Merge branch 'pm-cpufreq'

* pm-cpufreq: (37 commits)
  cpufreq: dt: allow driver to boot automatically
  intel_pstate: Fix overflow in busy_scaled due to long delay
  cpufreq: qoriq: optimize the CPU frequency switching time
  cpufreq: gx-suspmod: Fix two typos in two comments
  cpufreq: nforce2: Fix typo in comment to function nforce2_init()
  cpufreq: governor: Serialize governor callbacks
  cpufreq: governor: split cpufreq_governor_dbs()
  cpufreq: governor: register notifier from cs_init()
  cpufreq: Remove cpufreq_update_policy()
  cpufreq: Restart governor as soon as possible
  cpufreq: Call cpufreq_policy_put_kobj() from cpufreq_policy_free()
  cpufreq: Initialize policy->kobj while allocating policy
  cpufreq: Stop migrating sysfs files on hotplug
  cpufreq: Don't allow updating inactive policies from sysfs
  intel_pstate: Force setting target pstate when required
  intel_pstate: change some inconsistent debug information
  cpufreq: Track cpu managing sysfs kobjects separately
  cpufreq: Fix for typos in two comments
  cpufreq: Mark policy->governor = NULL for inactive policies
  cpufreq: Manage governor usage history with 'policy->last_governor'
  ...

16 files changed, 670 insertions, 503 deletions

diff --git a/Documentation/cpu-freq/user-guide.txt b/Documentation/cpu-freq/user-guide.txt
index ff2f28332cc4..109e97bbab77 100644
--- a/Documentation/cpu-freq/user-guide.txt
+++ b/Documentation/cpu-freq/user-guide.txt
@@ -196,8 +196,6 @@ affected_cpus :			List of Online CPUs that require software
 related_cpus :			List of Online + Offline CPUs that need software
 				coordination of frequency.
 
-scaling_driver :		Hardware driver for cpufreq.
-
 scaling_cur_freq :		Current frequency of the CPU as determined by
 				the governor and cpufreq core, in KHz. This is
 				the frequency the kernel thinks the CPU runs
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 4f3dbc8cf729..611cb09239eb 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -5,7 +5,7 @@
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
+	depends on (ARM_CPU_TOPOLOGY || ARM64) && HAVE_CLK
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
diff --git a/drivers/cpufreq/arm_big_little.c b/drivers/cpufreq/arm_big_little.c
index e1a6ba66a7f5..f1e42f8ce0fc 100644
--- a/drivers/cpufreq/arm_big_little.c
+++ b/drivers/cpufreq/arm_big_little.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
-#include <asm/bL_switcher.h>
 
 #include "arm_big_little.h"
 
@@ -41,12 +40,16 @@
 #define MAX_CLUSTERS	2
 
 #ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
 static bool bL_switching_enabled;
 #define is_bL_switching_enabled()	bL_switching_enabled
 #define set_switching_enabled(x)	(bL_switching_enabled = (x))
 #else
 #define is_bL_switching_enabled()	false
 #define set_switching_enabled(x)	do { } while (0)
+#define bL_switch_request(...)		do { } while (0)
+#define bL_switcher_put_enabled()	do { } while (0)
+#define bL_switcher_get_enabled()	do { } while (0)
 #endif
 
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
@@ -186,6 +189,15 @@ bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
 		mutex_unlock(&cluster_lock[old_cluster]);
 	}
 
+	/*
+	 * FIXME: clk_set_rate has to handle the case where clk_change_rate
+	 * can fail due to hardware or firmware issues. Until the clk core
+	 * layer is fixed, we can check here. In most of the cases we will
+	 * be reading only the cached value anyway. This needs to  be removed
+	 * once clk core is fixed.
+	 */
+	if (bL_cpufreq_get_rate(cpu) != new_rate)
+		return -EIO;
 	return 0;
 }
 
