frequency of the device, the governor does one of the following:
  : Derives the optimal devfreq device opp from required-opps property of
    the parent cpu opp_table.

  : Scales the device frequency in proportion to the CPU frequency. So, if
    the CPUs are running at their max frequency, the device runs at its
    max frequency. If the CPUs are running at their min frequency, the
    device runs at its min frequency. It is interpolated for frequencies
    in between.

 2. Update devfreq drivers

  - Update rk3399_dmc.c as following:

   : Convert dt-binding document to YAML and deprecate unused properties.

   : Use Hz units for the device-tree properties of rk3399_dmc.

   : rk3399_dmc is able to set the idle time before changing the dmc clock.
     Specify idle time parameters by using nano-second unit on dt bidning.

   : Add new disable-freq properties to optimize the power-saving feature
     of rk3399_dmc.

   : Disable devfreq-event device on remove() to fix unbalanced
     enable-disable count.

   : Use devm_pm_opp_of_add_table()

   : Block PMU (Power-Management Unit) transitions when scaling frequency
     by ARM Trust Firmware in order to fix the conflict between PMU and DMC
     (Dynamic Memory Controller)."

* tag 'devfreq-next-for-5.19' of git://git.kernel.org/pub/scm/linux/kernel/git/chanwoo/linux:
  PM / devfreq: passive: Keep cpufreq_policy for possible cpus
  PM / devfreq: passive: Reduce duplicate code when passive_devfreq case
  PM / devfreq: Add cpu based scaling support to passive governor
  PM / devfreq: Export devfreq_get_freq_range symbol within devfreq
  PM / devfreq: rk3399_dmc: Block PMU during transitions
  soc: rockchip: power-domain: Manage resource conflicts with firmware
  PM / devfreq: rk3399_dmc: Avoid static (reused) profile
  PM / devfreq: rk3399_dmc: Use devm_pm_opp_of_add_table()
  PM / devfreq: rk3399_dmc: Disable edev on remove()
  PM / devfreq: rk3399_dmc: Support new *-ns properties
  PM / devfreq: rk3399_dmc: Support new disable-freq properties
  PM / devfreq: rk3399_dmc: Use bitfield macro definitions for ODT_PD
  PM / devfreq: rk3399_dmc: Drop excess timing properties
  PM / devfreq: rk3399_dmc: Drop undocumented ondemand DT props
  dt-bindings: devfreq: rk3399_dmc: Add more disable-freq properties
  dt-bindings: devfreq: rk3399_dmc: Specify idle params in nanoseconds
  dt-bindings: devfreq: rk3399_dmc: Fix Hz units
  dt-bindings: devfreq: rk3399_dmc: Deprecate unused/redundant properties
  dt-bindings: devfreq: rk3399_dmc: Convert to YAML

1 files changed, 335 insertions, 68 deletions

diff --git a/drivers/devfreq/governor_passive.c b/drivers/devfreq/governor_passive.c
index fc09324a03e0..7306e943a234 100644
--- a/drivers/devfreq/governor_passive.c
+++ b/drivers/devfreq/governor_passive.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0-only
+	// SPDX-License-Identifier: GPL-2.0-only
 /*
  * linux/drivers/devfreq/governor_passive.c
  *
@@ -8,76 +8,129 @@
  */
 
 #include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/slab.h>
 #include <linux/device.h>
 #include <linux/devfreq.h>
 #include "governor.h"
 
-static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
-					unsigned long *freq)
+#define HZ_PER_KHZ	1000
+
+static struct devfreq_cpu_data *
+get_parent_cpu_data(struct devfreq_passive_data *p_data,
+		    struct cpufreq_policy *policy)
 {
-	struct devfreq_passive_data *p_data
-			= (struct devfreq_passive_data *)devfreq->data;
-	struct devfreq *parent_devfreq = (struct devfreq *)p_data->parent;
-	unsigned long child_freq = ULONG_MAX;
-	struct dev_pm_opp *opp, *p_opp;
-	int i, count;
+	struct devfreq_cpu_data *parent_cpu_data;
 
