[PATCH v3 1/5] powercap/drivers/dtpm: Encapsulate even more the code

[PATCH v3 1/5] powercap/drivers/dtpm: Encapsulate even more the code

[Daniel Lezcano]

In order to increase the self-encapsulation of the dtpm generic code,
the following changes are adding a power update ops to the dtpm
ops. That allows the generic code to call directly the dtpm backend
function to update the power values.

The power update function does compute the power characteristics when
the function is invoked. In the case of the CPUs, the power
consumption depends on the number of online CPUs. The online CPUs mask
is not up to date at CPUHP_AP_ONLINE_DYN state in the tear down
callback. That is the reason why the online / offline are at separate
state. As there is already an existing state for DTPM, this one is
only moved to the DEAD state, so there is no addition of new state
with these changes. The dtpm node is not removed when the cpu is
unplugged.

That simplifies the code for the next changes and results in a more
self-encapsulated code.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---
V2:
 - Updated the changelog with the CPU node not being removed
 - Commented the cpu hotplug callbacks to explain why there are two callbacks
 - Changed 'upt_power_uw' to 'update_power_uw'
 - Removed unused cpumask variable
---
 drivers/powercap/dtpm.c     |  54 ++++++-------
 drivers/powercap/dtpm_cpu.c | 148 ++++++++++++++++--------------------
 include/linux/cpuhotplug.h  |   2 +-
 include/linux/dtpm.h        |   3 +-
 4 files changed, 97 insertions(+), 110 deletions(-)

diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c
index c2185ec5f887..58433b8ef9a1 100644
--- a/drivers/powercap/dtpm.c
+++ b/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);
 
-	__dtpm_rebalance_weight(root);
+	ret = dtpm->ops->update_power_uw(dtpm);
+	if (ret)
+		pr_err("Failed to update power for '%s': %d\n",
+		       dtpm->zone.name, ret);
+
+	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;
@@ -436,6 +434,7 @@ 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 +454,8 @@ 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);
 
 	pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n",
 		dtpm->zone.name, dtpm->power_min, dtpm->power_max);
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 51c366938acd..cfb120280887 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -14,6 +14,8 @@
  * The CPU hotplug is supported and the power numbers will be updated
  * if a CPU is hot plugged / unplugged.
  */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/cpumask.h>
 #include <linux/cpufreq.h>
 #include <linux/cpuhotplug.h>
@@ -23,8 +25,6 @@
 #include <linux/slab.h>
 #include <linux/units.h>
 
-static struct dtpm *__parent;
-
 static DEFINE_PER_CPU(struct dtpm *, dtpm_per_cpu);
 
 struct dtpm_cpu {
@@ -32,57 +32,16 @@ struct dtpm_cpu {
 	int cpu;
 };
 
-/*
- * When a new CPU is inserted at hotplug or boot time, add the power
- * contribution and update the dtpm tree.
- */
-static int power_add(struct dtpm *dtpm, struct em_perf_domain *em)
-{
-	u64 power_min, power_max;
-
-	power_min = em->table[0].power;
-	power_min *= MICROWATT_PER_MILLIWATT;
-	power_min += dtpm->power_min;
-
-	power_max = em->table[em->nr_perf_states - 1].power;
-	power_max *= MICROWATT_PER_MILLIWATT;
-	power_max += dtpm->power_max;
-
-	return dtpm_update_power(dtpm, power_min, power_max);
-}
-
-/*
- * When a CPU is unplugged, remove its power contribution from the
- * dtpm tree.
- */
-static int power_sub(struct dtpm *dtpm, struct em_perf_domain *em)
-{
-	u64 power_min, power_max;
-
-	power_min = em->table[0].power;
-	power_min *= MICROWATT_PER_MILLIWATT;
-	power_min = dtpm->power_min - power_min;
-
-	power_max = em->table[em->nr_perf_states - 1].power;
-	power_max *= MICROWATT_PER_MILLIWATT;
-	power_max = dtpm->power_max - power_max;
-
-	return dtpm_update_power(dtpm, power_min, power_max);
-}
-
 static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 {
 	struct dtpm_cpu *dtpm_cpu = dtpm->private;
-	struct em_perf_domain *pd;
+	struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu);
 	struct cpumask cpus;
 	unsigned long freq;
 	u64 power;
 	int i, nr_cpus;
 
-	pd = em_cpu_get(dtpm_cpu->cpu);
-
 	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
-
 	nr_cpus = cpumask_weight(&cpus);
 
 	for (i = 0; i < pd->nr_perf_states; i++) {
@@ -113,6 +72,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 
 	pd = em_cpu_get(dtpm_cpu->cpu);
 	freq = cpufreq_quick_get(dtpm_cpu->cpu);
+
 	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
 	nr_cpus = cpumask_weight(&cpus);
 
@@ -128,6 +88,27 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 	return 0;
 }
 
+static int update_pd_power_uw(struct dtpm *dtpm)
+{
+	struct dtpm_cpu *dtpm_cpu = dtpm->private;
+	struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu);
+	struct cpumask cpus;
+	int nr_cpus;
+
+	cpumask_and(&cpus, cpu_online_mask, to_cpumask(em->cpus));
+	nr_cpus = cpumask_weight(&cpus);
+
+	dtpm->power_min = em->table[0].power;
+	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
+	dtpm->power_min *= nr_cpus;
+
+	dtpm->power_max = em->table[em->nr_perf_states - 1].power;
+	dtpm->power_max *= MICROWATT_PER_MILLIWATT;
+	dtpm->power_max *= nr_cpus;
+
+	return 0;
+}
+
 static void pd_release(struct dtpm *dtpm)
 {
 	struct dtpm_cpu *dtpm_cpu = dtpm->private;
@@ -139,39 +120,24 @@ static void pd_release(struct dtpm *dtpm)
 }
 
 static struct dtpm_ops dtpm_ops = {
-	.set_power_uw = set_pd_power_limit,
-	.get_power_uw = get_pd_power_uw,
-	.release = pd_release,
+	.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 cpuhp_dtpm_cpu_offline(unsigned int cpu)
 {
-	struct cpufreq_policy *policy;
 	struct em_perf_domain *pd;
 	struct dtpm *dtpm;
 
-	policy = cpufreq_cpu_get(cpu);
-
-	if (!policy)
-		return 0;
-
 	pd = em_cpu_get(cpu);
 	if (!pd)
 		return -EINVAL;
 
 	dtpm = per_cpu(dtpm_per_cpu, cpu);
 
