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()
  ...

4 files changed, 130 insertions, 39 deletions

diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index ae7ee611978b..bc90126f1b5f 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -42,6 +42,7 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 {
 	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *pd = em_cpu_get(dtpm_cpu->cpu);
+	struct em_perf_state *table;
 	struct cpumask cpus;
 	unsigned long freq;
 	u64 power;
@@ -50,20 +51,22 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
 	nr_cpus = cpumask_weight(&cpus);
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
 	for (i = 0; i < pd->nr_perf_states; i++) {
 
-		power = pd->table[i].power * nr_cpus;
+		power = table[i].power * nr_cpus;
 
 		if (power > power_limit)
 			break;
 	}
 
-	freq = pd->table[i - 1].frequency;
+	freq = table[i - 1].frequency;
+	power_limit = table[i - 1].power * nr_cpus;
+	rcu_read_unlock();
 
 	freq_qos_update_request(&dtpm_cpu->qos_req, freq);
 
-	power_limit = pd->table[i - 1].power * nr_cpus;
-
 	return power_limit;
 }
 
@@ -87,9 +90,11 @@ static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
 static u64 get_pd_power_uw(struct dtpm *dtpm)
 {
 	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
+	struct em_perf_state *table;
 	struct em_perf_domain *pd;
 	struct cpumask *pd_mask;
 	unsigned long freq;
+	u64 power = 0;
 	int i;
 
 	pd = em_cpu_get(dtpm_cpu->cpu);
@@ -98,33 +103,43 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 
 	freq = cpufreq_quick_get(dtpm_cpu->cpu);
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
 	for (i = 0; i < pd->nr_perf_states; i++) {
 
-		if (pd->table[i].frequency < freq)
+		if (table[i].frequency < freq)
 			continue;
 
-		return scale_pd_power_uw(pd_mask, pd->table[i].power);
+		power = scale_pd_power_uw(pd_mask, table[i].power);
+		break;
 	}
+	rcu_read_unlock();
 
-	return 0;
+	return power;
 }
 
 static int update_pd_power_uw(struct dtpm *dtpm)
 {
 	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
 	struct em_perf_domain *em = em_cpu_get(dtpm_cpu->cpu);
+	struct em_perf_state *table;
 	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;
+	rcu_read_lock();
+	table = em_perf_state_from_pd(em);
+
+	dtpm->power_min = table[0].power;
 	dtpm->power_min *= nr_cpus;
 
-	dtpm->power_max = em->table[em->nr_perf_states - 1].power;
+	dtpm->power_max = table[em->nr_perf_states - 1].power;
 	dtpm->power_max *= nr_cpus;
 
+	rcu_read_unlock();
+
 	return 0;
 }
 
@@ -143,7 +158,7 @@ static void pd_release(struct dtpm *dtpm)
 
 		cpufreq_cpu_put(policy);
 	}
-	
+
 	kfree(dtpm_cpu);
 }
 
@@ -180,6 +195,7 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
 {
 	struct dtpm_cpu *dtpm_cpu;
 	struct cpufreq_policy *policy;
+	struct em_perf_state *table;
 	struct em_perf_domain *pd;
 	char name[CPUFREQ_NAME_LEN];
 	int ret = -ENOMEM;
@@ -216,9 +232,12 @@ static int __dtpm_cpu_setup(int cpu, struct dtpm *parent)
 	if (ret)
 		goto out_kfree_dtpm_cpu;
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
 	ret = freq_qos_add_request(&policy->constraints,
 				   &dtpm_cpu->qos_req, FREQ_QOS_MAX,
-				   pd->table[pd->nr_perf_states - 1].frequency);
+				   table[pd->nr_perf_states - 1].frequency);
+	rcu_read_unlock();
 	if (ret < 0)
 		goto out_dtpm_unregister;
 
diff --git a/drivers/powercap/dtpm_devfreq.c b/drivers/powercap/dtpm_devfreq.c
index 612c3b59dd5b..f40bce8176df 100644
--- a/drivers/powercap/dtpm_devfreq.c
+++ b/drivers/powercap/dtpm_devfreq.c
@@ -37,11 +37,16 @@ static int update_pd_power_uw(struct dtpm *dtpm)
 	struct devfreq *devfreq = dtpm_devfreq->devfreq;
 	struct device *dev = devfreq->dev.parent;
 	struct em_perf_domain *pd = em_pd_get(dev);
+	struct em_perf_state *table;
 
-	dtpm->power_min = pd->table[0].power;
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
 
-	dtpm->power_max = pd->table[pd->nr_perf_states - 1].power;
+	dtpm->power_min = table[0].power;
 
+	dtpm->power_max = table[pd->nr_perf_states - 1].power;
+
+	rcu_read_unlock();
 	return 0;
 }
 
@@ -51,20 +56,23 @@ static u64 set_pd_power_limit(struct dtpm *dtpm, u64 power_limit)
 	struct devfreq *devfreq = dtpm_devfreq->devfreq;
 	struct device *dev = devfreq->dev.parent;
 	struct em_perf_domain *pd = em_pd_get(dev);
+	struct em_perf_state *table;
 	unsigned long freq;
 	int i;
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
 	for (i = 0; i < pd->nr_perf_states; i++) {
-		if (pd->table[i].power > power_limit)
+		if (table[i].power > power_limit)
 			break;
 	}
 
-	freq = pd->table[i - 1].frequency;
+	freq = table[i - 1].frequency;
+	power_limit = table[i - 1].power;
+	rcu_read_unlock();
 
 	dev_pm_qos_update_request(&dtpm_devfreq->qos_req, freq);
 
-	power_limit = pd->table[i - 1].power;
-
 	return power_limit;
 }
 
@@ -89,8 +97,9 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 	struct device *dev = devfreq->dev.parent;
 	struct em_perf_domain *pd = em_pd_get(dev);
 	struct devfreq_dev_status status;
+	struct em_perf_state *table;
 	unsigned long freq;
-	u64 power;
+	u64 power = 0;
 	int i;
 
 	mutex_lock(&devfreq->lock);
@@ -100,19 +109,22 @@ static u64 get_pd_power_uw(struct dtpm *dtpm)
 	freq = DIV_ROUND_UP(status.current_frequency, HZ_PER_KHZ);
 	_normalize_load(&status);
 
+	rcu_read_lock();
+	table = em_perf_state_from_pd(pd);
 	for (i = 0; i < pd->nr_perf_states; i++) {
 
-		if (pd->table[i].frequency < freq)
+		if (table[i].frequency < freq)
 			continue;
 
-		power = pd->table[i].power;
+		power = table[i].power;
 		power *= status.busy_time;
 		power >>= 10;
 
-		return power;
+		break;
 	}
+	rcu_read_unlock();
 
-	return 0;
+	return power;
 }
 
 static void pd_release(struct dtpm *dtpm)
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;