-	/*
-	 * If the devfreq device with passive governor has the specific method
-	 * to determine the next frequency, should use the get_target_freq()
-	 * of struct devfreq_passive_data.
-	 */
-	if (p_data->get_target_freq)
-		return p_data->get_target_freq(devfreq, freq);
+	if (!p_data || !policy)
+		return NULL;
 
-	/*
-	 * If the parent and passive devfreq device uses the OPP table,
-	 * get the next frequency by using the OPP table.
-	 */
+	list_for_each_entry(parent_cpu_data, &p_data->cpu_data_list, node)
+		if (parent_cpu_data->first_cpu == cpumask_first(policy->related_cpus))
+			return parent_cpu_data;
 
-	/*
-	 * - parent devfreq device uses the governors except for passive.
-	 * - passive devfreq device uses the passive governor.
-	 *
-	 * Each devfreq has the OPP table. After deciding the new frequency
-	 * from the governor of parent devfreq device, the passive governor
-	 * need to get the index of new frequency on OPP table of parent
-	 * device. And then the index is used for getting the suitable
-	 * new frequency for passive devfreq device.
-	 */
-	if (!devfreq->profile || !devfreq->profile->freq_table
-		|| devfreq->profile->max_state <= 0)
-		return -EINVAL;
+	return NULL;
+}
 
-	/*
-	 * The passive governor have to get the correct frequency from OPP
-	 * list of parent device. Because in this case, *freq is temporary
-	 * value which is decided by ondemand governor.
-	 */
-	if (devfreq->opp_table && parent_devfreq->opp_table) {
-		p_opp = devfreq_recommended_opp(parent_devfreq->dev.parent,
-						freq, 0);
-		if (IS_ERR(p_opp))
-			return PTR_ERR(p_opp);
+static unsigned long get_target_freq_by_required_opp(struct device *p_dev,
+						struct opp_table *p_opp_table,
+						struct opp_table *opp_table,
+						unsigned long *freq)
+{
+	struct dev_pm_opp *opp = NULL, *p_opp = NULL;
+	unsigned long target_freq;
 
-		opp = dev_pm_opp_xlate_required_opp(parent_devfreq->opp_table,
-						    devfreq->opp_table, p_opp);
-		dev_pm_opp_put(p_opp);
+	if (!p_dev || !p_opp_table || !opp_table || !freq)
+		return 0;
 
-		if (IS_ERR(opp))
-			goto no_required_opp;
+	p_opp = devfreq_recommended_opp(p_dev, freq, 0);
+	if (IS_ERR(p_opp))
+		return 0;
 
-		*freq = dev_pm_opp_get_freq(opp);
-		dev_pm_opp_put(opp);
+	opp = dev_pm_opp_xlate_required_opp(p_opp_table, opp_table, p_opp);
+	dev_pm_opp_put(p_opp);
 
