[PATCH V7 5/7] cpufreq: Register notifiers with the PM QoS framework

[Viresh Kumar <viresh.kumar@linaro.org>]

This registers the notifiers for min/max frequency constraints with the
PM QoS framework. The constraints are also taken into consideration in
cpufreq_set_policy().

This also relocates cpufreq_policy_put_kobj() as it is required to be
called from cpufreq_policy_alloc() now.

refresh_frequency_limits() is updated to avoid calling
cpufreq_set_policy() for inactive policies and handle_update() is
updated to have proper locking in place.

No constraints are added until now though.

Reviewed-by: Matthias Kaehlcke <mka@chromium.org>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
V6->V7:
- All callers of refresh_frequency_limits(), except handle_update(),
  take the policy->rwsem and result in deadlock as
  refresh_frequency_limits() also takes the same lock again. Fix that
  by taking the rwsem from handle_update() instead.

@Rafael: Sending it before Pavel has verified it as I would be offline
later, in case you want to apply this today itself.

 drivers/cpufreq/cpufreq.c | 135 +++++++++++++++++++++++++++++---------
 include/linux/cpufreq.h   |   3 +
 2 files changed, 108 insertions(+), 30 deletions(-)

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index ceb57af15ca0..b96ef6db1bfe 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -26,6 +26,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/pm_qos.h>
 #include <linux/slab.h>
 #include <linux/suspend.h>
 #include <linux/syscore_ops.h>
@@ -999,7 +1000,7 @@ static void add_cpu_dev_symlink(struct cpufreq_policy *policy, unsigned int cpu)
 {
 	struct device *dev = get_cpu_device(cpu);
 
-	if (!dev)
+	if (unlikely(!dev))
 		return;
 
 	if (cpumask_test_and_set_cpu(cpu, policy->real_cpus))
@@ -1117,14 +1118,16 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cp
 
 static void refresh_frequency_limits(struct cpufreq_policy *policy)
 {
-	struct cpufreq_policy new_policy = *policy;
-
-	pr_debug("updating policy for CPU %u\n", policy->cpu);
+	struct cpufreq_policy new_policy;
 
-	new_policy.min = policy->user_policy.min;
-	new_policy.max = policy->user_policy.max;
+	if (!policy_is_inactive(policy)) {
+		new_policy = *policy;
+		pr_debug("updating policy for CPU %u\n", policy->cpu);
 
-	cpufreq_set_policy(policy, &new_policy);
+		new_policy.min = policy->user_policy.min;
+		new_policy.max = policy->user_policy.max;
+		cpufreq_set_policy(policy, &new_policy);
+	}
 }
 
 static void handle_update(struct work_struct *work)
@@ -1133,14 +1136,60 @@ static void handle_update(struct work_struct *work)
 		container_of(work, struct cpufreq_policy, update);
 
 	pr_debug("handle_update for cpu %u called\n", policy->cpu);
+	down_write(&policy->rwsem);
 	refresh_frequency_limits(policy);
+	up_write(&policy->rwsem);
+}
+
+static int cpufreq_notifier_min(struct notifier_block *nb, unsigned long freq,
+				void *data)
+{
+	struct cpufreq_policy *policy = container_of(nb, struct cpufreq_policy, nb_min);
+
+	schedule_work(&policy->update);
+	return 0;
+}
+
+static int cpufreq_notifier_max(struct notifier_block *nb, unsigned long freq,
+				void *data)
+{
+	struct cpufreq_policy *policy = container_of(nb, struct cpufreq_policy, nb_max);
+
+	schedule_work(&policy->update);
+	return 0;
+}
+
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
+{
+	struct kobject *kobj;
+	struct completion *cmp;
+
+	down_write(&policy->rwsem);
+	cpufreq_stats_free_table(policy);
+	kobj = &policy->kobj;
+	cmp = &policy->kobj_unregister;
+	up_write(&policy->rwsem);
+	kobject_put(kobj);
+
+	/*
+	 * We need to make sure that the underlying kobj is
+	 * actually not referenced anymore by anybody before we
+	 * proceed with unloading.
+	 */
+	pr_debug("waiting for dropping of refcount\n");
+	wait_for_completion(cmp);
+	pr_debug("wait complete\n");
 }
 
 static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
+	struct device *dev = get_cpu_device(cpu);
 	int ret;
 
+	if (!dev)
+		return NULL;
+
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
 	if (!policy)
 		return NULL;
@@ -1157,7 +1206,7 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
 				   cpufreq_global_kobject, "policy%u", cpu);
 	if (ret) {
-		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		dev_err(dev, "%s: failed to init policy->kobj: %d\n", __func__, ret);
 		/*
 		 * The entire policy object will be freed below, but the extra
 		 * memory allocated for the kobject name needs to be freed by
@@ -1167,6 +1216,25 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 		goto err_free_real_cpus;
 	}
 
