ACPI: cpufreq: Switch to QoS requests instead of cpufreq notifier

The cpufreq core now takes the min/max frequency constraints via QoS
requests and the CPUFREQ_ADJUST notifier shall get removed later on.

Switch over to using the QoS request for maximum frequency constraint
for acpi driver.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

3 files changed, 114 insertions, 109 deletions

diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index aea8d674a33d..08da9c29f1e9 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -284,6 +284,29 @@ static int acpi_processor_stop(struct device *dev)
 	return 0;
 }
 
+bool acpi_processor_cpufreq_init;
+
+static int acpi_processor_notifier(struct notifier_block *nb,
+				   unsigned long event, void *data)
+{
+	struct cpufreq_policy *policy = data;
+	int cpu = policy->cpu;
+
+	if (event == CPUFREQ_CREATE_POLICY) {
+		acpi_thermal_cpufreq_init(cpu);
+		acpi_processor_ppc_init(cpu);
+	} else if (event == CPUFREQ_REMOVE_POLICY) {
+		acpi_processor_ppc_exit(cpu);
+		acpi_thermal_cpufreq_exit(cpu);
+	}
+
+	return 0;
+}
+
+static struct notifier_block acpi_processor_notifier_block = {
+	.notifier_call = acpi_processor_notifier,
+};
+
 /*
  * We keep the driver loaded even when ACPI is not running.
  * This is needed for the powernow-k8 driver, that works even without
@@ -310,8 +333,12 @@ static int __init acpi_processor_driver_init(void)
 	cpuhp_setup_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD, "acpi/cpu-drv:dead",
 				  NULL, acpi_soft_cpu_dead);
 
-	acpi_thermal_cpufreq_init();
-	acpi_processor_ppc_init();
+	if (!cpufreq_register_notifier(&acpi_processor_notifier_block,
+				       CPUFREQ_POLICY_NOTIFIER)) {
+		acpi_processor_cpufreq_init = true;
+		acpi_processor_ignore_ppc_init();
+	}
+
 	acpi_processor_throttling_init();
 	return 0;
 err:
@@ -324,8 +351,12 @@ static void __exit acpi_processor_driver_exit(void)
 	if (acpi_disabled)
 		return;
 
-	acpi_processor_ppc_exit();
-	acpi_thermal_cpufreq_exit();
+	if (acpi_processor_cpufreq_init) {
+		cpufreq_unregister_notifier(&acpi_processor_notifier_block,
+					    CPUFREQ_POLICY_NOTIFIER);
+		acpi_processor_cpufreq_init = false;
+	}
+
 	cpuhp_remove_state_nocalls(hp_online);
 	cpuhp_remove_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD);
 	driver_unregister(&acpi_processor_driver);
diff --git a/drivers/acpi/processor_perflib.c b/drivers/acpi/processor_perflib.c
index ee87cb6f6e59..2261713d1aec 100644
--- a/drivers/acpi/processor_perflib.c
+++ b/drivers/acpi/processor_perflib.c
@@ -50,57 +50,13 @@ module_param(ignore_ppc, int, 0644);
 MODULE_PARM_DESC(ignore_ppc, "If the frequency of your machine gets wrongly" \
 		 "limited by BIOS, this should help");
 
-#define PPC_REGISTERED   1
-#define PPC_IN_USE       2
-
-static int acpi_processor_ppc_status;
-
-static int acpi_processor_ppc_notifier(struct notifier_block *nb,
-				       unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	struct acpi_processor *pr;
-	unsigned int ppc = 0;
-
-	if (ignore_ppc < 0)
-		ignore_ppc = 0;
-
-	if (ignore_ppc)
-		return 0;
-
-	if (event != CPUFREQ_ADJUST)
-		return 0;
-
-	mutex_lock(&performance_mutex);
-
-	pr = per_cpu(processors, policy->cpu);
-	if (!pr || !pr->performance)
-		goto out;
-
-	ppc = (unsigned int)pr->performance_platform_limit;
-
-	if (ppc >= pr->performance->state_count)
-		goto out;
-
-	cpufreq_verify_within_limits(policy, 0,
-				     pr->performance->states[ppc].
-				     core_frequency * 1000);
-
-      out:
-	mutex_unlock(&performance_mutex);
-
-	return 0;
-}
-
-static struct notifier_block acpi_ppc_notifier_block = {
-	.notifier_call = acpi_processor_ppc_notifier,
-};
+static bool acpi_processor_ppc_in_use;
 
 static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 {
 	acpi_status status = 0;
 	unsigned long long ppc = 0;
-
+	int ret;
 
 	if (!pr)
 		return -EINVAL;
@@ -112,7 +68,7 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 	status = acpi_evaluate_integer(pr->handle, "_PPC", NULL, &ppc);
 
 	if (status != AE_NOT_FOUND)
-		acpi_processor_ppc_status |= PPC_IN_USE;
+		acpi_processor_ppc_in_use = true;
 