@@ -322,7 +334,6 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
-	char name[14] = "cpu-cluster.";
 	int ret;
 
 	if (freq_table[cluster])
@@ -342,8 +353,7 @@ static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 		goto free_opp_table;
 	}
 
-	name[12] = cluster + '0';
-	clk[cluster] = clk_get(cpu_dev, name);
+	clk[cluster] = clk_get(cpu_dev, NULL);
 	if (!IS_ERR(clk[cluster])) {
 		dev_dbg(cpu_dev, "%s: clk: %p & freq table: %p, cluster: %d\n",
 				__func__, clk[cluster], freq_table[cluster],
@@ -506,6 +516,7 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.attr			= cpufreq_generic_attr,
 };
 
+#ifdef CONFIG_BL_SWITCHER
 static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
 					unsigned long action, void *_arg)
 {
@@ -538,6 +549,20 @@ static struct notifier_block bL_switcher_notifier = {
 	.notifier_call = bL_cpufreq_switcher_notifier,
 };
 
+static int __bLs_register_notifier(void)
+{
+	return bL_switcher_register_notifier(&bL_switcher_notifier);
+}
+
+static int __bLs_unregister_notifier(void)
+{
+	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
+}
+#else
+static int __bLs_register_notifier(void) { return 0; }
+static int __bLs_unregister_notifier(void) { return 0; }
+#endif
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 {
 	int ret, i;
@@ -555,8 +580,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 
 	arm_bL_ops = ops;
 
-	ret = bL_switcher_get_enabled();
-	set_switching_enabled(ret);
+	set_switching_enabled(bL_switcher_get_enabled());
 
 	for (i = 0; i < MAX_CLUSTERS; i++)
 		mutex_init(&cluster_lock[i]);
@@ -567,7 +591,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 				__func__, ops->name, ret);
 		arm_bL_ops = NULL;
 	} else {
-		ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+		ret = __bLs_register_notifier();
 		if (ret) {
 			cpufreq_unregister_driver(&bL_cpufreq_driver);
 			arm_bL_ops = NULL;
@@ -591,7 +615,7 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 	}
 
 	bL_switcher_get_enabled();
-	bL_switcher_unregister_notifier(&bL_switcher_notifier);
+	__bLs_unregister_notifier();
 	cpufreq_unregister_driver(&bL_cpufreq_driver);
 	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index bab67db54b7e..528a82bf5038 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -416,6 +416,7 @@ static struct platform_driver dt_cpufreq_platdrv = {
 };
 module_platform_driver(dt_cpufreq_platdrv);
 
+MODULE_ALIAS("platform:cpufreq-dt");
 MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
 MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
 MODULE_DESCRIPTION("Generic cpufreq driver");
diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c
index a2258090b58b..db69eeb501a7 100644
--- a/drivers/cpufreq/cpufreq-nforce2.c
+++ b/drivers/cpufreq/cpufreq-nforce2.c
@@ -414,7 +414,7 @@ static int nforce2_detect_chipset(void)
  * nforce2_init - initializes the nForce2 CPUFreq driver
  *
  * Initializes the nForce2 FSB support. Returns -ENODEV on unsupported
- * devices, -EINVAL on problems during initiatization, and zero on
+ * devices, -EINVAL on problems during initialization, and zero on
  * success.
  */
 static int __init nforce2_init(void)
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 8ae655c364f4..b612411655f9 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -31,10 +31,62 @@
 #include <linux/tick.h>
 #include <trace/events/power.h>
 
