1 files changed, 159 insertions, 68 deletions

diff --git a/drivers/acpi/processor_thermal.c b/drivers/acpi/processor_thermal.c
index 59c3a5d1e600..c7b1dc5687ec 100644
--- a/drivers/acpi/processor_thermal.c
+++ b/drivers/acpi/processor_thermal.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
 /*
  * processor_thermal.c - Passive cooling submodule of the ACPI processor driver
  *
@@ -6,20 +7,6 @@
  *  Copyright (C) 2004       Dominik Brodowski <linux@brodo.de>
  *  Copyright (C) 2004  Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
  *  			- Added processor hotplug support
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2 of the License, or (at
- *  your option) any later version.
- *
- *  This program is distributed in the hope that it will be useful, but
- *  WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- *  General Public License for more details.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
  */
 
 #include <linux/kernel.h>
@@ -30,11 +17,7 @@
 #include <acpi/processor.h>
 #include <linux/uaccess.h>
 
-#define PREFIX "ACPI: "
-
-#define ACPI_PROCESSOR_CLASS            "processor"
-#define _COMPONENT              ACPI_PROCESSOR_COMPONENT
-ACPI_MODULE_NAME("processor_thermal");
+#include "internal.h"
 
 #ifdef CONFIG_CPU_FREQ
 
@@ -45,13 +28,21 @@ ACPI_MODULE_NAME("processor_thermal");
  */
 
 #define CPUFREQ_THERMAL_MIN_STEP 0
-#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;
+static int cpufreq_thermal_max_step __read_mostly = 3;
+
+/*
+ * Minimum throttle percentage for processor_thermal cooling device.
+ * The processor_thermal driver uses it to calculate the percentage amount by
+ * which cpu frequency must be reduced for each cooling state. This is also used
+ * to calculate the maximum number of throttling steps or cooling states.
+ */
+static int cpufreq_thermal_reduction_pctg __read_mostly = 20;
+
+static DEFINE_PER_CPU(unsigned int, cpufreq_thermal_reduction_step);
 
-#define reduction_pctg(cpu) \
-	per_cpu(cpufreq_thermal_reduction_pctg, phys_package_first_cpu(cpu))
+#define reduction_step(cpu) \
+	per_cpu(cpufreq_thermal_reduction_step, phys_package_first_cpu(cpu))
 
 /*
  * Emulate "per package data" using per cpu data (which should really be
@@ -71,44 +62,22 @@ static int phys_package_first_cpu(int cpu)
 	return 0;
 }
 
-static int cpu_has_cpufreq(unsigned int cpu)
+static bool 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)
 		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;
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
 
-	cpufreq_verify_within_limits(policy, 0, max_freq);
-
-      out:
-	return 0;
+	return policy != NULL;
 }
 
-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))
 		return 0;
 
-	return CPUFREQ_THERMAL_MAX_STEP;
+	return cpufreq_thermal_max_step;
 }
 
 static int cpufreq_get_cur_state(unsigned int cpu)
@@ -116,17 +85,39 @@ static int cpufreq_get_cur_state(unsigned int cpu)
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	return reduction_pctg(cpu);
+	return reduction_step(cpu);
+}
+
+static bool cpufreq_update_thermal_limit(unsigned int cpu, struct acpi_processor *pr)
+{
+	unsigned long max_freq;
+	int ret;
+
+	struct cpufreq_policy *policy __free(put_cpufreq_policy) = cpufreq_cpu_get(cpu);
+	if (!policy)
+		return false;
+
+	max_freq = (policy->cpuinfo.max_freq *
+		(100 - reduction_step(cpu) * cpufreq_thermal_reduction_pctg)) / 100;
+
+	ret = freq_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 true;
 }
 
 static int cpufreq_set_cur_state(unsigned int cpu, int state)
 {
+	struct acpi_processor *pr;
 	int i;
 
 	if (!cpu_has_cpufreq(cpu))
 		return 0;
 
-	reduction_pctg(cpu) = state;
+	reduction_step(cpu) = state;
 
 	/*
 	 * Update all the CPUs in the same package because they all
@@ -134,33 +125,79 @@ 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(!freq_qos_request_active(&pr->thermal_req)))
+			continue;
+
+		if (!cpufreq_update_thermal_limit(i, pr))
+			return -EINVAL;
 	}
 	return 0;
 }
 
-void acpi_thermal_cpufreq_init(void)
+static void acpi_thermal_cpufreq_config(void)
 {
-	int i;
+	int cpufreq_pctg = acpi_arch_thermal_cpufreq_pctg();
+
+	if (!cpufreq_pctg)
+		return;
 