 	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
 		ACPI_EXCEPTION((AE_INFO, status, "Evaluating _PPC"));
@@ -124,6 +80,17 @@ static int acpi_processor_get_platform_limit(struct acpi_processor *pr)
 
 	pr->performance_platform_limit = (int)ppc;
 
+	if (ppc >= pr->performance->state_count ||
+	    unlikely(!dev_pm_qos_request_active(&pr->perflib_req)))
+		return 0;
+
+	ret = dev_pm_qos_update_request(&pr->perflib_req,
+			pr->performance->states[ppc].core_frequency * 1000);
+	if (ret < 0) {
+		pr_warn("Failed to update perflib freq constraint: CPU%d (%d)\n",
+			pr->id, ret);
+	}
+
 	return 0;
 }
 
@@ -184,23 +151,32 @@ int acpi_processor_get_bios_limit(int cpu, unsigned int *limit)
 }
 EXPORT_SYMBOL(acpi_processor_get_bios_limit);
 
-void acpi_processor_ppc_init(void)
+void acpi_processor_ignore_ppc_init(void)
 {
-	if (!cpufreq_register_notifier
-	    (&acpi_ppc_notifier_block, CPUFREQ_POLICY_NOTIFIER))
-		acpi_processor_ppc_status |= PPC_REGISTERED;
-	else
-		printk(KERN_DEBUG
-		       "Warning: Processor Platform Limit not supported.\n");
+	if (ignore_ppc < 0)
+		ignore_ppc = 0;
+}
+
+void acpi_processor_ppc_init(int cpu)
+{
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+	int ret;
+
+	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+				     &pr->perflib_req, DEV_PM_QOS_MAX_FREQUENCY,
+				     INT_MAX);
+	if (ret < 0) {
+		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
+		       ret);
+		return;
+	}
 }
 
-void acpi_processor_ppc_exit(void)
+void acpi_processor_ppc_exit(int cpu)
 {
-	if (acpi_processor_ppc_status & PPC_REGISTERED)
-		cpufreq_unregister_notifier(&acpi_ppc_notifier_block,
-					    CPUFREQ_POLICY_NOTIFIER);
+	struct acpi_processor *pr = per_cpu(processors, cpu);
 
-	acpi_processor_ppc_status &= ~PPC_REGISTERED;
+	dev_pm_qos_remove_request(&pr->perflib_req);
 }
 
 static int acpi_processor_get_performance_control(struct acpi_processor *pr)
@@ -477,7 +453,7 @@ int acpi_processor_notify_smm(struct module *calling_module)
 	static int is_done = 0;
 	int result;
 
-	if (!(acpi_processor_ppc_status & PPC_REGISTERED))
+	if (!acpi_processor_cpufreq_init)
 		return -EBUSY;
 
 	if (!try_module_get(calling_module))
@@ -513,7 +489,7 @@ int acpi_processor_notify_smm(struct module *calling_module)
 	 * we can allow the cpufreq driver to be rmmod'ed. */
 	is_done = 1;
 
-	if (!(acpi_processor_ppc_status & PPC_IN_USE))
+	if (!acpi_processor_ppc_in_use)
 		module_put(calling_module);
 
 	return 0;
@@ -742,7 +718,7 @@ acpi_processor_register_performance(struct acpi_processor_performance
 {
 	struct acpi_processor *pr;
 
-	if (!(acpi_processor_ppc_status & PPC_REGISTERED))
+	if (!acpi_processor_cpufreq_init)
 		return -EINVAL;
 
 	mutex_lock(&performance_mutex);
diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 50fb0107375e..ec2638f1df4f 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -35,7 +35,6 @@ ACPI_MODULE_NAME("processor_thermal");
 #define CPUFREQ_THERMAL_MAX_STEP 3
 
 static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_pctg);
-static unsigned int acpi_thermal_cpufreq_is_init = 0;
 