+	if (IS_ERR(opp))
 		return 0;
+
+	target_freq = dev_pm_opp_get_freq(opp);
+	dev_pm_opp_put(opp);
+
+	return target_freq;
+}
+
+static int get_target_freq_with_cpufreq(struct devfreq *devfreq,
+					unsigned long *target_freq)
+{
+	struct devfreq_passive_data *p_data =
+				(struct devfreq_passive_data *)devfreq->data;
+	struct devfreq_cpu_data *parent_cpu_data;
+	struct cpufreq_policy *policy;
+	unsigned long cpu, cpu_cur, cpu_min, cpu_max, cpu_percent;
+	unsigned long dev_min, dev_max;
+	unsigned long freq = 0;
+	int ret = 0;
+
+	for_each_online_cpu(cpu) {
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy) {
+			ret = -EINVAL;
+			continue;
+		}
+
+		parent_cpu_data = get_parent_cpu_data(p_data, policy);
+		if (!parent_cpu_data) {
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+
+		/* Get target freq via required opps */
+		cpu_cur = parent_cpu_data->cur_freq * HZ_PER_KHZ;
+		freq = get_target_freq_by_required_opp(parent_cpu_data->dev,
+					parent_cpu_data->opp_table,
+					devfreq->opp_table, &cpu_cur);
+		if (freq) {
+			*target_freq = max(freq, *target_freq);
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+
+		/* Use interpolation if required opps is not available */
+		devfreq_get_freq_range(devfreq, &dev_min, &dev_max);
+
+		cpu_min = parent_cpu_data->min_freq;
+		cpu_max = parent_cpu_data->max_freq;
+		cpu_cur = parent_cpu_data->cur_freq;
+
+		cpu_percent = ((cpu_cur - cpu_min) * 100) / (cpu_max - cpu_min);
+		freq = dev_min + mult_frac(dev_max - dev_min, cpu_percent, 100);
+
+		*target_freq = max(freq, *target_freq);
+		cpufreq_cpu_put(policy);
 	}
 
-no_required_opp:
-	/*
-	 * Get the OPP table's index of decided frequency by governor
-	 * of parent device.
-	 */
+	return ret;
+}
+
+static int get_target_freq_with_devfreq(struct devfreq *devfreq,
+					unsigned long *freq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq *parent_devfreq = (struct devfreq *)p_data->parent;
+	unsigned long child_freq = ULONG_MAX;
+	int i, count;
+
+	/* Get target freq via required opps */
+	child_freq = get_target_freq_by_required_opp(parent_devfreq->dev.parent,
+						parent_devfreq->opp_table,
+						devfreq->opp_table, freq);
+	if (child_freq)
+		goto out;
+
+	/* Use interpolation if required opps is not available */
 	for (i = 0; i < parent_devfreq->profile->max_state; i++)
 		if (parent_devfreq->profile->freq_table[i] == *freq)
 			break;
@@ -85,7 +138,6 @@ no_required_opp:
 	if (i == parent_devfreq->profile->max_state)
 		return -EINVAL;
 
-	/* Get the suitable frequency by using index of parent device. */
 	if (i < devfreq->profile->max_state) {
 		child_freq = devfreq->profile->freq_table[i];
 	} else {
@@ -93,12 +145,202 @@ no_required_opp:
 		child_freq = devfreq->profile->freq_table[count - 1];
 	}
 
-	/* Return the suitable frequency for passive device. */
+out:
 	*freq = child_freq;
 