-	power_sub(dtpm, pd);
-
-	if (cpumask_weight(policy->cpus) != 1)
-		return 0;
-
-	for_each_cpu(cpu, policy->related_cpus)
-		per_cpu(dtpm_per_cpu, cpu) = NULL;
-
-	dtpm_unregister(dtpm);
-
-	return 0;
+	return dtpm_update_power(dtpm);
 }
 
 static int cpuhp_dtpm_cpu_online(unsigned int cpu)
@@ -184,7 +150,6 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 	int ret = -ENOMEM;
 
 	policy = cpufreq_cpu_get(cpu);
-
 	if (!policy)
 		return 0;
 
@@ -194,7 +159,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
 	dtpm = per_cpu(dtpm_per_cpu, cpu);
 	if (dtpm)
-		return power_add(dtpm, pd);
+		return dtpm_update_power(dtpm);
 
 	dtpm = dtpm_alloc(&dtpm_ops);
 	if (!dtpm)
@@ -210,27 +175,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 	for_each_cpu(cpu, policy->related_cpus)
 		per_cpu(dtpm_per_cpu, cpu) = dtpm;
 
-	sprintf(name, "cpu%d", dtpm_cpu->cpu);
+	sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);
 
-	ret = dtpm_register(name, dtpm, __parent);
+	ret = dtpm_register(name, dtpm, NULL);
 	if (ret)
 		goto out_kfree_dtpm_cpu;
 
-	ret = power_add(dtpm, pd);
-	if (ret)
-		goto out_dtpm_unregister;
-
 	ret = freq_qos_add_request(&policy->constraints,
 				   &dtpm_cpu->qos_req, FREQ_QOS_MAX,
 				   pd->table[pd->nr_perf_states - 1].frequency);
 	if (ret)
-		goto out_power_sub;
+		goto out_dtpm_unregister;
 
 	return 0;
 
-out_power_sub:
-	power_sub(dtpm, pd);
-
 out_dtpm_unregister:
 	dtpm_unregister(dtpm);
 	dtpm_cpu = NULL;
@@ -248,10 +206,38 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
 int dtpm_register_cpu(struct dtpm *parent)
 {
-	__parent = parent;
+	int ret;
+
+	/*
+	 * The callbacks at CPU hotplug time are calling
+	 * dtpm_update_power() which in turns calls update_pd_power().
+	 *
+	 * The function update_pd_power() uses the online mask to
+	 * figure out the power consumption limits.
+	 *
+	 * At CPUHP_AP_ONLINE_DYN, the CPU is present in the CPU
+	 * online mask when the cpuhp_dtpm_cpu_online function is
+	 * called, but the CPU is still in the online mask for the
+	 * tear down callback. So the power can not be updated when
+	 * the CPU is unplugged.
+	 *
+	 * At CPUHP_AP_DTPM_CPU_DEAD, the situation is the opposite as
+	 * above. The CPU online mask is not up to date when the CPU
+	 * is plugged in.
+	 *
+	 * For this reason, we need to call the online and offline
+	 * callbacks at different moments when the CPU online mask is
+	 * consistent with the power numbers we want to update.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_DTPM_CPU_DEAD, "dtpm_cpu:offline",
+				NULL, cpuhp_dtpm_cpu_offline);
+	if (ret < 0)
+		return ret;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "dtpm_cpu:online",
+				cpuhp_dtpm_cpu_online, NULL);
+	if (ret < 0)
+		return ret;
 
-	return cpuhp_setup_state(CPUHP_AP_DTPM_CPU_ONLINE,
-				 "dtpm_cpu:online",
-				 cpuhp_dtpm_cpu_online,
-				 cpuhp_dtpm_cpu_offline);
+	return 0;
 }
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index ee09a39627d6..fcb2967fb5ba 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -61,6 +61,7 @@ enum cpuhp_state {
 	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
 	CPUHP_PADATA_DEAD,
+	CPUHP_AP_DTPM_CPU_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
@@ -193,7 +194,6 @@ enum cpuhp_state {
 	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
 	CPUHP_AP_X86_HPET_ONLINE,
 	CPUHP_AP_X86_KVM_CLK_ONLINE,
-	CPUHP_AP_DTPM_CPU_ONLINE,
 	CPUHP_AP_ACTIVE,
 	CPUHP_ONLINE,
 };
diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h
index e80a332e3d8a..acf8d3638988 100644
--- a/include/linux/dtpm.h
+++ b/include/linux/dtpm.h
@@ -29,6 +29,7 @@ struct dtpm {
 struct dtpm_ops {
 	u64 (*set_power_uw)(struct dtpm *, u64);
 	u64 (*get_power_uw)(struct dtpm *);
+	int (*update_power_uw)(struct dtpm *);
 	void (*release)(struct dtpm *);
 };
 
@@ -62,7 +63,7 @@ static inline struct dtpm *to_dtpm(struct powercap_zone *zone)
 	return container_of(zone, struct dtpm, zone);
 }
 
-int dtpm_update_power(struct dtpm *dtpm, u64 power_min, u64 power_max);
+int dtpm_update_power(struct dtpm *dtpm);
 
 int dtpm_release_zone(struct powercap_zone *pcz);
 
-- 
2.17.1

[PATCH v3 2/5] powercap/drivers/dtpm: Create a registering system

[Daniel Lezcano]

A SoC can be differently structured depending on the platform and the
kernel can not be aware of all the combinations, as well as the
specific tweaks for a particular board.

The creation of the hierarchy must be delegated to userspace.

These changes provide a registering mechanism where the different
subsystems will initialize their dtpm backends and register with a
name the dtpm node in a list.

The next changes will provide an userspace interface to create
hierachically the different nodes. Those will be created by name and
found via the list filled by the different subsystem.

If a specified name is not found in the list, it is assumed to be a
virtual node which will have children and the default is to allocate
such node.

When the node register in the list, the function will be dtpm_register
where the previous semantic was to create the node. Thus, the
functions are renamed to reflect their purpose.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---

 V2:
   - Fixed error code path by dropping lock
---
 drivers/powercap/dtpm.c     | 161 ++++++++++++++++++++++++++++++++++--
 drivers/powercap/dtpm_cpu.c |   4 +-
 include/linux/dtpm.h        |  12 ++-
 3 files changed, 164 insertions(+), 13 deletions(-)

diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c
index 58433b8ef9a1..d00f55f0ee30 100644
--- a/drivers/powercap/dtpm.c
+++ b/drivers/powercap/dtpm.c
@@ -20,6 +20,7 @@
 #include <linux/dtpm.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/powercap.h>
 #include <linux/slab.h>
 #include <linux/mutex.h>
@@ -34,6 +35,14 @@ static DEFINE_MUTEX(dtpm_lock);
 static struct powercap_control_type *pct;
 static struct dtpm *root;
 
+struct dtpm_node {
+	const char *name;
+	struct dtpm *dtpm;
+	struct list_head node;
+};
+
+static LIST_HEAD(dtpm_list);
+
 static int get_time_window_us(struct powercap_zone *pcz, int cid, u64 *window)
 {
 	return -ENOSYS;
@@ -152,6 +161,138 @@ static int __dtpm_update_power(struct dtpm *dtpm)
 	return ret;
 }
 
