PM: EM: Introduce runtime modifiable table

The new runtime table can be populated with a new power data to better
reflect the actual efficiency of the device e.g. CPU. The power can vary
over time e.g. due to the SoC temperature change. Higher temperature can
increase power values. For longer running scenarios, such as game or
camera, when also other devices are used (e.g. GPU, ISP) the CPU power can
change. The new EM framework is able to addresses this issue and change
the EM data at runtime safely.

Reviewed-by: Dietmar Eggemann <[email protected]>
Tested-by: Dietmar Eggemann <[email protected]>
Signed-off-by: Lukasz Luba <[email protected]>
Signed-off-by: Rafael J. Wysocki <[email protected]>

Author: lukaszluba-arm

include/linux/energy_model.h

@@ -36,9 +36,20 @@ struct em_perf_state {
  */
 #define EM_PERF_STATE_INEFFICIENT BIT(0)
 
+/**
+ * struct em_perf_table - Performance states table
+ * @rcu:	RCU used for safe access and destruction
+ * @state:	List of performance states, in ascending order
+ */
+struct em_perf_table {
+	struct rcu_head rcu;
+	struct em_perf_state state[];
+};
+
 /**
  * struct em_perf_domain - Performance domain
  * @table:		List of performance states, in ascending order
+ * @em_table:		Pointer to the runtime modifiable em_perf_table
  * @nr_perf_states:	Number of performance states
  * @flags:		See "em_perf_domain flags"
  * @cpus:		Cpumask covering the CPUs of the domain. It's here
@@ -54,6 +65,7 @@ struct em_perf_state {
  */
 struct em_perf_domain {
 	struct em_perf_state *table;
+	struct em_perf_table __rcu *em_table;
 	int nr_perf_states;
 	unsigned long flags;
 	unsigned long cpus[];

kernel/power/energy_model.c

@@ -23,6 +23,9 @@
  */
 static DEFINE_MUTEX(em_pd_mutex);
 
+static void em_cpufreq_update_efficiencies(struct device *dev,
+					   struct em_perf_state *table);
+
 static bool _is_cpu_device(struct device *dev)
 {
 	return (dev->bus == &cpu_subsys);
@@ -103,6 +106,31 @@ static void em_debug_create_pd(struct device *dev) {}
 static void em_debug_remove_pd(struct device *dev) {}
 #endif
 
+static void em_destroy_table_rcu(struct rcu_head *rp)
+{
+	struct em_perf_table __rcu *table;
+
+	table = container_of(rp, struct em_perf_table, rcu);
+	kfree(table);
+}
+
+static void em_free_table(struct em_perf_table __rcu *table)
+{
+	call_rcu(&table->rcu, em_destroy_table_rcu);
+}
+
+static struct em_perf_table __rcu *
+em_allocate_table(struct em_perf_domain *pd)
+{
+	struct em_perf_table __rcu *table;
+	int table_size;
+
+	table_size = sizeof(struct em_perf_state) * pd->nr_perf_states;
+
+	table = kzalloc(sizeof(*table) + table_size, GFP_KERNEL);
+	return table;
+}
+
 static int em_compute_costs(struct device *dev, struct em_perf_state *table,
 			    struct em_data_callback *cb, int nr_states,
 			    unsigned long flags)
@@ -153,6 +181,24 @@ static int em_allocate_perf_table(struct em_perf_domain *pd,
 	return 0;
 }
 
+static int em_create_runtime_table(struct em_perf_domain *pd)
+{
+	struct em_perf_table __rcu *table;
+	int table_size;
+
+	table = em_allocate_table(pd);
+	if (!table)
+		return -ENOMEM;
+
+	/* Initialize runtime table with existing data */
+	table_size = sizeof(struct em_perf_state) * pd->nr_perf_states;
+	memcpy(table->state, pd->table, table_size);
+
+	rcu_assign_pointer(pd->em_table, table);
+
+	return 0;
+}
+
 static int em_create_perf_table(struct device *dev, struct em_perf_domain *pd,
 				struct em_perf_state *table,
 				struct em_data_callback *cb,
@@ -245,6 +291,10 @@ static int em_create_pd(struct device *dev, int nr_states,
 	if (ret)
 		goto free_pd_table;
 
+	ret = em_create_runtime_table(pd);
+	if (ret)
+		goto free_pd_table;
+
 	if (_is_cpu_device(dev))
 		for_each_cpu(cpu, cpus) {
 			cpu_dev = get_cpu_device(cpu);
@@ -461,6 +511,9 @@ void em_dev_unregister_perf_domain(struct device *dev)
 	em_debug_remove_pd(dev);
 
 	kfree(dev->em_pd->table);
+
+	em_free_table(dev->em_pd->em_table);
+
 	kfree(dev->em_pd);
 	dev->em_pd = NULL;
 	mutex_unlock(&em_pd_mutex);