-/* Macros to iterate over lists */
-/* Iterate over online CPUs policies */
 static LIST_HEAD(cpufreq_policy_list);
-#define for_each_policy(__policy)				\
+
+static inline bool policy_is_inactive(struct cpufreq_policy *policy)
+{
+	return cpumask_empty(policy->cpus);
+}
+
+static bool suitable_policy(struct cpufreq_policy *policy, bool active)
+{
+	return active == !policy_is_inactive(policy);
+}
+
+/* Finds Next Acive/Inactive policy */
+static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
+					  bool active)
+{
+	do {
+		policy = list_next_entry(policy, policy_list);
+
+		/* No more policies in the list */
+		if (&policy->policy_list == &cpufreq_policy_list)
+			return NULL;
+	} while (!suitable_policy(policy, active));
+
+	return policy;
+}
+
+static struct cpufreq_policy *first_policy(bool active)
+{
+	struct cpufreq_policy *policy;
+
+	/* No policies in the list */
+	if (list_empty(&cpufreq_policy_list))
+		return NULL;
+
+	policy = list_first_entry(&cpufreq_policy_list, typeof(*policy),
+				  policy_list);
+
+	if (!suitable_policy(policy, active))
+		policy = next_policy(policy, active);
+
+	return policy;
+}
+
+/* Macros to iterate over CPU policies */
+#define for_each_suitable_policy(__policy, __active)	\
+	for (__policy = first_policy(__active);		\
+	     __policy;					\
+	     __policy = next_policy(__policy, __active))
+
+#define for_each_active_policy(__policy)		\
+	for_each_suitable_policy(__policy, true)
+#define for_each_inactive_policy(__policy)		\
+	for_each_suitable_policy(__policy, false)
+
+#define for_each_policy(__policy)			\
 	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list)
 
 /* Iterate over governors */
@@ -49,13 +101,9 @@ static LIST_HEAD(cpufreq_governor_list);
  */
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
-static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 DEFINE_MUTEX(cpufreq_governor_lock);
 
-/* This one keeps track of the previously set governor of a removed CPU */
-static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
-
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -178,7 +226,7 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 	policy->cpuinfo.transition_latency = transition_latency;
 
 	/*
-	 * The driver only supports the SMP configuartion where all processors
+	 * The driver only supports the SMP configuration where all processors
 	 * share the clock and voltage and clock.
 	 */
 	cpumask_setall(policy->cpus);
@@ -187,10 +235,18 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_init);
 
-unsigned int cpufreq_generic_get(unsigned int cpu)
+/* Only for cpufreq core internal use */
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
+	return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL;
+}
+
+unsigned int cpufreq_generic_get(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+
 	if (!policy || IS_ERR(policy->clk)) {
 		pr_err("%s: No %s associated to cpu: %d\n",
 		       __func__, policy ? "clk" : "policy", cpu);
@@ -201,18 +257,29 @@ unsigned int cpufreq_generic_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_get);
 
-/* Only for cpufreq core internal use */
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
-{
-	return per_cpu(cpufreq_cpu_data, cpu);
-}
-
+/**
+ * cpufreq_cpu_get: returns policy for a cpu and marks it busy.
+ *
+ * @cpu: cpu to find policy for.
+ *
+ * This returns policy for 'cpu', returns NULL if it doesn't exist.
+ * It also increments the kobject reference count to mark it busy and so would
+ * require a corresponding call to cpufreq_cpu_put() to decrement it back.
+ * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be
+ * freed as that depends on the kobj count.
+ *
+ * It also takes a read-lock of 'cpufreq_rwsem' and doesn't put it back if a
+ * valid policy is found. This is done to make sure the driver doesn't get
+ * unregistered while the policy is being used.
+ *
+ * Return: A valid policy on success, otherwise NULL on failure.
+ */
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = NULL;
 	unsigned long flags;
 
-	if (cpu >= nr_cpu_ids)
+	if (WARN_ON(cpu >= nr_cpu_ids))
 		return NULL;
 
 	if (!down_read_trylock(&cpufreq_rwsem))
@@ -223,7 +290,7 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 
 	if (cpufreq_driver) {
 		/* get the CPU */
-		policy = per_cpu(cpufreq_cpu_data, cpu);
+		policy = cpufreq_cpu_get_raw(cpu);
 		if (policy)
 			kobject_get(&policy->kobj);
 	}
@@ -237,6 +304,16 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
 
