1 files changed, 104 insertions, 57 deletions

diff --git a/drivers/powercap/dtpm_cpu.c b/drivers/powercap/dtpm_cpu.c
index b740866b228d..99390ec1481f 100644
--- a/drivers/powercap/dtpm_cpu.c
+++ b/drivers/powercap/dtpm_cpu.c
@@ -21,9 +21,9 @@
 #include <linux/cpuhotplug.h>
 #include <linux/dtpm.h>
 #include <linux/energy_model.h>
+#include <linux/of.h>
 #include <linux/pm_qos.h>
 #include <linux/slab.h>
-#include <linux/units.h>
 
 struct dtpm_cpu {
 	struct dtpm dtpm;
@@ -42,118 +42,121 @@ 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 cpumask cpus;
+	struct em_perf_state *table;
 	unsigned long freq;
 	u64 power;
 	int i, nr_cpus;
 
-	cpumask_and(&cpus, cpu_online_mask, to_cpumask(pd->cpus));
-	nr_cpus = cpumask_weight(&cpus);
+	nr_cpus = cpumask_weight_and(cpu_online_mask, to_cpumask(pd->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 * MICROWATT_PER_MILLIWATT * 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 *
-		MICROWATT_PER_MILLIWATT * nr_cpus;
-
 	return power_limit;
 }
 
 static u64 scale_pd_power_uw(struct cpumask *pd_mask, u64 power)
 {
-	unsigned long max = 0, sum_util = 0;
+	unsigned long max, sum_util = 0;
 	int cpu;
 
-	for_each_cpu_and(cpu, pd_mask, cpu_online_mask) {
-
-		/*
-		 * The capacity is the same for all CPUs belonging to
-		 * the same perf domain, so a single call to
-		 * arch_scale_cpu_capacity() is enough. However, we
-		 * need the CPU parameter to be initialized by the
-		 * loop, so the call ends up in this block.
-		 *
-		 * We can initialize 'max' with a cpumask_first() call
-		 * before the loop but the bits computation is not
-		 * worth given the arch_scale_cpu_capacity() just
-		 * returns a value where the resulting assembly code
-		 * will be optimized by the compiler.
-		 */
-		max = arch_scale_cpu_capacity(cpu);
-		sum_util += sched_cpu_util(cpu, max);
-	}
-
 	/*
-	 * In the improbable case where all the CPUs of the perf
-	 * domain are offline, 'max' will be zero and will lead to an
-	 * illegal operation with a zero division.
+	 * The capacity is the same for all CPUs belonging to
+	 * the same perf domain.
 	 */
-	return max ? (power * ((sum_util << 10) / max)) >> 10 : 0;
+	max = arch_scale_cpu_capacity(cpumask_first(pd_mask));
+
+	for_each_cpu_and(cpu, pd_mask, cpu_online_mask)
+		sum_util += sched_cpu_util(cpu);
+
+	return (power * ((sum_util << 10) / max)) >> 10;
 }
 
 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);
+	if (!pd)
+		return 0;
 
 	pd_mask = em_span_cpus(pd);
 
 	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 *
-					 MICROWATT_PER_MILLIWATT);
+		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 cpumask cpus;
+	struct em_perf_state *table;
 	int nr_cpus;
 
-	cpumask_and(&cpus, cpu_online_mask, to_cpumask(em->cpus));
-	nr_cpus = cpumask_weight(&cpus);
+	nr_cpus = cpumask_weight_and(cpu_online_mask, to_cpumask(em->cpus));
+
+	rcu_read_lock();
+	table = em_perf_state_from_pd(em);
 
-	dtpm->power_min = em->table[0].power;
-	dtpm->power_min *= MICROWATT_PER_MILLIWATT;
+	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 *= MICROWATT_PER_MILLIWATT;
+	dtpm->power_max = table[em->nr_perf_states - 1].power;
 	dtpm->power_max *= nr_cpus;
 