+static struct dtpm *__dtpm_lookup(const char *name)
+{
+	struct dtpm_node *node;
+
+	list_for_each_entry(node, &dtpm_list, node) {
+		if (!strcmp(name, node->name))
+			return node->dtpm;
+	}
+
+	return NULL;
+}
+
+/**
+ * dtpm_get - Get a reference to a dtpm structure
+ * @name: the name of the dtpm device
+ *
+ * The function looks up in the list of the registered dtpm
+ * devices. If the dtpm device is not found, a virtual one is
+ * allocated. This function must be called to create a dtpm node in
+ * the powercap hierarchy.
+ *
+ * Return: a pointer to a dtpm structure, NULL if there is not enough
+ * memory
+ */
+struct dtpm *dtpm_get(const char *name)
+{
+	struct dtpm *dtpm;
+
+	mutex_lock(&dtpm_lock);
+	dtpm = __dtpm_lookup(name);
+	if (!dtpm)
+		dtpm = dtpm_alloc(NULL);
+	else
+		kref_get(&dtpm->kref);
+	mutex_unlock(&dtpm_lock);
+
+	return dtpm;
+}
+
+static void dtpm_release(struct kref *kref)
+{
+	struct dtpm *dtpm = container_of(kref, struct dtpm, kref);
+
+	kfree(dtpm);
+}
+
+/**
+ * dtpm_put - Release a reference on a dtpm device
+ * @dtpm: a pointer to a dtpm structure
+ *
+ * Release the reference on the specified dtpm device. The last
+ * reference leads to a memory release.
+ */
+void dtpm_put(struct dtpm *dtpm)
+{
+	kref_put(&dtpm->kref, dtpm_release);
+}
+
+/**
+ * dtpm_register - Register the dtpm in the dtpm list
+ * @name: a name used as an identifier
+ * @dtpm: the dtpm node to be registered
+ *
+ * Stores the dtpm device in a list.
+ *
+ * Return: 0 on success, -EEXIST if the device name is already present
+ * in the list, -ENOMEM in case of memory allocation failure.
+ */
+int dtpm_register(const char *name, struct dtpm *dtpm)
+{
+	struct dtpm_node *node;
+	int ret;
+
+	mutex_lock(&dtpm_lock);
+
+	ret = -EEXIST;
+	if (__dtpm_lookup(name))
+		goto out_unlock;
+
+	ret = -ENOMEM;
+	node = kzalloc(sizeof(*node), GFP_KERNEL);
+	if (!node)
+		goto out_unlock;
+
+	node->name = kstrdup(name, GFP_KERNEL);
+	if (!node->name) {
+		kfree(node);
+		goto out_unlock;
+	}
+
+	node->dtpm = dtpm;
+
+	list_add(&node->node, &dtpm_list);
+
+	pr_info("Registered %s\n", name);
+
+	ret = 0;
+out_unlock:
+	mutex_unlock(&dtpm_lock);
+
+	return ret;
+}
+
+/**
+ * dtpm_unregister - Remove the dtpm device from the list
+ * @name: the dtpm device name to be removed
+ *
+ * Remove the dtpm device from the list of the registered devices.
+ */
+void dtpm_unregister(const char *name)
+{
+	struct dtpm_node *node;
+
+	mutex_lock(&dtpm_lock);
+
+	list_for_each_entry(node, &dtpm_list, node) {
+
+		if (strcmp(name, node->name))
+			continue;
+
+		list_del(&node->node);
+		kfree(node->name);
+		kfree(node);
+
+		pr_info("Unregistered %s\n", name);
+
+		break;
+	}
+
+	mutex_unlock(&dtpm_lock);
+}
+
 /**
  * dtpm_update_power - Update the power on the dtpm
  * @dtpm: a pointer to a dtpm structure to update
@@ -208,7 +349,7 @@ int dtpm_release_zone(struct powercap_zone *pcz)
 	if (root == dtpm)
 		root = NULL;
 
-	kfree(dtpm);
+	dtpm_put(dtpm);
 
 	return 0;
 }
@@ -370,6 +511,7 @@ struct dtpm *dtpm_alloc(struct dtpm_ops *ops)
 	if (dtpm) {
 		INIT_LIST_HEAD(&dtpm->children);
 		INIT_LIST_HEAD(&dtpm->sibling);
+		kref_init(&dtpm->kref);
 		dtpm->weight = 1024;
 		dtpm->ops = ops;
 	}
@@ -378,28 +520,29 @@ struct dtpm *dtpm_alloc(struct dtpm_ops *ops)
 }
 
 /**
- * dtpm_unregister - Unregister a dtpm node from the hierarchy tree
- * @dtpm: a pointer to a dtpm structure corresponding to the node to be removed
+ * dtpm_destroy - Destroy a dtpm node from the hierarchy tree
+ * @dtpm: a pointer to a dtpm structure corresponding to the node to be
+ *	  removed and destroyed
  *
  * Call the underlying powercap unregister function. That will call
  * the release callback of the powercap zone.
  */
-void dtpm_unregister(struct dtpm *dtpm)
+void dtpm_destroy(struct dtpm *dtpm)
 {
 	powercap_unregister_zone(pct, &dtpm->zone);
 
-	pr_info("Unregistered dtpm node '%s'\n", dtpm->zone.name);
+	pr_info("Destroyed dtpm node '%s'\n", dtpm->zone.name);
 }
 
 /**
- * dtpm_register - Register a dtpm node in the hierarchy tree
+ * dtpm_create - Create a dtpm node in the hierarchy tree
  * @name: a string specifying the name of the node
  * @dtpm: a pointer to a dtpm structure corresponding to the new node
  * @parent: a pointer to a dtpm structure corresponding to the parent node
  *
  * Create a dtpm node in the tree. If no parent is specified, the node
  * is the root node of the hierarchy. If the root node already exists,
- * then the registration will fail. The powercap controller must be
+ * then the creation will fail. The powercap controller must be
  * initialized before calling this function.
  *
  * The dtpm structure must be initialized with the power numbers
@@ -413,7 +556,7 @@ void dtpm_unregister(struct dtpm *dtpm)
  *           * parent have ops which are reserved for leaves
  *   Other negative values are reported back from the powercap framework
  */
-int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
+int dtpm_create(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 {
 	struct powercap_zone *pcz;
 
@@ -457,7 +600,7 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 	if (dtpm->ops && !dtpm->ops->update_power_uw(dtpm))
 		__dtpm_add_power(dtpm);
 
