powercap/drivers/dtpm: Encapsulate even more the code

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 <[email protected]>

---
  drivers/powercap/dtpm.c     | 158 ++++++++++++++++++++++++++++++++++--
  drivers/powercap/dtpm_cpu.c |   4 +-
  include/linux/dtpm.h        |  12 ++-
  3 files changed, 161 insertions(+), 13 deletions(-)

drivers/powercap/dtpm.c +80 -0

index 1085dccf9c58..20728a28ff0d 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 +161,135 @@ 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;

drivers/powercap/dtpm.c +17 -0

+		return -ENOMEM;
+	}
+
+	node->dtpm = dtpm;
+
+	list_add(&node->node, &dtpm_list);
+
+	pr_info("Registered %s\n", name);
+
+	mutex_unlock(&dtpm_lock);
+
+	return 0;
+}
+
+/**
+ * dtpm_unregister - Remove the dtpm device from the list
+ * @name: the dtpm device name to be removed

drivers/powercap/dtpm.c +27 -9

+
+		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 +346,7 @@ int dtpm_release_zone(struct powercap_zone *pcz)
  	if (root == dtpm)
  		root = NULL;
 
-	kfree(dtpm);
+	dtpm_put(dtpm);
 
  	return 0;
  }

@@ -370,6 +508,7 @@ 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 +517,29 @@ 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 +553,7 @@ 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 +597,7 @@ int dtpm_register(const char *name, struct dtpm *dtpm, struct dtpm *parent)
  	if (dtpm->ops && !dtpm->ops->upt_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);

drivers/powercap/dtpm_cpu.c +2 -2

index aff79c649345..1a10537c4434 100644
@@ -180,7 +180,7 @@ 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;
 

@@ -193,7 +193,7 @@ 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;
 

include/linux/dtpm.h +10 -2

index d29be6a0e513..447ea6c60b59 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

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 <[email protected]>

---
  drivers/powercap/dtpm.c     |  4 ++--
  drivers/powercap/dtpm_cpu.c |  4 +++-
  include/linux/dtpm.h        | 22 +++++++++-------------
  3 files changed, 14 insertions(+), 16 deletions(-)

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 <[email protected]>

---
  drivers/powercap/dtpm.c     | 27 ++++++++++------------
  drivers/powercap/dtpm_cpu.c | 46 ++++++++++++++++++-------------------
  include/linux/dtpm.h        |  3 +--
  3 files changed, 35 insertions(+), 41 deletions(-)

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 <[email protected]>

---
  drivers/powercap/dtpm_cpu.c | 21 +++++++++++++++++----
  1 file changed, 17 insertions(+), 4 deletions(-)

drivers/powercap/dtpm_cpu.c +0 -0

index e728ebd6d0ca..8379b96468ef 100644

Quoted 1 line

  +static u64 scale_pd_power_uw(struct cpumask *cpus, u64 power)

renamed 'cpus' into 'pd_mask', see below

Quoted 3 lines

+{
+    unsigned long max, util;
+    int cpu, load = 0;

IMHO 'int load' looks odd when used with 'util' and 'max'. I would put in the line above to have them all the same type and renamed to 'sum_util'.

Quoted 2 lines

+
+    for_each_cpu(cpu, cpus) {

I would avoid the temporary CPU mask in the get_pd_power_uw() with this modified loop:

for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {

Quoted 3 lines

+        max = arch_scale_cpu_capacity(cpu);
+        util = sched_cpu_util(cpu, max);
+        load += ((util * 100) / max);

Below you can find 3 optimizations. Since we are not in the hot path here, it's up to if you would like to use all/some of them or just ignore.

1st optimization.
If we use 'load += (util << 10) / max' in the loop, then we could avoid div by 100 and use a right shift:
(power * load) >> 10

2nd optimization.
Since we use EM CPU mask, which span all CPUs with the same arch_scale_cpu_capacity(), you can avoid N divs inside the loop and do it once, below the loop.

3rd optimization.
If we just simply add all 'util' into 'sum_util' (no mul or div in the loop), then we might just have simple macro

#define CALC_POWER_USAGE(power, sum_util, max) \
    (((power * (sum_util << 10)) / max) >> 10)

Hi Lukasz,

thanks for your comments, one question below.