+	policy->nb_min.notifier_call = cpufreq_notifier_min;
+	policy->nb_max.notifier_call = cpufreq_notifier_max;
+
+	ret = dev_pm_qos_add_notifier(dev, &policy->nb_min,
+				      DEV_PM_QOS_MIN_FREQUENCY);
+	if (ret) {
+		dev_err(dev, "Failed to register MIN QoS notifier: %d (%*pbl)\n",
+			ret, cpumask_pr_args(policy->cpus));
+		goto err_kobj_remove;
+	}
+
+	ret = dev_pm_qos_add_notifier(dev, &policy->nb_max,
+				      DEV_PM_QOS_MAX_FREQUENCY);
+	if (ret) {
+		dev_err(dev, "Failed to register MAX QoS notifier: %d (%*pbl)\n",
+			ret, cpumask_pr_args(policy->cpus));
+		goto err_min_qos_notifier;
+	}
+
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1177,6 +1245,11 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	policy->cpu = cpu;
 	return policy;
 
+err_min_qos_notifier:
+	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
+				   DEV_PM_QOS_MIN_FREQUENCY);
+err_kobj_remove:
+	cpufreq_policy_put_kobj(policy);
 err_free_real_cpus:
 	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
@@ -1189,30 +1262,9 @@ static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
-{
-	struct kobject *kobj;
-	struct completion *cmp;
-
-	down_write(&policy->rwsem);
-	cpufreq_stats_free_table(policy);
-	kobj = &policy->kobj;
-	cmp = &policy->kobj_unregister;
-	up_write(&policy->rwsem);
-	kobject_put(kobj);
-
-	/*
-	 * We need to make sure that the underlying kobj is
-	 * actually not referenced anymore by anybody before we
-	 * proceed with unloading.
-	 */
-	pr_debug("waiting for dropping of refcount\n");
-	wait_for_completion(cmp);
-	pr_debug("wait complete\n");
-}
-
 static void cpufreq_policy_free(struct cpufreq_policy *policy)
 {
+	struct device *dev = get_cpu_device(policy->cpu);
 	unsigned long flags;
 	int cpu;
 
@@ -1224,6 +1276,11 @@ static void cpufreq_policy_free(struct cpufreq_policy *policy)
 		per_cpu(cpufreq_cpu_data, cpu) = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	dev_pm_qos_remove_notifier(dev, &policy->nb_max,
+				   DEV_PM_QOS_MAX_FREQUENCY);
+	dev_pm_qos_remove_notifier(dev, &policy->nb_min,
+				   DEV_PM_QOS_MIN_FREQUENCY);
+
 	cpufreq_policy_put_kobj(policy);
 	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
@@ -2283,6 +2340,8 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 		       struct cpufreq_policy *new_policy)
 {
 	struct cpufreq_governor *old_gov;
+	struct device *cpu_dev = get_cpu_device(policy->cpu);
+	unsigned long min, max;
 	int ret;
 
 	pr_debug("setting new policy for CPU %u: %u - %u kHz\n",
@@ -2297,11 +2356,27 @@ int cpufreq_set_policy(struct cpufreq_policy *policy,
 	if (new_policy->min > new_policy->max)
 		return -EINVAL;
 
+	/*
+	 * PM QoS framework collects all the requests from users and provide us
+	 * the final aggregated value here.
+	 */
+	min = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MIN_FREQUENCY);
+	max = dev_pm_qos_read_value(cpu_dev, DEV_PM_QOS_MAX_FREQUENCY);
+
+	if (min > new_policy->min)
+		new_policy->min = min;
+	if (max < new_policy->max)
+		new_policy->max = max;
+
 	/* verify the cpu speed can be set within this limit */
 	ret = cpufreq_driver->verify(new_policy);
 	if (ret)
 		return ret;
 
+	/*
+	 * The notifier-chain shall be removed once all the users of
+	 * CPUFREQ_ADJUST are moved to use the QoS framework.
+	 */
 	/* adjust if necessary - all reasons */
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 			CPUFREQ_ADJUST, new_policy);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index a1467aa7f58b..95425941f46d 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -147,6 +147,9 @@ struct cpufreq_policy {
 
 	/* Pointer to the cooling device if used for thermal mitigation */
 	struct thermal_cooling_device *cdev;
+
+	struct notifier_block nb_min;
+	struct notifier_block nb_max;
 };
 
 struct cpufreq_freqs {
-- 
2.21.0.rc0.269.g1a574e7a288b