Merge branch 'pm-em'

Merge Enery Model changes for 6.9-rc1:

 - Allow the Energy Model to be updated dynamically (Lukasz Luba).

* pm-em: (24 commits)
  PM: EM: Fix nr_states warnings in static checks
  Documentation: EM: Update with runtime modification design
  PM: EM: Add em_dev_compute_costs()
  PM: EM: Remove old table
  PM: EM: Change debugfs configuration to use runtime EM table data
  drivers/thermal/devfreq_cooling: Use new Energy Model interface
  drivers/thermal/cpufreq_cooling: Use new Energy Model interface
  powercap/dtpm_devfreq: Use new Energy Model interface to get table
  powercap/dtpm_cpu: Use new Energy Model interface to get table
  PM: EM: Optimize em_cpu_energy() and remove division
  PM: EM: Support late CPUs booting and capacity adjustment
  PM: EM: Add performance field to struct em_perf_state and optimize
  PM: EM: Add em_perf_state_from_pd() to get performance states table
  PM: EM: Introduce em_dev_update_perf_domain() for EM updates
  PM: EM: Add functions for memory allocations for new EM tables
  PM: EM: Use runtime modified EM for CPUs energy estimation in EAS
  PM: EM: Introduce runtime modifiable table
  PM: EM: Split the allocation and initialization of the EM table
  PM: EM: Check if the get_cost() callback is present in em_compute_costs()
  PM: EM: Introduce em_compute_costs()
  ...

2 files changed, 77 insertions, 17 deletions

diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index e2cc7bd30862..9d1b1459700d 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -91,12 +91,16 @@ struct cpufreq_cooling_device {
 static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 			       unsigned int freq)
 {
+	struct em_perf_state *table;
 	int i;
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(cpufreq_cdev->em);
 	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
-		if (freq > cpufreq_cdev->em->table[i].frequency)
+		if (freq > table[i].frequency)
 			break;
 	}
+	rcu_read_unlock();
 
 	return cpufreq_cdev->max_level - i - 1;
 }
@@ -104,16 +108,20 @@ static unsigned long get_level(struct cpufreq_cooling_device *cpufreq_cdev,
 static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev,
 			     u32 freq)
 {
+	struct em_perf_state *table;
 	unsigned long power_mw;
 	int i;
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(cpufreq_cdev->em);
 	for (i = cpufreq_cdev->max_level - 1; i >= 0; i--) {
-		if (freq > cpufreq_cdev->em->table[i].frequency)
+		if (freq > table[i].frequency)
 			break;
 	}
 
-	power_mw = cpufreq_cdev->em->table[i + 1].power;
+	power_mw = table[i + 1].power;
 	power_mw /= MICROWATT_PER_MILLIWATT;
+	rcu_read_unlock();
 
 	return power_mw;
 }
@@ -121,18 +129,24 @@ static u32 cpu_freq_to_power(struct cpufreq_cooling_device *cpufreq_cdev,
 static u32 cpu_power_to_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 			     u32 power)
 {
+	struct em_perf_state *table;
 	unsigned long em_power_mw;
+	u32 freq;
 	int i;
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(cpufreq_cdev->em);
 	for (i = cpufreq_cdev->max_level; i > 0; i--) {
 		/* Convert EM power to milli-Watts to make safe comparison */
-		em_power_mw = cpufreq_cdev->em->table[i].power;
+		em_power_mw = table[i].power;
 		em_power_mw /= MICROWATT_PER_MILLIWATT;
 		if (power >= em_power_mw)
 			break;
 	}
+	freq = table[i].frequency;
+	rcu_read_unlock();
 
-	return cpufreq_cdev->em->table[i].frequency;
+	return freq;
 }
 
 /**
@@ -262,8 +276,9 @@ static int cpufreq_get_requested_power(struct thermal_cooling_device *cdev,
 static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 			       unsigned long state, u32 *power)
 {
-	unsigned int freq, num_cpus, idx;
 	struct cpufreq_cooling_device *cpufreq_cdev = cdev->devdata;
+	unsigned int freq, num_cpus, idx;
+	struct em_perf_state *table;
 
 	/* Request state should be less than max_level */
 	if (state > cpufreq_cdev->max_level)
@@ -272,7 +287,12 @@ static int cpufreq_state2power(struct thermal_cooling_device *cdev,
 	num_cpus = cpumask_weight(cpufreq_cdev->policy->cpus);
 
 	idx = cpufreq_cdev->max_level - state;
-	freq = cpufreq_cdev->em->table[idx].frequency;
+
+	rcu_read_lock();
+	table = em_perf_state_from_pd(cpufreq_cdev->em);
+	freq = table[idx].frequency;
+	rcu_read_unlock();
+
 	*power = cpu_freq_to_power(cpufreq_cdev, freq) * num_cpus;
 
 	return 0;
@@ -378,8 +398,17 @@ static unsigned int get_state_freq(struct cpufreq_cooling_device *cpufreq_cdev,
 #ifdef CONFIG_THERMAL_GOV_POWER_ALLOCATOR
 	/* Use the Energy Model table if available */
 	if (cpufreq_cdev->em) {
+		struct em_perf_state *table;
+		unsigned int freq;
+
 		idx = cpufreq_cdev->max_level - state;
-		return cpufreq_cdev->em->table[idx].frequency;
+
+		rcu_read_lock();
+		table = em_perf_state_from_pd(cpufreq_cdev->em);
+		freq = table[idx].frequency;
+		rcu_read_unlock();
+
+		return freq;
 	}
 #endif
 