On 09/03/2021 11:01, Lukasz Luba wrote:

[ ... ]

Quoted 43 lines

Quoted 1 line

  +static u64 scale_pd_power_uw(struct cpumask *cpus, u64 power)

renamed 'cpus' into 'pd_mask', see below

Quoted 3 lines

+{
+    unsigned long max, util;
+    int cpu, load = 0;

IMHO 'int load' looks odd when used with 'util' and 'max'. I would put in the line above to have them all the same type and renamed to 'sum_util'.

Quoted 2 lines

+
+    for_each_cpu(cpu, cpus) {

I would avoid the temporary CPU mask in the get_pd_power_uw() with this modified loop:

for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {

Quoted 3 lines

+        max = arch_scale_cpu_capacity(cpu);
+        util = sched_cpu_util(cpu, max);
+        load += ((util * 100) / max);

Below you can find 3 optimizations. Since we are not in the hot path here, it's up to if you would like to use all/some of them or just ignore.

1st optimization.
If we use 'load += (util << 10) / max' in the loop, then we could avoid div by 100 and use a right shift:
(power * load) >> 10

2nd optimization.
Since we use EM CPU mask, which span all CPUs with the same arch_scale_cpu_capacity(), you can avoid N divs inside the loop and do it once, below the loop.

3rd optimization.
If we just simply add all 'util' into 'sum_util' (no mul or div in the loop), then we might just have simple macro

Quoted 2 lines

#define CALC_POWER_USAGE(power, sum_util, max) \
    (((power * (sum_util << 10)) / max) >> 10)

I don't understand the 'max' division, I was expecting here something
like: ((sum_util << 10) / sum_max) >> 10)

no ?

Hi Daniel,

I've started reviewing the series, please find some comments below.

Quoted 44 lines · 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 <[email protected]>

---
  drivers/powercap/dtpm_cpu.c | 21 +++++++++++++++++----

  1 file changed, 17 insertions(+), 4 deletions(-)

drivers/powercap/dtpm_cpu.c +0 -0

index e728ebd6d0ca..8379b96468ef 100644

drivers/powercap/dtpm_cpu.c static u64 set_pd_power_limit(struct dtpm *dtpm, · line 71

Quoted 4 lines

drivers/powercap/dtpm_cpu.c +0 -0

@@ -68,27 +68,40 @@ static u64 set_pd_power_limit(struct dtpm *dtpm,
 u64 power_limit)
       return power_limit;
   }
   +static u64 scale_pd_power_uw(struct cpumask *cpus, u64 power)

renamed 'cpus' into 'pd_mask', see below

drivers/powercap/dtpm_cpu.c static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) · line 74

Quoted 3 lines

drivers/powercap/dtpm_cpu.c +3 -0

+{
+    unsigned long max, util;
+    int cpu, load = 0;

IMHO 'int load' looks odd when used with 'util' and 'max'. I would put in the line above to have them all the same type and renamed to 'sum_util'.

drivers/powercap/dtpm_cpu.c static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) · line 76

Quoted 2 lines

drivers/powercap/dtpm_cpu.c +2 -0

+
+    for_each_cpu(cpu, cpus) {

I would avoid the temporary CPU mask in the get_pd_power_uw() with this modified loop:

for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {

drivers/powercap/dtpm_cpu.c static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit) · line 79

Quoted 3 lines

drivers/powercap/dtpm_cpu.c +3 -0

+        max = arch_scale_cpu_capacity(cpu);
+        util = sched_cpu_util(cpu, max);
+        load += ((util * 100) / max);

Below you can find 3 optimizations. Since we are not in the hot path here, it's up to if you would like to use all/some of them or just ignore.

1st optimization.
If we use 'load += (util << 10) / max' in the loop, then we could avoid div by 100 and use a right shift:
(power * load) >> 10

2nd optimization.
Since we use EM CPU mask, which span all CPUs with the same arch_scale_cpu_capacity(), you can avoid N divs inside the loop and do it once, below the loop.

3rd optimization.
If we just simply add all 'util' into 'sum_util' (no mul or div in the loop), then we might just have simple macro

#define CALC_POWER_USAGE(power, sum_util, max) \
    (((power * (sum_util << 10)) / max) >> 10)

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.