+/**
+ * cpufreq_cpu_put: Decrements the usage count of a policy
+ *
+ * @policy: policy earlier returned by cpufreq_cpu_get().
+ *
+ * This decrements the kobject reference count incremented earlier by calling
+ * cpufreq_cpu_get().
+ *
+ * It also drops the read-lock of 'cpufreq_rwsem' taken at cpufreq_cpu_get().
+ */
 void cpufreq_cpu_put(struct cpufreq_policy *policy)
 {
 	kobject_put(&policy->kobj);
@@ -798,11 +875,18 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 
 	down_write(&policy->rwsem);
 
+	/* Updating inactive policies is invalid, so avoid doing that. */
+	if (unlikely(policy_is_inactive(policy))) {
+		ret = -EBUSY;
+		goto unlock_policy_rwsem;
+	}
+
 	if (fattr->store)
 		ret = fattr->store(policy, buf, count);
 	else
 		ret = -EIO;
 
+unlock_policy_rwsem:
 	up_write(&policy->rwsem);
 
 	up_read(&cpufreq_rwsem);
@@ -873,28 +957,67 @@ void cpufreq_sysfs_remove_file(const struct attribute *attr)
 }
 EXPORT_SYMBOL(cpufreq_sysfs_remove_file);
 
-/* symlink affected CPUs */
+static int add_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+{
+	struct device *cpu_dev;
+
+	pr_debug("%s: Adding symlink for CPU: %u\n", __func__, cpu);
+
+	if (!policy)
+		return 0;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (WARN_ON(!cpu_dev))
+		return 0;
+
+	return sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq");
+}
+
+static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+{
+	struct device *cpu_dev;
+
+	pr_debug("%s: Removing symlink for CPU: %u\n", __func__, cpu);
+
+	cpu_dev = get_cpu_device(cpu);
+	if (WARN_ON(!cpu_dev))
+		return;
+
+	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
+}
+
+/* Add/remove symlinks for all related CPUs */
 static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
 {
 	unsigned int j;
 	int ret = 0;
 
-	for_each_cpu(j, policy->cpus) {
-		struct device *cpu_dev;
-
-		if (j == policy->cpu)
+	/* Some related CPUs might not be present (physically hotplugged) */
+	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+		if (j == policy->kobj_cpu)
 			continue;
 
-		pr_debug("Adding link for CPU: %u\n", j);
-		cpu_dev = get_cpu_device(j);
-		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
-					"cpufreq");
+		ret = add_cpu_dev_symlink(policy, j);
 		if (ret)
 			break;
 	}
+
 	return ret;
 }
 
+static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
+{
+	unsigned int j;
+
+	/* Some related CPUs might not be present (physically hotplugged) */
+	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+		if (j == policy->kobj_cpu)
+			continue;
+
+		remove_cpu_dev_symlink(policy, j);
+	}
+}
+
 static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 				     struct device *dev)
 {
@@ -937,7 +1060,7 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy)
 	memcpy(&new_policy, policy, sizeof(*policy));
 
 	/* Update governor of new_policy to the governor used before hotplug */
-	gov = find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu));
+	gov = find_governor(policy->last_governor);
 	if (gov)
 		pr_debug("Restoring governor %s for cpu %d\n",
 				policy->governor->name, policy->cpu);
@@ -963,7 +1086,10 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 				  unsigned int cpu, struct device *dev)
 {
 	int ret = 0;
-	unsigned long flags;
+
+	/* Has this CPU been taken care of already? */
+	if (cpumask_test_cpu(cpu, policy->cpus))
+		return 0;
 
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
@@ -974,13 +1100,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 	}
 
 	down_write(&policy->rwsem);
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-
 	cpumask_set_cpu(cpu, policy->cpus);
-	per_cpu(cpufreq_cpu_data, cpu) = policy;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
 	up_write(&policy->rwsem);
 
 	if (has_target()) {
@@ -994,7 +1114,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 		}
 	}
 
