[PATCH v6 4/5] powercap/drivers/dtpm: Add dtpm devfreq with energy model support

[Daniel Lezcano]

Currently the dtpm supports the CPUs via cpufreq and the energy
model. This change provides the same for the device which supports
devfreq.

Each device supporting devfreq and having an energy model can be added
to the hierarchy.

The concept is the same as the cpufreq DTPM support: the QoS is used
to aggregate the requests and the energy model gives the value of the
instantaneous power consumption ponderated by the load of the device.

Cc: Chanwoo Choi <cwchoi00@xxxxxxxxx>
Cc: Lukasz Luba <lukasz.luba@xxxxxxx>
Cc: Kyungmin Park <kyungmin.park@xxxxxxxxxxx>
Cc: MyungJoo Ham <myungjoo.ham@xxxxxxxxxxx>
Signed-off-by: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
---
 drivers/powercap/Kconfig        |   7 ++
 drivers/powercap/Makefile       |   1 +
 drivers/powercap/dtpm_devfreq.c | 204 ++++++++++++++++++++++++++++++++
 drivers/powercap/dtpm_subsys.h  |   4 +
 4 files changed, 216 insertions(+)
 create mode 100644 drivers/powercap/dtpm_devfreq.c

diff --git a/drivers/powercap/Kconfig b/drivers/powercap/Kconfig
index b1ca339957e3..515e3ceb3393 100644
--- a/drivers/powercap/Kconfig
+++ b/drivers/powercap/Kconfig
@@ -57,4 +57,11 @@ config DTPM_CPU
 	help
 	  This enables support for CPU power limitation based on
 	  energy model.
+
+config DTPM_DEVFREQ
+	bool "Add device power capping based on the energy model"
+	depends on DTPM && ENERGY_MODEL
+	help
+	  This enables support for device power limitation based on
+	  energy model.
 endif
diff --git a/drivers/powercap/Makefile b/drivers/powercap/Makefile
index fabcf388a8d3..494617cdad88 100644
--- a/drivers/powercap/Makefile
+++ b/drivers/powercap/Makefile
@@ -1,6 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_DTPM) += dtpm.o
 obj-$(CONFIG_DTPM_CPU) += dtpm_cpu.o
+obj-$(CONFIG_DTPM_DEVFREQ) += dtpm_devfreq.o
 obj-$(CONFIG_POWERCAP)	+= powercap_sys.o
 obj-$(CONFIG_INTEL_RAPL_CORE) += intel_rapl_common.o
 obj-$(CONFIG_INTEL_RAPL) += intel_rapl_msr.o
diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c
new file mode 100644
index 000000000000..755f55f941bf
--- /dev/null
+++ b/drivers/powercap/dtpm_devfreq.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright 2021 Linaro Limited
+ *
+ * Author: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
+ *
+ * The devfreq device combined with the energy model and the load can
+ * give an estimation of the power consumption as well as limiting the
+ * power.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpumask.h>
+#include <linux/devfreq.h>
+#include <linux/dtpm.h>
+#include <linux/energy_model.h>
+#include <linux/of.h>
+#include <linux/pm_qos.h>
+#include <linux/slab.h>
+#include <linux/units.h>
+
+struct dtpm_devfreq {
+	struct dtpm dtpm;
+	struct dev_pm_qos_request qos_req;
+	struct devfreq *devfreq;
+};
+
+static struct dtpm_devfreq *to_dtpm_devfreq(struct dtpm *dtpm)
+{
+	return container_of(dtpm, struct dtpm_devfreq, dtpm);
+}
+
+static int update_pd_power_uw(struct dtpm *dtpm)
+{
+	struct dtpm_devfreq *dtpm_devfreq = to_dtpm_devfreq(dtpm);
+	struct devfreq *devfreq = dtpm_devfreq->devfreq;
+	struct device *dev = devfreq->dev.parent;
+	struct em_perf_domain *pd = em_pd_get(dev);
+
+	dtpm->power_min = pd->table[0].power;
+	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
+
+	dtpm->power_max = pd->table[pd->nr_perf_states - 1].power;
+	dtpm->power_max *= MICROWATT_PER_MILLIWATT;
+
+	return 0;
+}
+
+static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
+{
+	struct dtpm_devfreq *dtpm_devfreq = to_dtpm_devfreq(dtpm);
+	struct devfreq *devfreq = dtpm_devfreq->devfreq;
+	struct device *dev = devfreq->dev.parent;
+	struct em_perf_domain *pd = em_pd_get(dev);
+	unsigned long freq;
+	u64 power;
+	int i;
+
+	for (i = 0; i < pd->nr_perf_states; i++) {
+