-	i = cpufreq_register_notifier(&acpi_thermal_cpufreq_notifier_block,
-				      CPUFREQ_POLICY_NOTIFIER);
-	if (!i)
-		acpi_thermal_cpufreq_is_init = 1;
+	cpufreq_thermal_reduction_pctg = cpufreq_pctg;
+
+	/*
+	 * Derive the MAX_STEP from minimum throttle percentage so that the reduction
+	 * percentage doesn't end up becoming negative. Also, cap the MAX_STEP so that
+	 * the CPU performance doesn't become 0.
+	 */
+	cpufreq_thermal_max_step = (100 / cpufreq_pctg) - 2;
 }
 
-void acpi_thermal_cpufreq_exit(void)
+void acpi_thermal_cpufreq_init(struct cpufreq_policy *policy)
 {
-	if (acpi_thermal_cpufreq_is_init)
-		cpufreq_unregister_notifier
-		    (&acpi_thermal_cpufreq_notifier_block,
-		     CPUFREQ_POLICY_NOTIFIER);
+	unsigned int cpu;
+
+	acpi_thermal_cpufreq_config();
+
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+		int ret;
+
+		if (!pr)
+			continue;
+
+		ret = freq_qos_add_request(&policy->constraints,
+					   &pr->thermal_req,
+					   FREQ_QOS_MAX, INT_MAX);
+		if (ret < 0) {
+			pr_err("Failed to add freq constraint for CPU%d (%d)\n",
+			       cpu, ret);
+			continue;
+		}
 
-	acpi_thermal_cpufreq_is_init = 0;
+		thermal_cooling_device_update(pr->cdev);
+	}
 }
 
+void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	unsigned int cpu;
+
+	for_each_cpu(cpu, policy->related_cpus) {
+		struct acpi_processor *pr = per_cpu(processors, cpu);
+
+		if (!pr)
+			continue;
+
+		freq_qos_remove_request(&pr->thermal_req);
+
+		thermal_cooling_device_update(pr->cdev);
+	}
+}
 #else				/* ! CONFIG_CPU_FREQ */
 static int cpufreq_get_max_state(unsigned int cpu)
 {
@@ -186,7 +223,7 @@ static int acpi_processor_max_state(struct acpi_processor *pr)
 
 	/*
 	 * There exists four states according to
-	 * cpufreq_thermal_reduction_pctg. 0, 1, 2, 3
+	 * cpufreq_thermal_reduction_step. 0, 1, 2, 3
 	 */
 	max_state += cpufreq_get_max_state(pr->id);
 	if (pr->flags.throttling)
@@ -270,3 +307,57 @@ const struct thermal_cooling_device_ops processor_cooling_ops = {
 	.get_cur_state = processor_get_cur_state,
 	.set_cur_state = processor_set_cur_state,
 };
+
+int acpi_processor_thermal_init(struct acpi_processor *pr,
+				struct acpi_device *device)
+{
+	int result = 0;
+
+	pr->cdev = thermal_cooling_device_register("Processor", device,
+						   &processor_cooling_ops);
+	if (IS_ERR(pr->cdev)) {
+		result = PTR_ERR(pr->cdev);
+		return result;
+	}
+
+	dev_dbg(&device->dev, "registered as cooling_device%d\n",
+		pr->cdev->id);
+
+	result = sysfs_create_link(&device->dev.kobj,
+				   &pr->cdev->device.kobj,
+				   "thermal_cooling");
+	if (result) {
+		dev_err(&device->dev,
+			"Failed to create sysfs link 'thermal_cooling'\n");
+		goto err_thermal_unregister;
+	}
+
+	result = sysfs_create_link(&pr->cdev->device.kobj,
+				   &device->dev.kobj,
+				   "device");
+	if (result) {
+		dev_err(&pr->cdev->device,
+			"Failed to create sysfs link 'device'\n");
+		goto err_remove_sysfs_thermal;
+	}
+
+	return 0;
+
+err_remove_sysfs_thermal:
+	sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
+err_thermal_unregister:
+	thermal_cooling_device_unregister(pr->cdev);
+
+	return result;
+}
+
+void acpi_processor_thermal_exit(struct acpi_processor *pr,
+				 struct acpi_device *device)
+{
+	if (pr->cdev) {
+		sysfs_remove_link(&device->dev.kobj, "thermal_cooling");
+		sysfs_remove_link(&pr->cdev->device.kobj, "device");
+		thermal_cooling_device_unregister(pr->cdev);
+		pr->cdev = NULL;
+	}
+}