-	pr_info("Registered dtpm node '%s' / %llu-%llu uW, \n",
+	pr_info("Created dtpm node '%s' / %llu-%llu uW, \n",
 		dtpm->zone.name, dtpm->power_min, dtpm->power_max);
 
 	mutex_unlock(&dtpm_lock);
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index cfb120280887..628d4d6d83a6 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -177,7 +177,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
 	sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);
 
-	ret = dtpm_register(name, dtpm, NULL);
+	ret = dtpm_register(name, dtpm);
 	if (ret)
 		goto out_kfree_dtpm_cpu;
 
@@ -190,7 +190,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 	return 0;
 
 out_dtpm_unregister:
-	dtpm_unregister(dtpm);
+	dtpm_unregister(name);
 	dtpm_cpu = NULL;
 	dtpm = NULL;
 
diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h
index acf8d3638988..d724c5a7b2f4 100644
--- a/include/linux/dtpm.h
+++ b/include/linux/dtpm.h
@@ -14,6 +14,7 @@
 
 struct dtpm {
 	struct powercap_zone zone;
+	struct kref kref;
 	struct dtpm *parent;
 	struct list_head sibling;
 	struct list_head children;
@@ -69,10 +70,17 @@ int dtpm_release_zone(struct powercap_zone *pcz);
 
 struct dtpm *dtpm_alloc(struct dtpm_ops *ops);
 
-void dtpm_unregister(struct dtpm *dtpm);
+void dtpm_destroy(struct dtpm *dtpm);
 
-int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent);
+int dtpm_create(const char *name, struct dtpm *dtpm, struct dtpm *parent);
 
 int dtpm_register_cpu(struct dtpm *parent);
 
+int dtpm_register(const char *name, struct dtpm *dtpm);
+
+void dtpm_unregister(const char *name);
+
+struct dtpm *dtpm_get(const char *name);
+
+void dtpm_put(struct dtpm *dtpm);
 #endif
-- 
2.17.1

[PATCH v3 3/5] powercap/drivers/dtpm: Simplify the dtpm table

[Daniel Lezcano]

The dtpm table is an array of pointers, that forces the user of the
table to define initdata along with the declaration of the table
entry. It is more efficient to create an array of dtpm structure, so
the declaration of the table entry can be done by initializing the
different fields.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
---
 drivers/powercap/dtpm.c     |  4 ++--
 drivers/powercap/dtpm_cpu.c |  4 +++-
 include/linux/dtpm.h        | 22 +++++++++-------------
 3 files changed, 14 insertions(+), 16 deletions(-)

diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c
index d00f55f0ee30..74d9603bd42a 100644
--- a/drivers/powercap/dtpm.c
+++ b/drivers/powercap/dtpm.c
@@ -610,7 +610,7 @@ int dtpm_create(const char *name, struct dtpm *dtpm, struct dtpm *parent)
 
 static int __init dtpm_init(void)
 {
-	struct dtpm_descr **dtpm_descr;
+	struct dtpm_descr *dtpm_descr;
 
 	pct = powercap_register_control_type(NULL, "dtpm", NULL);
 	if (IS_ERR(pct)) {
@@ -619,7 +619,7 @@ static int __init dtpm_init(void)
 	}
 
 	for_each_dtpm_table(dtpm_descr)
-		(*dtpm_descr)->init(*dtpm_descr);
+		dtpm_descr->init();
 
 	return 0;
 }
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 628d4d6d83a6..983f1ca27dc3 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -204,7 +204,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 	return ret;
 }
 
-int dtpm_register_cpu(struct dtpm *parent)
+static int __init dtpm_cpu_init(void)
 {
 	int ret;
 
@@ -241,3 +241,5 @@ int dtpm_register_cpu(struct dtpm *parent)
 
 	return 0;
 }
+
+DTPM_DECLARE(dtpm_cpu, dtpm_cpu_init);
diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h
index d724c5a7b2f4..5f71ddc18ee9 100644
--- a/include/linux/dtpm.h
+++ b/include/linux/dtpm.h
@@ -34,25 +34,23 @@ struct dtpm_ops {
 	void (*release)(struct dtpm *);
 };
 
-struct dtpm_descr;
-
-typedef int (*dtpm_init_t)(struct dtpm_descr *);
+typedef int (*dtpm_init_t)(void);
 
 struct dtpm_descr {
-	struct dtpm *parent;
-	const char *name;
 	dtpm_init_t init;
 };
 
 /* Init section thermal table */
-extern struct dtpm_descr *__dtpm_table[];
-extern struct dtpm_descr *__dtpm_table_end[];
+extern struct dtpm_descr __dtpm_table[];
+extern struct dtpm_descr __dtpm_table_end[];
 
-#define DTPM_TABLE_ENTRY(name)			\
-	static typeof(name) *__dtpm_table_entry_##name	\
-	__used __section("__dtpm_table") = &name
+#define DTPM_TABLE_ENTRY(name, __init)				\
+	static struct dtpm_descr __dtpm_table_entry_##name	\
+	__used __section("__dtpm_table") = {			\
+		.init = __init,					\
+	}
 
-#define DTPM_DECLARE(name)	DTPM_TABLE_ENTRY(name)
+#define DTPM_DECLARE(name, init)	DTPM_TABLE_ENTRY(name, init)
 
 #define for_each_dtpm_table(__dtpm)	\
 	for (__dtpm = __dtpm_table;	\
@@ -74,8 +72,6 @@ void dtpm_destroy(struct dtpm *dtpm);
 
 int dtpm_create(const char *name, struct dtpm *dtpm, struct dtpm *parent);
 
-int dtpm_register_cpu(struct dtpm *parent);
-
 int dtpm_register(const char *name, struct dtpm *dtpm);
 
 void dtpm_unregister(const char *name);
-- 
2.17.1

[PATCH v3 4/5] powercap/drivers/dtpm: Use container_of instead of a private data field

[Daniel Lezcano]

The dtpm framework provides an API to allocate a dtpm node. However
when a backend dtpm driver needs to allocate a dtpm node it must
define its own structure and store the pointer of this structure in
the private field of the dtpm structure.

It is more elegant to use the container_of macro and add the dtpm
structure inside the dtpm backend specific structure. The code will be
able to deal properly with the dtpm structure as a generic entity,
making all this even more self-encapsulated.

The dtpm_alloc() function does no longer make sense as the dtpm
structure will be allocated when allocating the device specific dtpm
structure. The dtpm_init() is provided instead.