-	return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
+	return 0;
 }
 
 static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
@@ -1003,20 +1123,25 @@ static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
 	unsigned long flags;
 
 	read_lock_irqsave(&cpufreq_driver_lock, flags);
-
-	policy = per_cpu(cpufreq_cpu_data_fallback, cpu);
-
+	policy = per_cpu(cpufreq_cpu_data, cpu);
 	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	if (policy)
-		policy->governor = NULL;
+	if (likely(policy)) {
+		/* Policy should be inactive here */
+		WARN_ON(!policy_is_inactive(policy));
+
+		down_write(&policy->rwsem);
+		policy->cpu = cpu;
+		up_write(&policy->rwsem);
+	}
 
 	return policy;
 }
 
-static struct cpufreq_policy *cpufreq_policy_alloc(void)
+static struct cpufreq_policy *cpufreq_policy_alloc(struct device *dev)
 {
 	struct cpufreq_policy *policy;
+	int ret;
 
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
 	if (!policy)
@@ -1028,6 +1153,13 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
 		goto err_free_cpumask;
 
+	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj,
+				   "cpufreq");
+	if (ret) {
+		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
+		goto err_free_rcpumask;
+	}
+
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1035,8 +1167,15 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
+	policy->cpu = dev->id;
+
+	/* Set this once on allocation */
+	policy->kobj_cpu = dev->id;
+
 	return policy;
 
+err_free_rcpumask:
+	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
 	free_cpumask_var(policy->cpus);
 err_free_policy:
@@ -1045,18 +1184,20 @@ err_free_policy:
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 {
 	struct kobject *kobj;
 	struct completion *cmp;
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_REMOVE_POLICY, policy);
+	if (notify)
+		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+					     CPUFREQ_REMOVE_POLICY, policy);
 
-	down_read(&policy->rwsem);
+	down_write(&policy->rwsem);
+	cpufreq_remove_dev_symlink(policy);
 	kobj = &policy->kobj;
 	cmp = &policy->kobj_unregister;
-	up_read(&policy->rwsem);
+	up_write(&policy->rwsem);
 	kobject_put(kobj);
 
 	/*
@@ -1069,68 +1210,64 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
 	pr_debug("wait complete\n");
 }
 
-static void cpufreq_policy_free(struct cpufreq_policy *policy)
-{
-	free_cpumask_var(policy->related_cpus);
-	free_cpumask_var(policy->cpus);
-	kfree(policy);
-}
-
-static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu,
-			     struct device *cpu_dev)
+static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
 {
-	int ret;
-
-	if (WARN_ON(cpu == policy->cpu))
-		return 0;
+	unsigned long flags;
+	int cpu;
 
-	/* Move kobject to the new policy->cpu */
-	ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
-	if (ret) {
-		pr_err("%s: Failed to move kobj: %d\n", __func__, ret);
-		return ret;
-	}
+	/* Remove policy from list */
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	list_del(&policy->policy_list);
 
-	down_write(&policy->rwsem);
-	policy->cpu = cpu;
-	up_write(&policy->rwsem);
+	for_each_cpu(cpu, policy->related_cpus)
+		per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	return 0;
+	cpufreq_policy_put_kobj(policy, notify);
+	free_cpumask_var(policy->related_cpus);
+	free_cpumask_var(policy->cpus);
+	kfree(policy);
 }
 
-static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+/**
+ * cpufreq_add_dev - add a CPU device
+ *
+ * Adds the cpufreq interface for a CPU device.
+ *
+ * The Oracle says: try running cpufreq registration/unregistration concurrently
+ * with with cpu hotplugging and all hell will break loose. Tried to clean this
+ * mess up, but more thorough testing is needed. - Mathieu
+ */
+static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int j, cpu = dev->id;
 	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
-	bool recover_policy = cpufreq_suspended;
-
-	if (cpu_is_offline(cpu))
-		return 0;
+	bool recover_policy = !sif;
 
 	pr_debug("adding CPU %u\n", cpu);
 
