powercap/drivers/dtpm: Encapsulate even more the code

index c2185ec5f887..58433b8ef9a1 100644
@@ -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);

240 lines not on this page · raw message

index ee09a39627d6..fcb2967fb5ba 100644
@@ -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,
 };

index e80a332e3d8a..acf8d3638988 100644
@@ -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);
 

index 58433b8ef9a1..d00f55f0ee30 100644
@@ -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);

index f6076de39540..8592a78e47e4 100644
@@ -177,7 +177,7 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
 	snprintf(name, sizeof(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;
 

index acf8d3638988..d724c5a7b2f4 100644
@@ -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

index d00f55f0ee30..74d9603bd42a 100644
@@ -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;
 }

index 8592a78e47e4..c4fa35fabc40 100644
@@ -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);

index d724c5a7b2f4..5f71ddc18ee9 100644
@@ -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);

index 74d9603bd42a..a4784ac2f79b 100644
@@ -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);

121 lines not on this page · raw message

index 5f71ddc18ee9..4f7ad21291e6 100644
@@ -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);
 

index 1c6d1e54691f..e120ea239d75 100644
@@ -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;