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
---
 drivers/powercap/dtpm.c     | 27 ++++++++++------------
 drivers/powercap/dtpm_cpu.c | 46 ++++++++++++++++++-------------------
 include/linux/dtpm.h        |  3 +--
 3 files changed, 35 insertions(+), 41 deletions(-)

diff --git a/drivers/powercap/dtpm.c b/drivers/powercap/dtpm.c
index 74d9603bd42a..a4784ac2f79b 100644
--- a/drivers/powercap/dtpm.c
+++ b/drivers/powercap/dtpm.c
@@ -191,10 +191,13 @@ struct dtpm *dtpm_get(const char *name)
 
 	mutex_lock(&dtpm_lock);
 	dtpm = __dtpm_lookup(name);
-	if (!dtpm)
-		dtpm = dtpm_alloc(NULL);
-	else
+	if (!dtpm) {
+		dtpm = kzalloc(sizeof(*dtpm), GFP_KERNEL);
+		if (dtpm)
+			dtpm_init(dtpm, NULL);
+	} else {
 		kref_get(&dtpm->kref);
+	}
 	mutex_unlock(&dtpm_lock);
 
 	return dtpm;
@@ -498,16 +501,12 @@ 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);
@@ -515,8 +514,6 @@ struct dtpm *dtpm_alloc(struct dtpm_ops *ops)
 		dtpm->weight = 1024;
 		dtpm->ops = ops;
 	}
-
-	return dtpm;
 }
 
 /**
@@ -608,7 +605,7 @@ int dtpm_create(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;
 
@@ -623,4 +620,4 @@ static int __init dtpm_init(void)
 
 	return 0;
 }
-late_initcall(dtpm_init);
+late_initcall(init_dtpm);
diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index 983f1ca27dc3..ac7f2e7e262f 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -25,16 +25,22 @@
 #include <linux/slab.h>
 #include <linux/units.h>
 
-static DEFINE_PER_CPU(struct dtpm *, dtpm_per_cpu);
-
 struct dtpm_cpu {
+	struct dtpm dtpm;
 	struct freq_qos_request qos_req;
 	int cpu;
 };
 
+static DEFINE_PER_CPU(struct dtpm_cpu *, dtpm_per_cpu);
+
+static struct dtpm_cpu *to_dtpm_cpu(struct dtpm *dtpm)
+{
+	return container_of(dtpm, struct dtpm_cpu, dtpm);
+}
+
 static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 {
-	struct dtpm_cpu *dtpm_cpu = dtpm->private;
+	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu);
 	struct cpumask cpus;
 	unsigned long freq;
@@ -64,7 +70,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 
 static u64 get_pd_power_uw(struct dtpm *dtpm)
 {
-	struct dtpm_cpu *dtpm_cpu = dtpm->private;
+	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *pd;
 	struct cpumask cpus;
 	unsigned long freq;
@@ -90,7 +96,7 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 
 static int update_pd_power_uw(struct dtpm *dtpm)
 {
-	struct dtpm_cpu *dtpm_cpu = dtpm->private;
+	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu);
 	struct cpumask cpus;
 	int nr_cpus;
@@ -111,7 +117,7 @@ static int update_pd_power_uw(struct dtpm *dtpm)
 
 static void pd_release(struct dtpm *dtpm)
 {
-	struct dtpm_cpu *dtpm_cpu = dtpm->private;
+	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 
 	if (freq_qos_request_active(&dtpm_cpu->qos_req))
 		freq_qos_remove_request(&dtpm_cpu->qos_req);
@@ -129,20 +135,19 @@ static struct dtpm_ops dtpm_ops = {
 static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
 {
 	struct em_perf_domain *pd;
-	struct dtpm *dtpm;
+	struct dtpm_cpu *dtpm_cpu;
 
 	pd = em_cpu_get(cpu);
 	if (!pd)
 		return -EINVAL;
 
-	dtpm = per_cpu(dtpm_per_cpu, cpu);
+	dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
 
-	return dtpm_update_power(dtpm);
+	return dtpm_update_power(&dtpm_cpu->dtpm);
 }
 
 static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 {
-	struct dtpm *dtpm;
 	struct dtpm_cpu *dtpm_cpu;
 	struct cpufreq_policy *policy;
 	struct em_perf_domain *pd;
@@ -157,27 +162,23 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 	if (!pd)
 		return -EINVAL;
 
-	dtpm = per_cpu(dtpm_per_cpu, cpu);
-	if (dtpm)
-		return dtpm_update_power(dtpm);
-
-	dtpm = dtpm_alloc(&dtpm_ops);
-	if (!dtpm)
-		return -EINVAL;
+	dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+	if (dtpm_cpu)
+		return dtpm_update_power(&dtpm_cpu->dtpm);
 
 	dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL);
 	if (!dtpm_cpu)
-		goto out_kfree_dtpm;
+		return -ENOMEM;
 
-	dtpm->private = dtpm_cpu;
+	dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops);
 	dtpm_cpu->cpu = cpu;
 
 	for_each_cpu(cpu, policy->related_cpus)
-		per_cpu(dtpm_per_cpu, cpu) = dtpm;
+		per_cpu(dtpm_per_cpu, cpu) = dtpm_cpu;
 
 	sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);
 
-	ret = dtpm_register(name, dtpm);
+	ret = dtpm_register(name, &dtpm_cpu->dtpm);
 	if (ret)
 		goto out_kfree_dtpm_cpu;
 
@@ -192,15 +193,12 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 out_dtpm_unregister:
 	dtpm_unregister(name);
 	dtpm_cpu = NULL;
-	dtpm = NULL;
 
 out_kfree_dtpm_cpu:
 	for_each_cpu(cpu, policy->related_cpus)
 		per_cpu(dtpm_per_cpu, cpu) = NULL;
 	kfree(dtpm_cpu);
 
-out_kfree_dtpm:
-	kfree(dtpm);
 	return ret;
 }
 
diff --git a/include/linux/dtpm.h b/include/linux/dtpm.h
index 5f71ddc18ee9..4f7ad21291e6 100644
--- a/include/linux/dtpm.h
+++ b/include/linux/dtpm.h
@@ -24,7 +24,6 @@ struct dtpm {
 	u64 power_max;
 	u64 power_min;
 	int weight;
-	void *private;
 };
 
 struct dtpm_ops {
@@ -66,7 +65,7 @@ int dtpm_update_power(struct dtpm *dtpm);
 
 int dtpm_release_zone(struct powercap_zone *pcz);
 
-struct dtpm *dtpm_alloc(struct dtpm_ops *ops);
+void dtpm_init(struct dtpm *dtpm, struct dtpm_ops *ops);
 
 void dtpm_destroy(struct dtpm *dtpm);
 
-- 
2.17.1

[PATCH v3 5/5] powercap/drivers/dtpm: Scale the power with the load

[Daniel Lezcano]

Currently the power consumption is based on the current OPP power
assuming the entire performance domain is fully loaded.

That gives very gross power estimation and we can do much better by
using the load to scale the power consumption.

Use the utilization to normalize and scale the power usage over the
max possible power.

Tested on a rock960 with 2 big CPUS, the power consumption estimation
conforms with the expected one.