 #define reduction_pctg(cpu) \
 	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
@@ -61,35 +60,11 @@ static int phys_package_first_cpu(int cpu)
 static int cpu_has_cpufreq(unsigned int cpu)
 {
 	struct cpufreq_policy policy;
-	if (!acpi_thermal_cpufreq_is_init || cpufreq_get_policy(&policy, cpu))
+	if (!acpi_processor_cpufreq_init || cpufreq_get_policy(&policy, cpu))
 		return 0;
 	return 1;
 }
 
-static int acpi_thermal_cpufreq_notifier(struct notifier_block *nb,
-					 unsigned long event, void *data)
-{
-	struct cpufreq_policy *policy = data;
-	unsigned long max_freq = 0;
-
-	if (event != CPUFREQ_ADJUST)
-		goto out;
-
-	max_freq = (
-	    policy->cpuinfo.max_freq *
-	    (100 - reduction_pctg(policy->cpu) * 20)
-	) / 100;
-
-	cpufreq_verify_within_limits(policy, 0, max_freq);
-
-      out:
-	return 0;
-}
-
-static struct notifier_block acpi_thermal_cpufreq_notifier_block = {
-	.notifier_call = acpi_thermal_cpufreq_notifier,
-};
-
 static int cpufreq_get_max_state(unsigned int cpu)
 {
 	if (!cpu_has_cpufreq(cpu))
@@ -108,7 +83,10 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
 {
-	int i;
+	struct cpufreq_policy *policy;
+	struct acpi_processor *pr;
+	unsigned long max_freq;
+	int i, ret;
 
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
@@ -121,33 +99,53 @@ static int cpufreq_set_cur_state(unsigned int cpu, int state)
 	 * frequency.
 	 */
 	for_each_online_cpu(i) {
-		if (topology_physical_package_id(i) ==
+		if (topology_physical_package_id(i) !=
 		    topology_physical_package_id(cpu))
-			cpufreq_update_policy(i);
+			continue;
+
+		pr = per_cpu(processors, i);
+
+		if (unlikely(!dev_pm_qos_request_active(&pr->thermal_req)))
+			continue;
+
+		policy = cpufreq_cpu_get(i);
+		if (!policy)
+			return -EINVAL;
+
+		max_freq = (policy->cpuinfo.max_freq * (100 - reduction_pctg(i) * 20)) / 100;
+
+		cpufreq_cpu_put(policy);
+
+		ret = dev_pm_qos_update_request(&pr->thermal_req, max_freq);
+		if (ret < 0) {
+			pr_warn("Failed to update thermal freq constraint: CPU%d (%d)\n",
+				pr->id, ret);
+		}
 	}
 	return 0;
 }
 
-void acpi_thermal_cpufreq_init(void)
+void acpi_thermal_cpufreq_init(int cpu)
 {
-	int i;
-
-	i = cpufreq_register_notifier(&acpi_thermal_cpufreq_notifier_block,
-				      CPUFREQ_POLICY_NOTIFIER);
-	if (!i)
-		acpi_thermal_cpufreq_is_init = 1;
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+	int ret;
+
+	ret = dev_pm_qos_add_request(get_cpu_device(cpu),
+				     &pr->thermal_req, DEV_PM_QOS_MAX_FREQUENCY,
+				     INT_MAX);
+	if (ret < 0) {
+		pr_err("Failed to add freq constraint for CPU%d (%d)\n", cpu,
+		       ret);
+		return;
+	}
 }
 
-void acpi_thermal_cpufreq_exit(void)
+void acpi_thermal_cpufreq_exit(int cpu)
 {
-	if (acpi_thermal_cpufreq_is_init)
-		cpufreq_unregister_notifier
-		    (&acpi_thermal_cpufreq_notifier_block,
-		     CPUFREQ_POLICY_NOTIFIER);
+	struct acpi_processor *pr = per_cpu(processors, cpu);
 
-	acpi_thermal_cpufreq_is_init = 0;
+	dev_pm_qos_remove_request(&pr->thermal_req);
 }
-
 #else				/* ! CONFIG_CPU_FREQ */
 static int cpufreq_get_max_state(unsigned int cpu)
 {