3 files changed, 174 insertions, 183 deletions

diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 1f93dbd7235..5f72ad48674 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -47,6 +47,9 @@ static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
 #endif
 static DEFINE_SPINLOCK(cpufreq_driver_lock);
 
+/* Used when we unregister cpufreq driver */
+static struct cpumask cpufreq_online_mask;
+
 /*
  * cpu_policy_rwsem is a per CPU reader-writer semaphore designed to cure
  * all cpufreq/hotplug/workqueue/etc related lock issues.
@@ -700,87 +703,6 @@ static struct kobj_type ktype_cpufreq = {
 	.release	= cpufreq_sysfs_release,
 };
 
-/*
- * Returns:
- *   Negative: Failure
- *   0:        Success
- *   Positive: When we have a managed CPU and the sysfs got symlinked
- */
-static int cpufreq_add_dev_policy(unsigned int cpu,
-				  struct cpufreq_policy *policy,
-				  struct device *dev)
-{
-	int ret = 0;
-#ifdef CONFIG_SMP
-	unsigned long flags;
-	unsigned int j;
-#ifdef CONFIG_HOTPLUG_CPU
-	struct cpufreq_governor *gov;
-
-	gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
-	if (gov) {
-		policy->governor = gov;
-		pr_debug("Restoring governor %s for cpu %d\n",
-		       policy->governor->name, cpu);
-	}
-#endif
-
-	for_each_cpu(j, policy->cpus) {
-		struct cpufreq_policy *managed_policy;
-
-		if (cpu == j)
-			continue;
-
-		/* Check for existing affected CPUs.
-		 * They may not be aware of it due to CPU Hotplug.
-		 * cpufreq_cpu_put is called when the device is removed
-		 * in __cpufreq_remove_dev()
-		 */
-		managed_policy = cpufreq_cpu_get(j);
-		if (unlikely(managed_policy)) {
-
-			/* Set proper policy_cpu */
-			unlock_policy_rwsem_write(cpu);
-			per_cpu(cpufreq_policy_cpu, cpu) = managed_policy->cpu;
-
-			if (lock_policy_rwsem_write(cpu) < 0) {
-				/* Should not go through policy unlock path */
-				if (cpufreq_driver->exit)
-					cpufreq_driver->exit(policy);
-				cpufreq_cpu_put(managed_policy);
-				return -EBUSY;
-			}
-
-			spin_lock_irqsave(&cpufreq_driver_lock, flags);
-			cpumask_copy(managed_policy->cpus, policy->cpus);
-			per_cpu(cpufreq_cpu_data, cpu) = managed_policy;
-			spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-			pr_debug("CPU already managed, adding link\n");
-			ret = sysfs_create_link(&dev->kobj,
-						&managed_policy->kobj,
-						"cpufreq");
-			if (ret)
-				cpufreq_cpu_put(managed_policy);
-			/*
-			 * Success. We only needed to be added to the mask.
-			 * Call driver->exit() because only the cpu parent of
-			 * the kobj needed to call init().
-			 */
-			if (cpufreq_driver->exit)
-				cpufreq_driver->exit(policy);
-
-			if (!ret)
-				return 1;
-			else
-				return ret;
-		}
-	}
-#endif
-	return ret;
-}
-
-
 /* symlink affected CPUs */
 static int cpufreq_add_dev_symlink(unsigned int cpu,
 				   struct cpufreq_policy *policy)
@@ -885,6 +807,42 @@ err_out_kobj_put:
 	return ret;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int cpufreq_add_policy_cpu(unsigned int cpu, unsigned int sibling,
+				  struct device *dev)
+{
+	struct cpufreq_policy *policy;
+	int ret = 0;
+	unsigned long flags;
+
+	policy = cpufreq_cpu_get(sibling);
+	WARN_ON(!policy);
+
+	per_cpu(cpufreq_policy_cpu, cpu) = policy->cpu;
+
+	lock_policy_rwsem_write(cpu);
+
+	__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+
+	spin_lock_irqsave(&cpufreq_driver_lock, flags);
+	cpumask_set_cpu(cpu, policy->cpus);
+	per_cpu(cpufreq_cpu_data, cpu) = policy;
+	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	__cpufreq_governor(policy, CPUFREQ_GOV_START);
+	__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+
+	unlock_policy_rwsem_write(cpu);
+
+	ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
+	if (ret) {
+		cpufreq_cpu_put(policy);
+		return ret;
+	}
+
+	return 0;
+}
+#endif
 