 	return 0;
 }
 
+static int devfreq_passive_get_target_freq(struct devfreq *devfreq,
+					   unsigned long *freq)
+{
+	struct devfreq_passive_data *p_data =
+				(struct devfreq_passive_data *)devfreq->data;
+	int ret;
+
+	if (!p_data)
+		return -EINVAL;
+
+	/*
+	 * If the devfreq device with passive governor has the specific method
+	 * to determine the next frequency, should use the get_target_freq()
+	 * of struct devfreq_passive_data.
+	 */
+	if (p_data->get_target_freq)
+		return p_data->get_target_freq(devfreq, freq);
+
+	switch (p_data->parent_type) {
+	case DEVFREQ_PARENT_DEV:
+		ret = get_target_freq_with_devfreq(devfreq, freq);
+		break;
+	case CPUFREQ_PARENT_DEV:
+		ret = get_target_freq_with_cpufreq(devfreq, freq);
+		break;
+	default:
+		ret = -EINVAL;
+		dev_err(&devfreq->dev, "Invalid parent type\n");
+		break;
+	}
+
+	return ret;
+}
+
+static int cpufreq_passive_notifier_call(struct notifier_block *nb,
+					 unsigned long event, void *ptr)
+{
+	struct devfreq_passive_data *p_data =
+			container_of(nb, struct devfreq_passive_data, nb);
+	struct devfreq *devfreq = (struct devfreq *)p_data->this;
+	struct devfreq_cpu_data *parent_cpu_data;
+	struct cpufreq_freqs *freqs = ptr;
+	unsigned int cur_freq;
+	int ret;
+
+	if (event != CPUFREQ_POSTCHANGE || !freqs)
+		return 0;
+
+	parent_cpu_data = get_parent_cpu_data(p_data, freqs->policy);
+	if (!parent_cpu_data || parent_cpu_data->cur_freq == freqs->new)
+		return 0;
+
+	cur_freq = parent_cpu_data->cur_freq;
+	parent_cpu_data->cur_freq = freqs->new;
+
+	mutex_lock(&devfreq->lock);
+	ret = devfreq_update_target(devfreq, freqs->new);
+	mutex_unlock(&devfreq->lock);
+	if (ret) {
+		parent_cpu_data->cur_freq = cur_freq;
+		dev_err(&devfreq->dev, "failed to update the frequency.\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int cpufreq_passive_unregister_notifier(struct devfreq *devfreq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq_cpu_data *parent_cpu_data;
+	int cpu, ret = 0;
+
+	if (p_data->nb.notifier_call) {
+		ret = cpufreq_unregister_notifier(&p_data->nb,
+					CPUFREQ_TRANSITION_NOTIFIER);
+		if (ret < 0)
+			return ret;
+	}
+
+	for_each_possible_cpu(cpu) {
+		struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
+		if (!policy) {
+			ret = -EINVAL;
+			continue;
+		}
+
+		parent_cpu_data = get_parent_cpu_data(p_data, policy);
+		if (!parent_cpu_data) {
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+
+		list_del(&parent_cpu_data->node);
+		if (parent_cpu_data->opp_table)
+			dev_pm_opp_put_opp_table(parent_cpu_data->opp_table);
+		kfree(parent_cpu_data);
+		cpufreq_cpu_put(policy);
+	}
+
+	return ret;
+}
+
+static int cpufreq_passive_register_notifier(struct devfreq *devfreq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct device *dev = devfreq->dev.parent;
+	struct opp_table *opp_table = NULL;
+	struct devfreq_cpu_data *parent_cpu_data;
+	struct cpufreq_policy *policy;
+	struct device *cpu_dev;
+	unsigned int cpu;
+	int ret;
+
+	p_data->cpu_data_list
+		= (struct list_head)LIST_HEAD_INIT(p_data->cpu_data_list);
+
+	p_data->nb.notifier_call = cpufreq_passive_notifier_call;
+	ret = cpufreq_register_notifier(&p_data->nb, CPUFREQ_TRANSITION_NOTIFIER);
+	if (ret) {
+		dev_err(dev, "failed to register cpufreq notifier\n");
+		p_data->nb.notifier_call = NULL;
+		goto err;
+	}
+
+	for_each_possible_cpu(cpu) {
+		policy = cpufreq_cpu_get(cpu);
+		if (!policy) {
+			ret = -EPROBE_DEFER;
+			goto err;
+		}
+
+		parent_cpu_data = get_parent_cpu_data(p_data, policy);
+		if (parent_cpu_data) {
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+
+		parent_cpu_data = kzalloc(sizeof(*parent_cpu_data),
+						GFP_KERNEL);
+		if (!parent_cpu_data) {
+			ret = -ENOMEM;
+			goto err_put_policy;
+		}
+
+		cpu_dev = get_cpu_device(cpu);
+		if (!cpu_dev) {
+			dev_err(dev, "failed to get cpu device\n");
+			ret = -ENODEV;
+			goto err_free_cpu_data;
+		}
+
+		opp_table = dev_pm_opp_get_opp_table(cpu_dev);
+		if (IS_ERR(opp_table)) {
+			dev_err(dev, "failed to get opp_table of cpu%d\n", cpu);
+			ret = PTR_ERR(opp_table);
+			goto err_free_cpu_data;
+		}
+
+		parent_cpu_data->dev = cpu_dev;
+		parent_cpu_data->opp_table = opp_table;
+		parent_cpu_data->first_cpu = cpumask_first(policy->related_cpus);
+		parent_cpu_data->cur_freq = policy->cur;
+		parent_cpu_data->min_freq = policy->cpuinfo.min_freq;
+		parent_cpu_data->max_freq = policy->cpuinfo.max_freq;
+
+		list_add_tail(&parent_cpu_data->node, &p_data->cpu_data_list);
+		cpufreq_cpu_put(policy);
+	}
+
+	mutex_lock(&devfreq->lock);
+	ret = devfreq_update_target(devfreq, 0L);
+	mutex_unlock(&devfreq->lock);
+	if (ret)
+		dev_err(dev, "failed to update the frequency\n");
+
+	return ret;
+
+err_free_cpu_data:
+	kfree(parent_cpu_data);
+err_put_policy:
+	cpufreq_cpu_put(policy);
+err:
+	WARN_ON(cpufreq_passive_unregister_notifier(devfreq));
+
+	return ret;
+}
+
 static int devfreq_passive_notifier_call(struct notifier_block *nb,
 				unsigned long event, void *ptr)
 {
@@ -131,30 +373,55 @@ static int devfreq_passive_notifier_call(struct notifier_block *nb,
 	return NOTIFY_DONE;
 }
 