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

Signed-off-by Daniel Lezcano <[email protected]>

---
 drivers/powercap/dtpm.c     |  54 ++++++++--------
 drivers/powercap/dtpm_cpu.c | 124 +++++++++++++-----------------------
 include/linux/cpuhotplug.h  |   2 +-
 include/linux/dtpm.h        |   3 +-
 4 files changed, 76 insertions(+), 107 deletions(-)

drivers/powercap/dtpm.c +27 -27

index c2185ec5f887..1085dccf9c58 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->upt_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->upt_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->upt_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);

drivers/powercap/dtpm_cpu.c +46 -78

index 51c366938acd..aff79c649345 100644
@@ -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 upt_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;

@@ -141,37 +122,25 @@ 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,
+	.upt_power_uw = upt_pd_power_uw,
 	.release = pd_release,
 };
 
 static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
 {
-	struct cpufreq_policy *policy;
+	struct cpumask cpus;
 	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;
+	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
 
-	dtpm_unregister(dtpm);
+	dtpm = per_cpu(dtpm_per_cpu, cpu);
 
-	return 0;
+	return dtpm_update_power(dtpm);
 }
 
 static int cpuhp_dtpm_cpu_online(unsigned int cpu)

@@ -184,7 +153,6 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 	int ret = -ENOMEM;
 
 	policy = cpufreq_cpu_get(cpu);
-
 	if (!policy)
 		return 0;
 

@@ -194,7 +162,7 @@ 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 +178,20 @@ 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 +209,17 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
 int dtpm_register_cpu(struct dtpm *parent)
 {
-	__parent = parent;
+	int ret;
 
-	return cpuhp_setup_state(CPUHP_AP_DTPM_CPU_ONLINE,
-				 "dtpm_cpu:online",
-				 cpuhp_dtpm_cpu_online,
-				 cpuhp_dtpm_cpu_offline);
+	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 0;
 }

include/linux/cpuhotplug.h +1 -1

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,
 };

include/linux/dtpm.h +2 -1

index e80a332e3d8a..d29be6a0e513 100644
@@ -29,6 +29,7 @@ struct dtpm {
 struct dtpm_ops {
 	u64 (*set_power_uw)(struct dtpm *, u64);
 	u64 (*get_power_uw)(struct dtpm *);
+	int (*upt_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);
 

Quoted 14 lines · 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.

Quoted 4 lines

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

Signed-off-by Daniel Lezcano <[email protected]>

Is there any comment on this series ?

Hi Daniel,

Quoted 16 lines · Daniel Lezcano

Quoted 14 lines · 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.

Quoted 6 lines

Quoted 4 lines

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

Signed-off-by Daniel Lezcano <[email protected]>

Is there any comment on this series ?

If you can wait 1 day, I will review it tomorrow...

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.

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

Signed-off-by Daniel Lezcano <[email protected]>

---
  drivers/powercap/dtpm.c     |  54 ++++++++--------
  drivers/powercap/dtpm_cpu.c | 124 +++++++++++++-----------------------
  include/linux/cpuhotplug.h  |   2 +-
  include/linux/dtpm.h        |   3 +-
  4 files changed, 76 insertions(+), 107 deletions(-)

drivers/powercap/dtpm.c +27 -27

index c2185ec5f887..1085dccf9c58 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->upt_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->upt_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->upt_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);

drivers/powercap/dtpm_cpu.c +4 -44

index 51c366938acd..aff79c649345 100644
@@ -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);
 

drivers/powercap/dtpm_cpu.c +16 -0

+	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;

drivers/powercap/dtpm_cpu.c +0 -5

  	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;
 

drivers/powercap/dtpm_cpu.c +6 -14

-	dtpm_unregister(dtpm);
+	dtpm = per_cpu(dtpm_per_cpu, cpu);
 
-	return 0;
+	return dtpm_update_power(dtpm);
  }
 
  static int cpuhp_dtpm_cpu_online(unsigned int cpu)

@@ -184,7 +153,6 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
  	int ret = -ENOMEM;
 
  	policy = cpufreq_cpu_get(cpu);
-
  	if (!policy)
  		return 0;
 

@@ -194,7 +162,7 @@ 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 +178,20 @@ 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 +209,17 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
  int dtpm_register_cpu(struct dtpm *parent)

drivers/powercap/dtpm_cpu.c +4 -0

+	if (ret < 0)
+		return ret;
+
+	return 0;
  }

include/linux/cpuhotplug.h +1 -1

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,
  };

include/linux/dtpm.h +0 -0

index e80a332e3d8a..d29be6a0e513 100644

include/linux/dtpm.h +1 -1

  	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);