diff --git a/drivers/thermal/devfreq_cooling.c b/drivers/thermal/devfreq_cooling.c
index 262e62ab6cf2..50dec24e967a 100644
--- a/drivers/thermal/devfreq_cooling.c
+++ b/drivers/thermal/devfreq_cooling.c
@@ -87,6 +87,7 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
 	struct devfreq_cooling_device *dfc = cdev->devdata;
 	struct devfreq *df = dfc->devfreq;
 	struct device *dev = df->dev.parent;
+	struct em_perf_state *table;
 	unsigned long freq;
 	int perf_idx;
 
@@ -100,7 +101,11 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
 
 	if (dfc->em_pd) {
 		perf_idx = dfc->max_state - state;
-		freq = dfc->em_pd->table[perf_idx].frequency * 1000;
+
+		rcu_read_lock();
+		table = em_perf_state_from_pd(dfc->em_pd);
+		freq = table[perf_idx].frequency * 1000;
+		rcu_read_unlock();
 	} else {
 		freq = dfc->freq_table[state];
 	}
@@ -123,14 +128,21 @@ static int devfreq_cooling_set_cur_state(struct thermal_cooling_device *cdev,
  */
 static int get_perf_idx(struct em_perf_domain *em_pd, unsigned long freq)
 {
-	int i;
+	struct em_perf_state *table;
+	int i, idx = -EINVAL;
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(em_pd);
 	for (i = 0; i < em_pd->nr_perf_states; i++) {
-		if (em_pd->table[i].frequency == freq)
-			return i;
+		if (table[i].frequency != freq)
+			continue;
+
+		idx = i;
+		break;
 	}
+	rcu_read_unlock();
 
-	return -EINVAL;
+	return idx;
 }
 
 static unsigned long get_voltage(struct devfreq *df, unsigned long freq)
@@ -181,6 +193,7 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 	struct devfreq_cooling_device *dfc = cdev->devdata;
 	struct devfreq *df = dfc->devfreq;
 	struct devfreq_dev_status status;
+	struct em_perf_state *table;
 	unsigned long state;
 	unsigned long freq;
 	unsigned long voltage;
@@ -204,7 +217,11 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 			state = dfc->capped_state;
 
 			/* Convert EM power into milli-Watts first */
-			dfc->res_util = dfc->em_pd->table[state].power;
+			rcu_read_lock();
+			table = em_perf_state_from_pd(dfc->em_pd);
+			dfc->res_util = table[state].power;
+			rcu_read_unlock();
+
 			dfc->res_util /= MICROWATT_PER_MILLIWATT;
 
 			dfc->res_util *= SCALE_ERROR_MITIGATION;
@@ -225,7 +242,11 @@ static int devfreq_cooling_get_requested_power(struct thermal_cooling_device *cd
 		_normalize_load(&status);
 
 		/* Convert EM power into milli-Watts first */
-		*power = dfc->em_pd->table[perf_idx].power;
+		rcu_read_lock();
+		table = em_perf_state_from_pd(dfc->em_pd);
+		*power = table[perf_idx].power;
+		rcu_read_unlock();
+
 		*power /= MICROWATT_PER_MILLIWATT;
 		/* Scale power for utilization */
 		*power *= status.busy_time;
@@ -245,13 +266,19 @@ static int devfreq_cooling_state2power(struct thermal_cooling_device *cdev,
 				       unsigned long state, u32 *power)
 {
 	struct devfreq_cooling_device *dfc = cdev->devdata;
+	struct em_perf_state *table;
 	int perf_idx;
 
 	if (state > dfc->max_state)
 		return -EINVAL;
 
 	perf_idx = dfc->max_state - state;
-	*power = dfc->em_pd->table[perf_idx].power;
+
+	rcu_read_lock();
+	table = em_perf_state_from_pd(dfc->em_pd);
+	*power = table[perf_idx].power;
+	rcu_read_unlock();
+
 	*power /= MICROWATT_PER_MILLIWATT;
 
 	return 0;
@@ -264,6 +291,7 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
 	struct devfreq *df = dfc->devfreq;
 	struct devfreq_dev_status status;
 	unsigned long freq, em_power_mw;
+	struct em_perf_state *table;
 	s32 est_power;
 	int i;
 
@@ -288,13 +316,16 @@ static int devfreq_cooling_power2state(struct thermal_cooling_device *cdev,
 	 * Find the first cooling state that is within the power
 	 * budget. The EM power table is sorted ascending.
 	 */
+	rcu_read_lock();
+	table = em_perf_state_from_pd(dfc->em_pd);
 	for (i = dfc->max_state; i > 0; i--) {
 		/* Convert EM power to milli-Watts to make safe comparison */
-		em_power_mw = dfc->em_pd->table[i].power;
+		em_power_mw = table[i].power;
 		em_power_mw /= MICROWATT_PER_MILLIWATT;
 		if (est_power >= em_power_mw)
 			break;
 	}
+	rcu_read_unlock();
 
 	*state = dfc->max_state - i;
 	dfc->capped_state = *state;