-	/* check whether a different CPU already registered this
-	 * CPU because it is in the same boat. */
-	policy = cpufreq_cpu_get_raw(cpu);
-	if (unlikely(policy))
-		return 0;
+	/*
+	 * Only possible if 'cpu' wasn't physically present earlier and we are
+	 * here from subsys_interface add callback. A hotplug notifier will
+	 * follow and we will handle it like logical CPU hotplug then. For now,
+	 * just create the sysfs link.
+	 */
+	if (cpu_is_offline(cpu))
+		return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu);
 
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return 0;
 
-	/* Check if this cpu was hot-unplugged earlier and has siblings */
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_policy(policy) {
-		if (cpumask_test_cpu(cpu, policy->related_cpus)) {
-			read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-			ret = cpufreq_add_policy_cpu(policy, cpu, dev);
-			up_read(&cpufreq_rwsem);
-			return ret;
-		}
+	/* Check if this CPU already has a policy to manage it */
+	policy = per_cpu(cpufreq_cpu_data, cpu);
+	if (policy && !policy_is_inactive(policy)) {
+		WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus));
+		ret = cpufreq_add_policy_cpu(policy, cpu, dev);
+		up_read(&cpufreq_rwsem);
+		return ret;
 	}
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	/*
 	 * Restore the saved policy when doing light-weight init and fall back
@@ -1139,22 +1276,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	policy = recover_policy ? cpufreq_policy_restore(cpu) : NULL;
 	if (!policy) {
 		recover_policy = false;
-		policy = cpufreq_policy_alloc();
+		policy = cpufreq_policy_alloc(dev);
 		if (!policy)
 			goto nomem_out;
 	}
 
-	/*
-	 * In the resume path, since we restore a saved policy, the assignment
-	 * to policy->cpu is like an update of the existing policy, rather than
-	 * the creation of a brand new one. So we need to perform this update
-	 * by invoking update_policy_cpu().
-	 */
-	if (recover_policy && cpu != policy->cpu)
-		WARN_ON(update_policy_cpu(policy, cpu, dev));
-	else
-		policy->cpu = cpu;
-
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
 	/* call driver. From then on the cpufreq must be able
@@ -1181,21 +1307,12 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		policy->user_policy.min = policy->min;
 		policy->user_policy.max = policy->max;
 
-		/* prepare interface data */
-		ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
-					   &dev->kobj, "cpufreq");
-		if (ret) {
-			pr_err("%s: failed to init policy->kobj: %d\n",
-			       __func__, ret);
-			goto err_init_policy_kobj;
-		}
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		for_each_cpu(j, policy->related_cpus)
+			per_cpu(cpufreq_cpu_data, j) = policy;
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_cpu_data, j) = policy;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
@@ -1253,11 +1370,11 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 			goto err_out_unregister;
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
-	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	list_add(&policy->policy_list, &cpufreq_policy_list);
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		list_add(&policy->policy_list, &cpufreq_policy_list);
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	}
 
 	cpufreq_init_policy(policy);
 
@@ -1281,68 +1398,28 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 
 err_out_unregister:
 err_get_freq:
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_cpu_data, j) = NULL;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	if (!recover_policy) {
-		kobject_put(&policy->kobj);
-		wait_for_completion(&policy->kobj_unregister);
-	}
-err_init_policy_kobj:
 	up_write(&policy->rwsem);
 