+		power = pd->table[i].power * MICROWATT_PER_MILLIWATT;
+		if (power > power_limit)
+			break;
+	}
+
+	freq = pd->table[i - 1].frequency;
+
+	dev_pm_qos_update_request(&dtpm_devfreq->qos_req, freq);
+
+	power_limit = pd->table[i - 1].power * MICROWATT_PER_MILLIWATT;
+
+	return power_limit;
+}
+
+static void _normalize_load(struct devfreq_dev_status *status)
+{
+	if (status->total_time > 0xfffff) {
+		status->total_time >>= 10;
+		status->busy_time >>= 10;
+	}
+
+	status->busy_time <<= 10;
+	status->busy_time /= status->total_time ? : 1;
+
+	status->busy_time = status->busy_time ? : 1;
+	status->total_time = 1024;
+}
+
+static u64 get_pd_power_uw(struct dtpm *dtpm)
+{
+	struct dtpm_devfreq *dtpm_devfreq = to_dtpm_devfreq(dtpm);
+	struct devfreq *devfreq = dtpm_devfreq->devfreq;
+	struct device *dev = devfreq->dev.parent;
+	struct em_perf_domain *pd = em_pd_get(dev);
+	struct devfreq_dev_status status;
+	unsigned long freq;
+	u64 power;
+	int i;
+
+	mutex_lock(&devfreq->lock);
+	status = devfreq->last_status;
+	mutex_unlock(&devfreq->lock);
+
+	freq = DIV_ROUND_UP(status.current_frequency, HZ_PER_KHZ);
+	_normalize_load(&status);
+
+	for (i = 0; i < pd->nr_perf_states; i++) {
+
+		if (pd->table[i].frequency < freq)
+			continue;
+
+		power = pd->table[i].power * MICROWATT_PER_MILLIWATT;
+		power *= status.busy_time;
+		power >>= 10;
+
+		return power;
+	}
+
+	return 0;
+}
+
+static void pd_release(struct dtpm *dtpm)
+{
+	struct dtpm_devfreq *dtpm_devfreq = to_dtpm_devfreq(dtpm);
+
+	if (dev_pm_qos_request_active(&dtpm_devfreq->qos_req))
+		dev_pm_qos_remove_request(&dtpm_devfreq->qos_req);
+
+	kfree(dtpm_devfreq);
+}
+
+static struct dtpm_ops dtpm_ops = {
+	.set_power_uw = set_pd_power_limit,
+	.get_power_uw = get_pd_power_uw,
+	.update_power_uw = update_pd_power_uw,
+	.release = pd_release,
+};
+
+static int __dtpm_devfreq_setup(struct devfreq *devfreq, struct dtpm *parent)
+{
+	struct device *dev = devfreq->dev.parent;
+	struct dtpm_devfreq *dtpm_devfreq;
+	struct em_perf_domain *pd;
+	int ret = -ENOMEM;
+
+	pd = em_pd_get(dev);
+	if (!pd) {
+		ret = dev_pm_opp_of_register_em(dev, NULL);
+		if (ret) {
+			pr_err("No energy model available for '%s'\n", dev_name(dev));
+			return -EINVAL;
+		}
+	}
+
+	dtpm_devfreq = kzalloc(sizeof(*dtpm_devfreq), GFP_KERNEL);
+	if (!dtpm_devfreq)
+		return -ENOMEM;
+
+	dtpm_init(&dtpm_devfreq->dtpm, &dtpm_ops);
+
+	dtpm_devfreq->devfreq = devfreq;
+
+	ret = dtpm_register(dev_name(dev), &dtpm_devfreq->dtpm, parent);
+	if (ret) {
+		pr_err("Failed to register '%s': %d\n", dev_name(dev), ret);
+		goto out_dtpm_devfreq;
+	}
+
+	ret = dev_pm_qos_add_request(dev, &dtpm_devfreq->qos_req,
+				     DEV_PM_QOS_MAX_FREQUENCY,
+				     PM_QOS_MAX_FREQUENCY_DEFAULT_VALUE);
+	if (ret) {
+		pr_err("Failed to add QoS request: %d\n", ret);
+		goto out_dtpm_unregister;
+	}
+
+	dtpm_update_power(&dtpm_devfreq->dtpm);
+
+	return 0;
+
+out_dtpm_unregister:
+	dtpm_unregister(&dtpm_devfreq->dtpm);
+out_dtpm_devfreq:
+	kfree(dtpm_devfreq);
+
+	return ret;
+}
+
+static int dtpm_devfreq_setup(struct dtpm *dtpm, struct device_node *np)
+{
+	struct devfreq *devfreq;
+
+	devfreq = devfreq_get_devfreq_by_node(np);
+	if (IS_ERR(devfreq))
+		return 0;
+
+	return __dtpm_devfreq_setup(devfreq, dtpm);
+}
+
+struct dtpm_subsys_ops dtpm_devfreq_ops = {
+	.name = KBUILD_MODNAME,
+	.setup = dtpm_devfreq_setup,
+};
diff --git a/drivers/powercap/dtpm_subsys.h b/drivers/powercap/dtpm_subsys.h
index 2a3a2055f60e..db1712938a96 100644
--- a/drivers/powercap/dtpm_subsys.h
+++ b/drivers/powercap/dtpm_subsys.h
@@ -8,11 +8,15 @@
 #define ___DTPM_SUBSYS_H__
 
 extern struct dtpm_subsys_ops dtpm_cpu_ops;
+extern struct dtpm_subsys_ops dtpm_devfreq_ops;
 
 struct dtpm_subsys_ops *dtpm_subsys[] = {
 #ifdef CONFIG_DTPM_CPU
 	&dtpm_cpu_ops,
 #endif
+#ifdef CONFIG_DTPM_DEVFREQ
+	&dtpm_devfreq_ops,
+#endif
 };
 
 #endif
-- 
2.25.1