Before this change:

~$ ~/dhrystone -t 1 -l 10000&
~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
2260000

After this change:

~$ ~/dhrystone -t 1 -l 10000&
~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
1130000

~$ ~/dhrystone -t 2 -l 10000&
~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
2260000

Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
---

V3:
  - Fixed uninitialized 'cpu' in scaled_power_uw()
V2:
  - Replaced cpumask by em_span_cpus
  - Changed 'util' metrics variable types
  - Optimized utilization scaling power computation
  - Renamed parameter name for scale_pd_power_uw()
---
 drivers/powercap/dtpm_cpu.c | 46 +++++++++++++++++++++++++++++++------
 1 file changed, 39 insertions(+), 7 deletions(-)

diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index ac7f2e7e262f..47854923d958 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -68,27 +68,59 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 	return power_limit;
 }
 
+static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
+{
+	unsigned long max = 0, sum_util = 0;
+	int cpu;
+
+	for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
+
+		/*
+		 * The capacity is the same for all CPUs belonging to
+		 * the same perf domain, so a single call to
+		 * arch_scale_cpu_capacity() is enough. However, we
+		 * need the CPU parameter to be initialized by the
+		 * loop, so the call ends up in this block.
+		 *
+		 * We can initialize 'max' with a cpumask_first() call
+		 * before the loop but the bits computation is not
+		 * worth given the arch_scale_cpu_capacity() just
+		 * returns a value where the resulting assembly code
+		 * will be optimized by the compiler.
+		 */
+		max = arch_scale_cpu_capacity(cpu);
+		sum_util += sched_cpu_util(cpu, max);
+	}
+
+	/*
+	 * In the improbable case where all the CPUs of the perf
+	 * domain are offline, 'max' will be zero and will lead to an
+	 * illegal operation with a zero division.
+	 */
+	return max ? (power * ((sum_util << 10) / max)) >> 10 : 0;
+}
+
 static u64 get_pd_power_uw(struct dtpm *dtpm)
 {
 	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *pd;
-	struct cpumask cpus;
+	struct cpumask *pd_mask;
 	unsigned long freq;
-	int i, nr_cpus;
+	int i;
 
 	pd = em_cpu_get(dtpm_cpu->cpu);
-	freq = cpufreq_quick_get(dtpm_cpu->cpu);
 
-	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
-	nr_cpus = cpumask_weight(&cpus);
+	pd_mask = em_span_cpus(pd);
+
+	freq = cpufreq_quick_get(dtpm_cpu->cpu);
 
 	for (i = 0; i < pd->nr_perf_states; i++) {
 
 		if (pd->table[i].frequency < freq)
 			continue;
 
-		return pd->table[i].power *
-			MICROWATT_PER_MILLIWATT * nr_cpus;
+		return scale_pd_power_uw(pd_mask, pd->table[i].power *
+					 MICROWATT_PER_MILLIWATT);
 	}
 
 	return 0;
-- 
2.17.1

Re: [PATCH v3 5/5] powercap/drivers/dtpm: Scale the power with the load

[Lukasz Luba]

On 3/10/21 11:02 AM, Daniel Lezcano wrote:
> Currently the power consumption is based on the current OPP power
> assuming the entire performance domain is fully loaded.
> 
> That gives very gross power estimation and we can do much better by
> using the load to scale the power consumption.
> 
> Use the utilization to normalize and scale the power usage over the
> max possible power.
> 
> Tested on a rock960 with 2 big CPUS, the power consumption estimation
> conforms with the expected one.
> 
> Before this change:
> 
> ~$ ~/dhrystone -t 1 -l 10000&
> ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
> 2260000
> 
> After this change:
> 
> ~$ ~/dhrystone -t 1 -l 10000&
> ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
> 1130000
> 
> ~$ ~/dhrystone -t 2 -l 10000&
> ~$ cat /sys/devices/virtual/powercap/dtpm/dtpm:0/dtpm:0:1/constraint_0_max_power_uw
> 2260000
> 
> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
> ---
> 
> V3:
>    - Fixed uninitialized 'cpu' in scaled_power_uw()
> V2:
>    - Replaced cpumask by em_span_cpus
>    - Changed 'util' metrics variable types
>    - Optimized utilization scaling power computation
>    - Renamed parameter name for scale_pd_power_uw()
> ---
>   drivers/powercap/dtpm_cpu.c | 46 +++++++++++++++++++++++++++++++------
>   1 file changed, 39 insertions(+), 7 deletions(-)
> 
> diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
> index ac7f2e7e262f..47854923d958 100644
> --- a/drivers/powercap/dtpm_cpu.c
> +++ b/drivers/powercap/dtpm_cpu.c
> @@ -68,27 +68,59 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
>   	return power_limit;
>   }
>   
> +static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
> +{
> +	unsigned long max = 0, sum_util = 0;
> +	int cpu;
> +
> +	for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
> +
> +		/*
> +		 * The capacity is the same for all CPUs belonging to
> +		 * the same perf domain, so a single call to
> +		 * arch_scale_cpu_capacity() is enough. However, we
> +		 * need the CPU parameter to be initialized by the
> +		 * loop, so the call ends up in this block.
> +		 *
> +		 * We can initialize 'max' with a cpumask_first() call
> +		 * before the loop but the bits computation is not
> +		 * worth given the arch_scale_cpu_capacity() just
> +		 * returns a value where the resulting assembly code
> +		 * will be optimized by the compiler.
> +		 */
> +		max = arch_scale_cpu_capacity(cpu);
> +		sum_util += sched_cpu_util(cpu, max);
> +	}
> +
> +	/*
> +	 * In the improbable case where all the CPUs of the perf
> +	 * domain are offline, 'max' will be zero and will lead to an
> +	 * illegal operation with a zero division.
> +	 */
> +	return max ? (power * ((sum_util << 10) / max)) >> 10 : 0;
> +}
> +
>   static u64 get_pd_power_uw(struct dtpm *dtpm)
>   {
>   	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
>   	struct em_perf_domain *pd;
> -	struct cpumask cpus;
> +	struct cpumask *pd_mask;
>   	unsigned long freq;
> -	int i, nr_cpus;
> +	int i;
>   
>   	pd = em_cpu_get(dtpm_cpu->cpu);
> -	freq = cpufreq_quick_get(dtpm_cpu->cpu);
>   
> -	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
> -	nr_cpus = cpumask_weight(&cpus);
> +	pd_mask = em_span_cpus(pd);
> +
> +	freq = cpufreq_quick_get(dtpm_cpu->cpu);
>   
>   	for (i = 0; i < pd->nr_perf_states; i++) {
>   
>   		if (pd->table[i].frequency < freq)
>   			continue;
>   
> -		return pd->table[i].power *
> -			MICROWATT_PER_MILLIWATT * nr_cpus;
> +		return scale_pd_power_uw(pd_mask, pd->table[i].power *
> +					 MICROWATT_PER_MILLIWATT);
>   	}
>   
>   	return 0;
> 

