[PATCH v4 09/18] PM: EM: Introduce runtime modifiable table

[Lukasz Luba]

The new runtime table would be populated with a new power data to better
reflect the actual power. 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 data
at runtime safely.

The runtime modifiable EM data is used by the Energy Aware Scheduler (EAS)
for the task placement. All the other users (thermal, etc.) are still
using the default (basic) EM. This fact drove the design of this feature.

Signed-off-by: Lukasz Luba <lukasz.luba@xxxxxxx>
---
 include/linux/energy_model.h |  4 +++-
 kernel/power/energy_model.c  | 12 +++++++++++-
 2 files changed, 14 insertions(+), 2 deletions(-)

diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index 546dee90f716..740e7c25cfff 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -39,7 +39,7 @@ struct em_perf_state {
 /**
  * struct em_perf_table - Performance states table
  * @state:	List of performance states, in ascending order
- * @rcu:	RCU used for safe access and destruction
+ * @rcu:	RCU used only for runtime modifiable table
  */
 struct em_perf_table {
 	struct em_perf_state *state;
@@ -49,6 +49,7 @@ struct em_perf_table {
 /**
  * struct em_perf_domain - Performance domain
  * @default_table:	Pointer to the default em_perf_table
+ * @runtime_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
@@ -64,6 +65,7 @@ struct em_perf_table {
  */
 struct em_perf_domain {
 	struct em_perf_table *default_table;
+	struct em_perf_table __rcu *runtime_table;
 	int nr_perf_states;
 	unsigned long flags;
 	unsigned long cpus[];
diff --git a/kernel/power/energy_model.c b/kernel/power/energy_model.c
index 797141638b29..5b40db38b745 100644
--- a/kernel/power/energy_model.c
+++ b/kernel/power/energy_model.c
@@ -251,6 +251,9 @@ static int em_create_pd(struct device *dev, int nr_states,
 		return ret;
 	}
 
+	/* Initialize runtime table as default table. */
+	rcu_assign_pointer(pd->runtime_table, default_table);
+
 	if (_is_cpu_device(dev))
 		for_each_cpu(cpu, cpus) {
 			cpu_dev = get_cpu_device(cpu);
@@ -448,6 +451,7 @@ EXPORT_SYMBOL_GPL(em_dev_register_perf_domain);
  */
 void em_dev_unregister_perf_domain(struct device *dev)
 {
+	struct em_perf_table __rcu *runtime_table;
 	struct em_perf_domain *pd;
 
 	if (IS_ERR_OR_NULL(dev) || !dev->em_pd)
@@ -457,18 +461,24 @@ void em_dev_unregister_perf_domain(struct device *dev)
 		return;
 
 	pd = dev->em_pd;
-
 	/*
 	 * The mutex separates all register/unregister requests and protects
 	 * from potential clean-up/setup issues in the debugfs directories.
 	 * The debugfs directory name is the same as device's name.
 	 */
 	mutex_lock(&em_pd_mutex);
+
 	em_debug_remove_pd(dev);
 
+	runtime_table = pd->runtime_table;
+
+	rcu_assign_pointer(pd->runtime_table, NULL);
+	synchronize_rcu();
+
 	kfree(pd->default_table->state);
 	kfree(pd->default_table);
 	kfree(dev->em_pd);
+
 	dev->em_pd = NULL;
 	mutex_unlock(&em_pd_mutex);
 }
-- 
2.25.1