 /**
  * cpufreq_add_dev - add a CPU device
@@ -897,12 +855,12 @@ err_out_kobj_put:
  */
 static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
-	unsigned int cpu = dev->id;
-	int ret = 0, found = 0;
+	unsigned int j, cpu = dev->id;
+	int ret = -ENOMEM, found = 0;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
-	unsigned int j;
 #ifdef CONFIG_HOTPLUG_CPU
+	struct cpufreq_governor *gov;
 	int sibling;
 #endif
 
@@ -919,6 +877,15 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		cpufreq_cpu_put(policy);
 		return 0;
 	}
+
+#ifdef CONFIG_HOTPLUG_CPU
+	/* Check if this cpu was hot-unplugged earlier and has siblings */
+	for_each_online_cpu(sibling) {
+		struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
+		if (cp && cpumask_test_cpu(cpu, cp->related_cpus))
+			return cpufreq_add_policy_cpu(cpu, sibling, dev);
+	}
+#endif
 #endif
 
 	if (!try_module_get(cpufreq_driver->owner)) {
@@ -926,7 +893,6 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		goto module_out;
 	}
 
-	ret = -ENOMEM;
 	policy = kzalloc(sizeof(struct cpufreq_policy), GFP_KERNEL);
 	if (!policy)
 		goto nomem_out;
@@ -970,20 +936,28 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		pr_debug("initialization failed\n");
 		goto err_unlock_policy;
 	}
+
+	/*
+	 * affected cpus must always be the one, which are online. We aren't
+	 * managing offline cpus here.
+	 */
+	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
+	cpumask_and(policy->cpus, policy->cpus, &cpufreq_online_mask);
+
 	policy->user_policy.min = policy->min;
 	policy->user_policy.max = policy->max;
 
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
 
-	ret = cpufreq_add_dev_policy(cpu, policy, dev);
-	if (ret) {
-		if (ret > 0)
-			/* This is a managed cpu, symlink created,
-			   exit with 0 */
-			ret = 0;
-		goto err_unlock_policy;
+#ifdef CONFIG_HOTPLUG_CPU
+	gov = __find_governor(per_cpu(cpufreq_cpu_governor, cpu));
+	if (gov) {
+		policy->governor = gov;
+		pr_debug("Restoring governor %s for cpu %d\n",
+		       policy->governor->name, cpu);
 	}
+#endif
 
 	ret = cpufreq_add_dev_interface(cpu, policy, dev);
 	if (ret)
@@ -997,7 +971,6 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 
 	return 0;
 
-
 err_out_unregister:
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus)
@@ -1020,6 +993,25 @@ module_out:
 	return ret;
 }
 
+static void update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
+{
+	int j;
+
+	policy->last_cpu = policy->cpu;
+	policy->cpu = cpu;
+
+	for_each_cpu(j, policy->cpus) {
+		if (!cpu_online(j))
+			continue;
+		per_cpu(cpufreq_policy_cpu, j) = cpu;
+	}
+
+#ifdef CONFIG_CPU_FREQ_TABLE
+	cpufreq_frequency_table_update_policy_cpu(policy);
+#endif
+	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+			CPUFREQ_UPDATE_POLICY_CPU, policy);
+}
 
 /**
  * __cpufreq_remove_dev - remove a CPU device
@@ -1030,128 +1022,92 @@ module_out:
  */
 static int __cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 {
-	unsigned int cpu = dev->id;
+	unsigned int cpu = dev->id, ret, cpus;
 	unsigned long flags;
 	struct cpufreq_policy *data;
 	struct kobject *kobj;
 	struct completion *cmp;
-#ifdef CONFIG_SMP
 	struct device *cpu_dev;
-	unsigned int j;
-#endif
 
-	pr_debug("unregistering CPU %u\n", cpu);
+	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	data = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!data) {
+		pr_debug("%s: No cpu_data found\n", __func__);
 		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 		unlock_policy_rwsem_write(cpu);
 		return -EINVAL;
 	}
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
-
 