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 err_set_policy_cpu:
-	if (recover_policy) {
-		/* Do not leave stale fallback data behind. */
-		per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL;
-		cpufreq_policy_put_kobj(policy);
-	}
-	cpufreq_policy_free(policy);
-
+	cpufreq_policy_free(policy, recover_policy);
 nomem_out:
 	up_read(&cpufreq_rwsem);
 
 	return ret;
 }
 
-/**
- * cpufreq_add_dev - add a CPU device
- *
- * Adds the cpufreq interface for a CPU device.
- *
- * The Oracle says: try running cpufreq registration/unregistration concurrently
- * with with cpu hotplugging and all hell will break loose. Tried to clean this
- * mess up, but more thorough testing is needed. - Mathieu
- */
-static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
-{
-	return __cpufreq_add_dev(dev, sif);
-}
-
 static int __cpufreq_remove_dev_prepare(struct device *dev,
 					struct subsys_interface *sif)
 {
-	unsigned int cpu = dev->id, cpus;
-	int ret;
-	unsigned long flags;
+	unsigned int cpu = dev->id;
+	int ret = 0;
 	struct cpufreq_policy *policy;
 
 	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-
-	policy = per_cpu(cpufreq_cpu_data, cpu);
-
-	/* Save the policy somewhere when doing a light-weight tear-down */
-	if (cpufreq_suspended)
-		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;
-
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
+	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
@@ -1354,108 +1431,75 @@ static int __cpufreq_remove_dev_prepare(struct device *dev,
 			pr_err("%s: Failed to stop governor\n", __func__);
 			return ret;
 		}
-
-		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
-			policy->governor->name, CPUFREQ_NAME_LEN);
 	}
 
-	down_read(&policy->rwsem);
-	cpus = cpumask_weight(policy->cpus);
-	up_read(&policy->rwsem);
+	down_write(&policy->rwsem);
+	cpumask_clear_cpu(cpu, policy->cpus);
 
-	if (cpu != policy->cpu) {
-		sysfs_remove_link(&dev->kobj, "cpufreq");
-	} else if (cpus > 1) {
+	if (policy_is_inactive(policy)) {
+		if (has_target())
+			strncpy(policy->last_governor, policy->governor->name,
+				CPUFREQ_NAME_LEN);
+	} else if (cpu == policy->cpu) {
 		/* Nominate new CPU */
-		int new_cpu = cpumask_any_but(policy->cpus, cpu);
-		struct device *cpu_dev = get_cpu_device(new_cpu);
+		policy->cpu = cpumask_any(policy->cpus);
+	}
+	up_write(&policy->rwsem);
 
-		sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
-		ret = update_policy_cpu(policy, new_cpu, cpu_dev);
-		if (ret) {
-			if (sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
-					      "cpufreq"))
-				pr_err("%s: Failed to restore kobj link to cpu:%d\n",
-				       __func__, cpu_dev->id);
-			return ret;
-		}
+	/* Start governor again for active policy */
+	if (!policy_is_inactive(policy)) {
+		if (has_target()) {
+			ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+			if (!ret)
+				ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
-		if (!cpufreq_suspended)
-			pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
-				 __func__, new_cpu, cpu);
+			if (ret)
+				pr_err("%s: Failed to start governor\n", __func__);
+		}
 	} else if (cpufreq_driver->stop_cpu) {
 		cpufreq_driver->stop_cpu(policy);
 	}
 
-	return 0;
+	return ret;
 }
 
 static int __cpufreq_remove_dev_finish(struct device *dev,
 				       struct subsys_interface *sif)
 {
-	unsigned int cpu = dev->id, cpus;
+	unsigned int cpu = dev->id;
 	int ret;
-	unsigned long flags;
-	struct cpufreq_policy *policy;
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	policy = per_cpu(cpufreq_cpu_data, cpu);
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
 	}
 
-	down_write(&policy->rwsem);
-	cpus = cpumask_weight(policy->cpus);
-
-	if (cpus > 1)
-		cpumask_clear_cpu(cpu, policy->cpus);
-	up_write(&policy->rwsem);
+	/* Only proceed for inactive policies */
+	if (!policy_is_inactive(po