-static int devfreq_passive_event_handler(struct devfreq *devfreq,
-				unsigned int event, void *data)
+static int devfreq_passive_unregister_notifier(struct devfreq *devfreq)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	struct devfreq *parent = (struct devfreq *)p_data->parent;
+	struct notifier_block *nb = &p_data->nb;
+
+	return devfreq_unregister_notifier(parent, nb, DEVFREQ_TRANSITION_NOTIFIER);
+}
+
+static int devfreq_passive_register_notifier(struct devfreq *devfreq)
 {
 	struct devfreq_passive_data *p_data
 			= (struct devfreq_passive_data *)devfreq->data;
 	struct devfreq *parent = (struct devfreq *)p_data->parent;
 	struct notifier_block *nb = &p_data->nb;
-	int ret = 0;
 
 	if (!parent)
 		return -EPROBE_DEFER;
 
+	nb->notifier_call = devfreq_passive_notifier_call;
+	return devfreq_register_notifier(parent, nb, DEVFREQ_TRANSITION_NOTIFIER);
+}
+
+static int devfreq_passive_event_handler(struct devfreq *devfreq,
+				unsigned int event, void *data)
+{
+	struct devfreq_passive_data *p_data
+			= (struct devfreq_passive_data *)devfreq->data;
+	int ret = -EINVAL;
+
+	if (!p_data)
+		return -EINVAL;
+
+	if (!p_data->this)
+		p_data->this = devfreq;
+
 	switch (event) {
 	case DEVFREQ_GOV_START:
-		if (!p_data->this)
-			p_data->this = devfreq;
-
-		nb->notifier_call = devfreq_passive_notifier_call;
-		ret = devfreq_register_notifier(parent, nb,
-					DEVFREQ_TRANSITION_NOTIFIER);
+		if (p_data->parent_type == DEVFREQ_PARENT_DEV)
+			ret = devfreq_passive_register_notifier(devfreq);
+		else if (p_data->parent_type == CPUFREQ_PARENT_DEV)
+			ret = cpufreq_passive_register_notifier(devfreq);
 		break;
 	case DEVFREQ_GOV_STOP:
-		WARN_ON(devfreq_unregister_notifier(parent, nb,
-					DEVFREQ_TRANSITION_NOTIFIER));
+		if (p_data->parent_type == DEVFREQ_PARENT_DEV)
+			WARN_ON(devfreq_passive_unregister_notifier(devfreq));
+		else if (p_data->parent_type == CPUFREQ_PARENT_DEV)
+			WARN_ON(cpufreq_passive_unregister_notifier(devfreq));
 		break;
 	default:
 		break;