-#ifdef CONFIG_SMP
-	/* if this isn't the CPU which is the parent of the kobj, we
-	 * only need to unlink, put and exit
-	 */
-	if (unlikely(cpu != data->cpu)) {
-		pr_debug("removing link\n");
-		cpumask_clear_cpu(cpu, data->cpus);
-		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-		kobj = &dev->kobj;
-		cpufreq_cpu_put(data);
-		unlock_policy_rwsem_write(cpu);
-		sysfs_remove_link(kobj, "cpufreq");
-		return 0;
-	}
-#endif
-
-#ifdef CONFIG_SMP
+	if (cpufreq_driver->target)
+		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
 
 #ifdef CONFIG_HOTPLUG_CPU
 	strncpy(per_cpu(cpufreq_cpu_governor, cpu), data->governor->name,
 			CPUFREQ_NAME_LEN);
 #endif
 
-	/* if we have other CPUs still registered, we need to unlink them,
-	 * or else wait_for_completion below will lock up. Clean the
-	 * per_cpu(cpufreq_cpu_data) while holding the lock, and remove
-	 * the sysfs links afterwards.
-	 */
-	if (unlikely(cpumask_weight(data->cpus) > 1)) {
-		for_each_cpu(j, data->cpus) {
-			if (j == cpu)
-				continue;
-			per_cpu(cpufreq_cpu_data, j) = NULL;
-		}
-	}
-
-	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	cpus = cpumask_weight(data->cpus);
+	cpumask_clear_cpu(cpu, data->cpus);
 
-	if (unlikely(cpumask_weight(data->cpus) > 1)) {
-		for_each_cpu(j, data->cpus) {
-			if (j == cpu)
-				continue;
-			pr_debug("removing link for cpu %u\n", j);
-#ifdef CONFIG_HOTPLUG_CPU
-			strncpy(per_cpu(cpufreq_cpu_governor, j),
-				data->governor->name, CPUFREQ_NAME_LEN);
-#endif
-			cpu_dev = get_cpu_device(j);
-			kobj = &cpu_dev->kobj;
+	if (unlikely((cpu == data->cpu) && (cpus > 1))) {
+		/* first sibling now owns the new sysfs dir */
+		cpu_dev = get_cpu_device(cpumask_first(data->cpus));
+		sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
+		ret = kobject_move(&data->kobj, &cpu_dev->kobj);
+		if (ret) {
+			pr_err("%s: Failed to move kobj: %d", __func__, ret);
+			cpumask_set_cpu(cpu, data->cpus);
+			ret = sysfs_create_link(&cpu_dev->kobj, &data->kobj,
+					"cpufreq");
+			spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 			unlock_policy_rwsem_write(cpu);
-			sysfs_remove_link(kobj, "cpufreq");
-			lock_policy_rwsem_write(cpu);
-			cpufreq_cpu_put(data);
+			return -EINVAL;
 		}
+
+		update_policy_cpu(data, cpu_dev->id);
+		pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
+				__func__, cpu_dev->id, cpu);
 	}
-#else
-	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-#endif
 
-	if (cpufreq_driver->target)
-		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
+	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	kobj = &data->kobj;
-	cmp = &data->kobj_unregister;
+	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
+	cpufreq_cpu_put(data);
 	unlock_policy_rwsem_write(cpu);
-	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");
+	sysfs_remove_link(&dev->kobj, "cpufreq");
 
-	lock_policy_rwsem_write(cpu);
-	if (cpufreq_driver->exit)
-		cpufreq_driver->exit(data);
-	unlock_policy_rwsem_write(cpu);
+	/* If cpu is last user of policy, free policy */
+	if (cpus == 1) {
+		lock_policy_rwsem_write(cpu);
+		kobj = &data->kobj;
+		cmp = &data->kobj_unregister;
+		unlock_policy_rwsem_write(cpu);
+		kobject_put(kobj);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	/* when the CPU which is the parent of the kobj is hotplugged
-	 * offline, check for siblings, and create cpufreq sysfs interface
-	 * and symlinks
-	 */
-	if (unlikely(cpumask_weight(data->cpus) > 1)) {
-		/* first sibling now owns the new sysfs dir */
-		cpumask_clear_cpu(cpu, data->cpus);
-		cpufreq_add_dev(get_cpu_device(cpumask_first(data->cpus)), NULL);
+		/* 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");
 
-		/* finally remove our own symlink */
 		lock_policy_rwsem_write(cpu);
-		__cpufreq_remove_dev(dev, sif);
-	}
-#endif
+		if (cpufreq_driver->exit)
+			cpufreq_driver->exit(data);
+		unlock_policy_rwsem_write(cpu);
 