+	rcu_read_unlock();
+
 	return 0;
 }
 
 static void pd_release(struct dtpm *dtpm)
 {
 	struct dtpm_cpu *dtpm_cpu = to_dtpm_cpu(dtpm);
+	struct cpufreq_policy *policy;
 
 	if (freq_qos_request_active(&dtpm_cpu->qos_req))
 		freq_qos_remove_request(&dtpm_cpu->qos_req);
 
+	policy = cpufreq_cpu_get(dtpm_cpu->cpu);
+	if (policy) {
+		for_each_cpu(dtpm_cpu->cpu, policy->related_cpus)
+			per_cpu(dtpm_per_cpu, dtpm_cpu->cpu) = NULL;
+
+		cpufreq_cpu_put(policy);
+	}
+
 	kfree(dtpm_cpu);
 }
 
@@ -178,26 +181,42 @@ static int cpuhp_dtpm_cpu_offline(unsigned int cpu)
 static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 {
 	struct dtpm_cpu *dtpm_cpu;
+
+	dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+	if (dtpm_cpu)
+		return dtpm_update_power(&dtpm_cpu->dtpm);
+
+	return 0;
+}
+
+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;
 
+	dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
+	if (dtpm_cpu)
+		return 0;
+
 	policy = cpufreq_cpu_get(cpu);
 	if (!policy)
 		return 0;
 
 	pd = em_cpu_get(cpu);
-	if (!pd)
-		return -EINVAL;
-
-	dtpm_cpu = per_cpu(dtpm_per_cpu, cpu);
-	if (dtpm_cpu)
-		return dtpm_update_power(&dtpm_cpu->dtpm);
+	if (!pd || em_is_artificial(pd)) {
+		ret = -EINVAL;
+		goto release_policy;
+	}
 
 	dtpm_cpu = kzalloc(sizeof(*dtpm_cpu), GFP_KERNEL);
-	if (!dtpm_cpu)
-		return -ENOMEM;
+	if (!dtpm_cpu) {
+		ret = -ENOMEM;
+		goto release_policy;
+	}
 
 	dtpm_init(&dtpm_cpu->dtpm, &dtpm_ops);
 	dtpm_cpu->cpu = cpu;
@@ -207,16 +226,20 @@ static int cpuhp_dtpm_cpu_online(unsigned int cpu)
 
 	snprintf(name, sizeof(name), "cpu%d-cpufreq", dtpm_cpu->cpu);
 
-	ret = dtpm_register(name, &dtpm_cpu->dtpm, NULL);
+	ret = dtpm_register(name, &dtpm_cpu->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);
-	if (ret)
+				   table[pd->nr_perf_states - 1].frequency);
+	rcu_read_unlock();
+	if (ret < 0)
 		goto out_dtpm_unregister;
 
+	cpufreq_cpu_put(policy);
 	return 0;
 
 out_dtpm_unregister:
@@ -228,10 +251,23 @@ out_kfree_dtpm_cpu:
 		per_cpu(dtpm_per_cpu, cpu) = NULL;
 	kfree(dtpm_cpu);
 
+release_policy:
+	cpufreq_cpu_put(policy);
 	return ret;
 }
 
-static int __init dtpm_cpu_init(void)
+static int dtpm_cpu_setup(struct dtpm *dtpm, struct device_node *np)
+{
+	int cpu;
+
+	cpu = of_cpu_node_to_id(np);
+	if (cpu < 0)
+		return 0;
+
+	return __dtpm_cpu_setup(cpu, dtpm);
+}
+
+static int dtpm_cpu_init(void)
 {
 	int ret;
 
@@ -269,4 +305,15 @@ static int __init dtpm_cpu_init(void)
 	return 0;
 }
 
-DTPM_DECLARE(dtpm_cpu, dtpm_cpu_init);
+static void dtpm_cpu_exit(void)
+{
+	cpuhp_remove_state_nocalls(CPUHP_AP_ONLINE_DYN);
+	cpuhp_remove_state_nocalls(CPUHP_AP_DTPM_CPU_DEAD);
+}
+
+struct dtpm_subsys_ops dtpm_cpu_ops = {
+	.name = KBUILD_MODNAME,
+	.init = dtpm_cpu_init,
+	.exit = dtpm_cpu_exit,
+	.setup = dtpm_cpu_setup,
+};