LGTM

Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>

Re: [PATCH v3 1/5] powercap/drivers/dtpm: Encapsulate even more the code

[Lukasz Luba]

Hi Daniel,

On 3/10/21 11:02 AM, Daniel Lezcano wrote:
> In order to increase the self-encapsulation of the dtpm generic code,
> the following changes are adding a power update ops to the dtpm
> ops. That allows the generic code to call directly the dtpm backend
> function to update the power values.
> 
> The power update function does compute the power characteristics when
> the function is invoked. In the case of the CPUs, the power
> consumption depends on the number of online CPUs. The online CPUs mask
> is not up to date at CPUHP_AP_ONLINE_DYN state in the tear down
> callback. That is the reason why the online / offline are at separate
> state. As there is already an existing state for DTPM, this one is
> only moved to the DEAD state, so there is no addition of new state
> with these changes. The dtpm node is not removed when the cpu is
> unplugged.
> 
> That simplifies the code for the next changes and results in a more
> self-encapsulated code.
> 
> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
> ---
> V2:
>   - Updated the changelog with the CPU node not being removed
>   - Commented the cpu hotplug callbacks to explain why there are two callbacks
>   - Changed 'upt_power_uw' to 'update_power_uw'
>   - Removed unused cpumask variable
> ---
>   drivers/powercap/dtpm.c     |  54 ++++++-------
>   drivers/powercap/dtpm_cpu.c | 148 ++++++++++++++++--------------------
>   include/linux/cpuhotplug.h  |   2 +-
>   include/linux/dtpm.h        |   3 +-
>   4 files changed, 97 insertions(+), 110 deletions(-)
> 

[snip]

> @@ -210,27 +175,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
>   	for_each_cpu(cpu, policy->related_cpus)
>   		per_cpu(dtpm_per_cpu, cpu) = dtpm;
>   
> -	sprintf(name, "cpu%d", dtpm_cpu->cpu);
> +	sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);

We should be safe in normal platforms, since there is less than
< 300 cores. although, I would use 2x CPUFREQ_NAME_LEN array.

Other than that

Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>

Regards,
Lukasz

Re: [PATCH v3 2/5] powercap/drivers/dtpm: Create a registering system

[Lukasz Luba]

On 3/10/21 11:02 AM, Daniel Lezcano wrote:
> A SoC can be differently structured depending on the platform and the
> kernel can not be aware of all the combinations, as well as the
> specific tweaks for a particular board.
> 
> The creation of the hierarchy must be delegated to userspace.
> 
> These changes provide a registering mechanism where the different
> subsystems will initialize their dtpm backends and register with a
> name the dtpm node in a list.
> 
> The next changes will provide an userspace interface to create
> hierachically the different nodes. Those will be created by name and

s/hierachically/hierarchically

> found via the list filled by the different subsystem.
> 
> If a specified name is not found in the list, it is assumed to be a
> virtual node which will have children and the default is to allocate
> such node.
> 
> When the node register in the list, the function will be dtpm_register
> where the previous semantic was to create the node. Thus, the
> functions are renamed to reflect their purpose.
> 
> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
> ---
> 
>   V2:
>     - Fixed error code path by dropping lock
> ---
>   drivers/powercap/dtpm.c     | 161 ++++++++++++++++++++++++++++++++++--
>   drivers/powercap/dtpm_cpu.c |   4 +-
>   include/linux/dtpm.h        |  12 ++-
>   3 files changed, 164 insertions(+), 13 deletions(-)
> 

apart from the above, LGTM

Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>

Re: [PATCH v3 1/5] powercap/drivers/dtpm: Encapsulate even more the code

[Daniel Lezcano]

On 11/03/2021 11:15, Lukasz Luba wrote:
> Hi Daniel,
> 
> On 3/10/21 11:02 AM, Daniel Lezcano wrote:
>> In order to increase the self-encapsulation of the dtpm generic code,
>> the following changes are adding a power update ops to the dtpm
>> ops. That allows the generic code to call directly the dtpm backend
>> function to update the power values.
>>
>> The power update function does compute the power characteristics when
>> the function is invoked. In the case of the CPUs, the power
>> consumption depends on the number of online CPUs. The online CPUs mask
>> is not up to date at CPUHP_AP_ONLINE_DYN state in the tear down
>> callback. That is the reason why the online / offline are at separate
>> state. As there is already an existing state for DTPM, this one is
>> only moved to the DEAD state, so there is no addition of new state
>> with these changes. The dtpm node is not removed when the cpu is
>> unplugged.
>>
>> That simplifies the code for the next changes and results in a more
>> self-encapsulated code.
>>
>> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
>> ---
>> V2:
>>   - Updated the changelog with the CPU node not being removed
>>   - Commented the cpu hotplug callbacks to explain why there are two
>> callbacks
>>   - Changed 'upt_power_uw' to 'update_power_uw'
>>   - Removed unused cpumask variable
>> ---
>>   drivers/powercap/dtpm.c     |  54 ++++++-------
>>   drivers/powercap/dtpm_cpu.c | 148 ++++++++++++++++--------------------
>>   include/linux/cpuhotplug.h  |   2 +-
>>   include/linux/dtpm.h        |   3 +-
>>   4 files changed, 97 insertions(+), 110 deletions(-)
>>
> 
> [snip]
> 
>> @@ -210,27 +175,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
>>       for_each_cpu(cpu, policy->related_cpus)
>>           per_cpu(dtpm_per_cpu, cpu) = dtpm;
>>   -    sprintf(name, "cpu%d", dtpm_cpu->cpu);
>> +    sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);
> 
> We should be safe in normal platforms, since there is less than
> < 300 cores. although, I would use 2x CPUFREQ_NAME_LEN array.

I'm counting 9999 cores.

We have:
#define CPUFREQ_NAME_LEN 16

"cpu-cpufreq\0" counts 12 characters.

There are 4 characters left, 9999 max then, no ?

The code is designed for cpufreq with the energy model which targets
ARM64 architecture and AFAICT we are far away of having so many cores on
our phones.

Except I'm wrong, I would prefer to keep the current CPUFREQ_NAME_LEN to
not introduce subtle bugs (like stack overflow) if the length is
increased in cpufreq.h.

What do you think ?

> Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
> 
> Regards,
> Lukasz
> 


-- 
<http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog

Re: [PATCH v3 1/5] powercap/drivers/dtpm: Encapsulate even more the code

[Lukasz Luba]

On 3/11/21 10:57 AM, Daniel Lezcano wrote:
> On 11/03/2021 11:15, Lukasz Luba wrote:
>> Hi Daniel,
>>
>> On 3/10/21 11:02 AM, Daniel Lezcano wrote:
>>> In order to increase the self-encapsulation of the dtpm generic code,
>>> the following changes are adding a power update ops to the dtpm
>>> ops. That allows the generic code to call directly the dtpm backend
>>> function to update the power values.
>>>
>>> The power update function does compute the power characteristics when
>>> the function is invoked. In the case of the CPUs, the power
>>> consumption depends on the number of online CPUs. The online CPUs mask
>>> is not up to date at CPUHP_AP_ONLINE_DYN state in the tear down
>>> callback. That is the reason why the online / offline are at separate
>>> state. As there is already an existing state for DTPM, this one is
>>> only moved to the DEAD state, so there is no addition of new state
>>> with these changes. The dtpm node is not removed when the cpu is
>>> unplugged.
>>>
>>> That simplifies the code for the next changes and results in a more
>>> self-encapsulated code.
>>>
>>> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
>>> ---
>>> V2:
>>>    - Updated the changelog with the CPU node not being removed
>>>    - Commented the cpu hotplug callbacks to explain why there are two
>>> callbacks
>>>    - Changed 'upt_power_uw' to 'update_power_uw'
>>>    - Removed unused cpumask variable
>>> ---
>>>    drivers/powercap/dtpm.c     |  54 ++++++-------
>>>    drivers/powercap/dtpm_cpu.c | 148 ++++++++++++++++--------------------
>>>    include/linux/cpuhotplug.h  |   2 +-
>>>    include/linux/dtpm.h        |   3 +-
>>>    4 files changed, 97 insertions(+), 110 deletions(-)
>>>
>>
>> [snip]
>>
>>> @@ -210,27 +175,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
>>>        for_each_cpu(cpu, policy->related_cpus)
>>>            per_cpu(dtpm_per_cpu, cpu) = dtpm;
>>>    -    sprintf(name, "cpu%d", dtpm_cpu->cpu);
>>> +    sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);
>>
>> We should be safe in normal platforms, since there is less than
>> < 300 cores. although, I would use 2x CPUFREQ_NAME_LEN array.
> 
> I'm counting 9999 cores.
> 
> We have:
> #define CPUFREQ_NAME_LEN 16
> 
> "cpu-cpufreq\0" counts 12 characters.
> 
> There are 4 characters left, 9999 max then, no ?

Yes, my '< 300' was referring to some server platforms,
which IIRC had 2 sockets, each with 128 cores. I don't
know about future, though.

> 
> The code is designed for cpufreq with the energy model which targets
> ARM64 architecture and AFAICT we are far away of having so many cores on
> our phones.

True, otherwise with such big number of cores in mobile, we would face
probably more hard to investigate issues, than this simple one ;)

> 
> Except I'm wrong, I would prefer to keep the current CPUFREQ_NAME_LEN to
> not introduce subtle bugs (like stack overflow) if the length is
> increased in cpufreq.h.
> 
> What do you think ?

Agree, please skip my former comment and just take the reviewed tag.

> 
>> Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
>>
>> Regards,
>> Lukasz
>>
> 
> 

Re: [PATCH v3 1/5] powercap/drivers/dtpm: Encapsulate even more the code

[Lukasz Luba]

On 3/12/21 10:11 AM, Lukasz Luba wrote:
> 
> 
> On 3/11/21 10:57 AM, Daniel Lezcano wrote:
>> On 11/03/2021 11:15, Lukasz Luba wrote:
>>> Hi Daniel,
>>>
>>> On 3/10/21 11:02 AM, Daniel Lezcano wrote:
>>>> In order to increase the self-encapsulation of the dtpm generic code,
>>>> the following changes are adding a power update ops to the dtpm
>>>> ops. That allows the generic code to call directly the dtpm backend
>>>> function to update the power values.
>>>>
>>>> The power update function does compute the power characteristics when
>>>> the function is invoked. In the case of the CPUs, the power
>>>> consumption depends on the number of online CPUs. The online CPUs mask
>>>> is not up to date at CPUHP_AP_ONLINE_DYN state in the tear down
>>>> callback. That is the reason why the online / offline are at separate
>>>> state. As there is already an existing state for DTPM, this one is
>>>> only moved to the DEAD state, so there is no addition of new state
>>>> with these changes. The dtpm node is not removed when the cpu is
>>>> unplugged.
>>>>
>>>> That simplifies the code for the next changes and results in a more
>>>> self-encapsulated code.
>>>>
>>>> Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org>
>>>> ---
>>>> V2:
>>>>    - Updated the changelog with the CPU node not being removed
>>>>    - Commented the cpu hotplug callbacks to explain why there are two
>>>> callbacks
>>>>    - Changed 'upt_power_uw' to 'update_power_uw'
>>>>    - Removed unused cpumask variable
>>>> ---
>>>>    drivers/powercap/dtpm.c     |  54 ++++++-------
>>>>    drivers/powercap/dtpm_cpu.c | 148 
>>>> ++++++++++++++++--------------------
>>>>    include/linux/cpuhotplug.h  |   2 +-
>>>>    include/linux/dtpm.h        |   3 +-
>>>>    4 files changed, 97 insertions(+), 110 deletions(-)
>>>>
>>>
>>> [snip]
>>>
>>>> @@ -210,27 +175,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int 
>>>> cpu)
>>>>        for_each_cpu(cpu, policy->related_cpus)
>>>>            per_cpu(dtpm_per_cpu, cpu) = dtpm;
>>>>    -    sprintf(name, "cpu%d", dtpm_cpu->cpu);
>>>> +    sprintf(name, "cpu%d-cpufreq", dtpm_cpu->cpu);
>>>
>>> We should be safe in normal platforms, since there is less than
>>> < 300 cores. although, I would use 2x CPUFREQ_NAME_LEN array.
>>
>> I'm counting 9999 cores.
>>
>> We have:
>> #define CPUFREQ_NAME_LEN 16
>>
>> "cpu-cpufreq\0" counts 12 characters.
>>
>> There are 4 characters left, 9999 max then, no ?
> 
> Yes, my '< 300' was referring to some server platforms,
> which IIRC had 2 sockets, each with 128 cores. I don't
> know about future, though.
> 
>>
>> The code is designed for cpufreq with the energy model which targets
>> ARM64 architecture and AFAICT we are far away of having so many cores on
>> our phones.
> 
> True, otherwise with such big number of cores in mobile, we would face
> probably more hard to investigate issues, than this simple one ;)
> 
>>
>> Except I'm wrong, I would prefer to keep the current CPUFREQ_NAME_LEN to
>> not introduce subtle bugs (like stack overflow) if the length is
>> increased in cpufreq.h.
>>
>> What do you think ?
> 
> Agree, please skip my former comment and just take the reviewed tag.

What you could do, though, is to use:

snprintf(name, sizeof(name), "cpu%d-cpufreq", dtpm_cpu->cpu);

just to play safe.