-	free_cpumask_var(data->related_cpus);
-	free_cpumask_var(data->cpus);
-	kfree(data);
+		free_cpumask_var(data->related_cpus);
+		free_cpumask_var(data->cpus);
+		kfree(data);
+	} else if (cpufreq_driver->target) {
+		__cpufreq_governor(data, CPUFREQ_GOV_START);
+		__cpufreq_governor(data, CPUFREQ_GOV_LIMITS);
+	}
 
 	return 0;
 }
@@ -1168,6 +1124,7 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (unlikely(lock_policy_rwsem_write(cpu)))
 		BUG();
 
+	cpumask_clear_cpu(cpu, &cpufreq_online_mask);
 	retval = __cpufreq_remove_dev(dev, sif);
 	return retval;
 }
@@ -1886,6 +1843,8 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = driver_data;
 	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
+	cpumask_setall(&cpufreq_online_mask);
+
 	ret = subsys_interface_register(&cpufreq_interface);
 	if (ret)
 		goto err_null_driver;
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index e40e5080964..251719ae50d 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -170,11 +170,13 @@ static int freq_table_get_index(struct cpufreq_stats *stat, unsigned int freq)
 static void cpufreq_stats_free_table(unsigned int cpu)
 {
 	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table, cpu);
+
 	if (stat) {
+		pr_debug("%s: Free stat table\n", __func__);
 		kfree(stat->time_in_state);
 		kfree(stat);
+		per_cpu(cpufreq_stats_table, cpu) = NULL;
 	}
-	per_cpu(cpufreq_stats_table, cpu) = NULL;
 }
 
 /* must be called early in the CPU removal sequence (before
@@ -183,8 +185,10 @@ static void cpufreq_stats_free_table(unsigned int cpu)
 static void cpufreq_stats_free_sysfs(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);
-	if (policy && policy->cpu == cpu)
+	if (policy && (cpumask_weight(policy->cpus) == 1)) {
+		pr_debug("%s: Free sysfs stat\n", __func__);
 		sysfs_remove_group(&policy->kobj, &stats_attr_group);
+	}
 	if (policy)
 		cpufreq_cpu_put(policy);
 }
@@ -262,6 +266,19 @@ error_get_fail:
 	return ret;
 }
 
+static void cpufreq_stats_update_policy_cpu(struct cpufreq_policy *policy)
+{
+	struct cpufreq_stats *stat = per_cpu(cpufreq_stats_table,
+			policy->last_cpu);
+
+	pr_debug("Updating stats_table for new_cpu %u from last_cpu %u\n",
+			policy->cpu, policy->last_cpu);
+	per_cpu(cpufreq_stats_table, policy->cpu) = per_cpu(cpufreq_stats_table,
+			policy->last_cpu);
+	per_cpu(cpufreq_stats_table, policy->last_cpu) = NULL;
+	stat->cpu = policy->cpu;
+}
+
 static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
 		unsigned long val, void *data)
 {
@@ -269,6 +286,12 @@ static int cpufreq_stat_notifier_policy(struct notifier_block *nb,
 	struct cpufreq_policy *policy = data;
 	struct cpufreq_frequency_table *table;
 	unsigned int cpu = policy->cpu;
+
+	if (val == CPUFREQ_UPDATE_POLICY_CPU) {
+		cpufreq_stats_update_policy_cpu(policy);
+		return 0;
+	}
+
 	if (val != CPUFREQ_NOTIFY)
 		return 0;
 	table = cpufreq_frequency_get_table(cpu);
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 49cda256efb..aa5bd39d129 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -227,6 +227,15 @@ void cpufreq_frequency_table_put_attr(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_frequency_table_put_attr);
 
+void cpufreq_frequency_table_update_policy_cpu(struct cpufreq_policy *policy)
+{
+	pr_debug("Updating show_table for new_cpu %u from last_cpu %u\n",
+			policy->cpu, policy->last_cpu);
+	per_cpu(cpufreq_show_table, policy->cpu) = per_cpu(cpufreq_show_table,
+			policy->last_cpu);
+	per_cpu(cpufreq_show_table, policy->last_cpu) = NULL;
+}
+
 struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
 {
 	return per_cpu(cpufreq_show_table, cpu);