Merge branch 'pm-cpufreq'

* pm-cpufreq: (55 commits)
  cpufreq / intel_pstate: Fix 32 bit build
  cpufreq: conservative: Fix typos in comments
  cpufreq: ondemand: Fix typos in comments
  cpufreq: exynos: simplify .init() for setting policy->cpus
  cpufreq: kirkwood: Add a cpufreq driver for Marvell Kirkwood SoCs
  cpufreq/x86: Add P-state driver for sandy bridge.
  cpufreq_stats: do not remove sysfs files if frequency table is not present
  cpufreq: Do not track governor name for scaling drivers with internal governors.
  cpufreq: Only call cpufreq_out_of_sync() for driver that implement cpufreq_driver.target()
  cpufreq: Retrieve current frequency from scaling drivers with internal governors
  cpufreq: Fix locking issues
  cpufreq: Create a macro for unlock_policy_rwsem{read,write}
  cpufreq: Remove unused HOTPLUG_CPU code
  cpufreq: governors: Fix WARN_ON() for multi-policy platforms
  cpufreq: ondemand: Replace down_differential tuner with adj_up_threshold
  cpufreq / stats: Get rid of CPUFREQ_STATDEVICE_ATTR
  cpufreq: Don't check cpu_online(policy->cpu)
  cpufreq: add imx6q-cpufreq driver
  cpufreq: Don't remove sysfs link for policy->cpu
  cpufreq: Remove unnecessary use of policy->shared_type
  ...

24 files changed, 2051 insertions, 415 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index e0a899f25e37..cbcb21e32771 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -185,7 +185,7 @@ config CPU_FREQ_GOV_CONSERVATIVE
 	  If in doubt, say N.
 
 config GENERIC_CPUFREQ_CPU0
-	bool "Generic CPU0 cpufreq driver"
+	tristate "Generic CPU0 cpufreq driver"
 	depends on HAVE_CLK && REGULATOR && PM_OPP && OF
 	select CPU_FREQ_TABLE
 	help
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index a0b3661d90b0..7f333af1c059 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -77,9 +77,39 @@ config ARM_EXYNOS5250_CPUFREQ
 	  This adds the CPUFreq driver for Samsung EXYNOS5250
 	  SoC.
 
+config ARM_KIRKWOOD_CPUFREQ
+	def_bool ARCH_KIRKWOOD && OF
+	help
+	  This adds the CPUFreq driver for Marvell Kirkwood
+	  SoCs.
+
+config ARM_IMX6Q_CPUFREQ
+	tristate "Freescale i.MX6Q cpufreq support"
+	depends on SOC_IMX6Q
+	depends on REGULATOR_ANATOP
+	help
+	  This adds cpufreq driver support for Freescale i.MX6Q SOC.
+
+	  If in doubt, say N.
+
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR
 	default y
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
+
+config ARM_HIGHBANK_CPUFREQ
+	tristate "Calxeda Highbank-based"
+	depends on ARCH_HIGHBANK
+	select CPU_FREQ_TABLE
+	select GENERIC_CPUFREQ_CPU0
+	select PM_OPP
+	select REGULATOR
+
+	default m
+	help
+	  This adds the CPUFreq driver for Calxeda Highbank SoC
+	  based boards.
+
+	  If in doubt, say N.
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
index 7227cd734042..6aa7053ce2ef 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -2,6 +2,24 @@
 # x86 CPU Frequency scaling drivers
 #
 
+config X86_INTEL_PSTATE
+       tristate "Intel P state control"
+       depends on X86
+       help
+          This driver provides a P state for Intel core processors.
+	  The driver implements an internal governor and will become
+          the scaling driver and governor for Sandy bridge processors.
+
+	  When this driver is enabled it will become the perferred
+          scaling driver for Sandy bridge processors.
+
+	  Note: This driver should be built with the same settings as
+	  the other scaling drivers configured into the system
+	  (module/built-in) in order for the driver to register itself
+	  as the scaling driver on the system.
+
+	  If in doubt, say N.
+
 config X86_PCC_CPUFREQ
 	tristate "Processor Clocking Control interface driver"
 	depends on ACPI && ACPI_PROCESSOR
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index fadc4d496e2f..5399c45ac311 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -19,11 +19,12 @@ obj-$(CONFIG_GENERIC_CPUFREQ_CPU0)	+= cpufreq-cpu0.o
 ##################################################################################
 # x86 drivers.
 # Link order matters. K8 is preferred to ACPI because of firmware bugs in early
-# K8 systems. ACPI is preferred to all other hardware-specific drivers.
+# K8 systems. This is still the case but acpi-cpufreq errors out so that
+# powernow-k8 can load then. ACPI is preferred to all other hardware-specific drivers.
 # speedstep-* is preferred over p4-clockmod.
 
-obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
+obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
 obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
@@ -39,6 +40,7 @@ obj-$(CONFIG_X86_SPEEDSTEP_SMI)		+= speedstep-smi.o
 obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO)	+= speedstep-centrino.o
 obj-$(CONFIG_X86_P4_CLOCKMOD)		+= p4-clockmod.o
 obj-$(CONFIG_X86_CPUFREQ_NFORCE2)	+= cpufreq-nforce2.o
+obj-$(CONFIG_X86_INTEL_PSTATE)		+= intel_pstate.o
 
 ##################################################################################
 # ARM SoC drivers
@@ -50,8 +52,11 @@ obj-$(CONFIG_ARM_EXYNOS_CPUFREQ)	+= exynos-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS4210_CPUFREQ)	+= exynos4210-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS4X12_CPUFREQ)	+= exynos4x12-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS5250_CPUFREQ)	+= exynos5250-cpufreq.o
-obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)     += omap-cpufreq.o
+obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ)	+= kirkwood-cpufreq.o
+obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
+obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ)	+= highbank-cpufreq.o
+obj-$(CONFIG_ARM_IMX6Q_CPUFREQ)		+= imx6q-cpufreq.o
 
 ##################################################################################
 # PowerPC platform drivers
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 7b0d49d78c61..937bc286591f 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -734,7 +734,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 #ifdef CONFIG_SMP
 	dmi_check_system(sw_any_bug_dmi_table);
-	if (bios_with_sw_any_bug && cpumask_weight(policy->cpus) == 1) {
+	if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
 		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
 	}
@@ -762,6 +762,12 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	switch (perf->control_register.space_id) {
 	case ACPI_ADR_SPACE_SYSTEM_IO:
+		if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
+		    boot_cpu_data.x86 == 0xf) {
+			pr_debug("AMD K8 systems must use native drivers.\n");
+			result = -ENODEV;
+			goto err_unreg;
+		}
 		pr_debug("SYSTEM IO addr space\n");
 		data->cpu_feature = SYSTEM_IO_CAPABLE;
 		break;
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index debc5a7c8db6..4e5b7fb8927c 100644
--- a/drivers/cpufreq/cpufreq-cpu0.c
+++ b/drivers/cpufreq/cpufreq-cpu0.c
@@ -12,12 +12,12 @@
 #define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
 
 #include <linux/clk.h>
-#include <linux/cpu.h>
 #include <linux/cpufreq.h>
 #include <linux/err.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/opp.h>
+#include <linux/platform_device.h>
 #include <linux/regulator/consumer.h>
 #include <linux/slab.h>
 
@@ -146,7 +146,6 @@ static int cpu0_cpufreq_init(struct cpufreq_policy *policy)
 	 * share the clock and voltage and clock.  Use cpufreq affected_cpus
 	 * interface to have all CPUs scaled together.
 	 */
-	policy->shared_type = CPUFREQ_SHARED_TYPE_ANY;
 	cpumask_setall(policy->cpus);
 
 	cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
@@ -177,34 +176,32 @@ static struct cpufreq_driver cpu0_cpufreq_driver = {
 	.attr = cpu0_cpufreq_attr,
 };
 
-static int cpu0_cpufreq_driver_init(void)
+static int cpu0_cpufreq_probe(struct platform_device *pdev)
 {
 	struct device_node *np;
 	int ret;
 
-	np = of_find_node_by_path("/cpus/cpu@0");
+	for_each_child_of_node(of_find_node_by_path("/cpus"), np) {
+		if (of_get_property(np, "operating-points", NULL))
+			break;
+	}
+
 	if (!np) {
 		pr_err("failed to find cpu0 node\n");
 		return -ENOENT;
 	}
 
-	cpu_dev = get_cpu_device(0);
-	if (!cpu_dev) {
-		pr_err("failed to get cpu0 device\n");
-		ret = -ENODEV;
-		goto out_put_node;
-	}
-
+	cpu_dev = &pdev->dev;
 	cpu_dev->of_node = np;
 
-	cpu_clk = clk_get(cpu_dev, NULL);
+	cpu_clk = devm_clk_get(cpu_dev, NULL);
 	if (IS_ERR(cpu_clk)) {
 		ret = PTR_ERR(cpu_clk);
 		pr_err("failed to get cpu0 clock: %d\n", ret);
 		goto out_put_node;
 	}
 
-	cpu_reg = regulator_get(cpu_dev, "cpu0");
+	cpu_reg = devm_regulator_get(cpu_dev, "cpu0");
 	if (IS_ERR(cpu_reg)) {
 		pr_warn("failed to get cpu0 regulator\n");
 		cpu_reg = NULL;
@@ -267,7 +264,24 @@ out_put_node:
 	of_node_put(np);
 	return ret;
 }
-late_initcall(cpu0_cpufreq_driver_init);
+
+static int cpu0_cpufreq_remove(struct platform_device *pdev)
+{
+	cpufreq_unregister_driver(&cpu0_cpufreq_driver);
+	opp_free_cpufreq_table(cpu_dev, &freq_table);
+
+	return 0;
+}
+
+static struct platform_driver cpu0_cpufreq_platdrv = {
+	.driver = {
+		.name	= "cpufreq-cpu0",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= cpu0_cpufreq_probe,
+	.remove		= cpu0_cpufreq_remove,
+};
+module_platform_driver(cpu0_cpufreq_platdrv);
 
 MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
 MODULE_DESCRIPTION("Generic CPU0 cpufreq driver");
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 99faadf454ec..b02824d092e7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -59,8 +59,6 @@ static DEFINE_SPINLOCK(cpufreq_driver_lock);
  *   mode before doing so.
  *
  * Additional rules:
- * - All holders of the lock should check to make sure that the CPU they
- *   are concerned with are online after they get the lock.
  * - Governor routines that can be called in cpufreq hotplug path should not
  *   take this sem as top level hotplug notifier handler takes this.
  * - Lock should not be held across
@@ -70,38 +68,28 @@ static DEFINE_PER_CPU(int, cpufreq_policy_cpu);
 static DEFINE_PER_CPU(struct rw_semaphore, cpu_policy_rwsem);
 
 #define lock_policy_rwsem(mode, cpu)					\
-static int lock_policy_rwsem_##mode					\
-(int cpu)								\
+static int lock_policy_rwsem_##mode(int cpu)				\
 {									\
 	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);		\
 	BUG_ON(policy_cpu == -1);					\
 	down_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));		\
-	if (unlikely(!cpu_online(cpu))) {				\
-		up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));	\
-		return -1;						\
-	}								\
 									\
 	return 0;							\
 }
 
 lock_policy_rwsem(read, cpu);
-
 lock_policy_rwsem(write, cpu);
 
-static void unlock_policy_rwsem_read(int cpu)
-{
-	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
-	BUG_ON(policy_cpu == -1);
-	up_read(&per_cpu(cpu_policy_rwsem, policy_cpu));
-}
-
-static void unlock_policy_rwsem_write(int cpu)
-{
-	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);
-	BUG_ON(policy_cpu == -1);
-	up_write(&per_cpu(cpu_policy_rwsem, policy_cpu));
+#define unlock_policy_rwsem(mode, cpu)					\
+static void unlock_policy_rwsem_##mode(int cpu)				\
+{									\
+	int policy_cpu = per_cpu(cpufreq_policy_cpu, cpu);		\
+	BUG_ON(policy_cpu == -1);					\
+	up_##mode(&per_cpu(cpu_policy_rwsem, policy_cpu));		\
 }
 
+unlock_policy_rwsem(read, cpu);
+unlock_policy_rwsem(write, cpu);
 
 /* internal prototypes */
 static int __cpufreq_governor(struct cpufreq_policy *policy,
@@ -180,6 +168,9 @@ err_out:
 
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
+	if (cpufreq_disabled())
+		return NULL;
+
 	return __cpufreq_cpu_get(cpu, false);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
@@ -198,6 +189,9 @@ static void __cpufreq_cpu_put(struct cpufreq_policy *data, bool sysfs)
 
 void cpufreq_cpu_put(struct cpufreq_policy *data)
 {
+	if (cpufreq_disabled())
+		return;
+
 	__cpufreq_cpu_put(data, false);
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_put);
@@ -261,14 +255,21 @@ static inline void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
 {
 	struct cpufreq_policy *policy;
+	unsigned long flags;
 
 	BUG_ON(irqs_disabled());
 
+	if (cpufreq_disabled())
+		return;
+
 	freqs->flags = cpufreq_driver->flags;
 	pr_debug("notification %u of frequency transition to %u kHz\n",
 		state, freqs->new);
 
+	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	policy = per_cpu(cpufreq_cpu_data, freqs->cpu);
+	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
 	switch (state) {
 
 	case CPUFREQ_PRECHANGE:
@@ -542,8 +543,6 @@ static ssize_t show_cpus(const struct cpumask *mask, char *buf)
  */
 static ssize_t show_related_cpus(struct cpufreq_policy *policy, char *buf)
 {
-	if (cpumask_empty(policy->related_cpus))
-		return show_cpus(policy->cpus, buf);
 	return show_cpus(policy->related_cpus, buf);
 }
 
@@ -699,87 +698,6 @@ 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)
@@ -793,8 +711,6 @@ static int cpufreq_add_dev_symlink(unsigned int cpu,
 
 		if (j == cpu)
 			continue;
-		if (!cpu_online(j))
-			continue;
 
 		pr_debug("CPU %u already managed, adding link\n", j);
 		managed_policy = cpufreq_cpu_get(cpu);
@@ -851,8 +767,6 @@ static int cpufreq_add_dev_interface(unsigned int cpu,
 
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus) {
-		if (!cpu_online(j))
-			continue;
 		per_cpu(cpufreq_cpu_data, j) = policy;
 		per_cpu(cpufreq_policy_cpu, j) = policy->cpu;
 	}
@@ -884,6 +798,42 @@ 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);
+
+	__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+
+	lock_policy_rwsem_write(sibling);
+
+	spin_lock_irqsave(&cpufreq_driver_lock, flags);
+
+	cpumask_set_cpu(cpu, policy->cpus);
+	per_cpu(cpufreq_policy_cpu, cpu) = policy->cpu;
+	per_cpu(cpufreq_cpu_data, cpu) = policy;
+	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+
+	unlock_policy_rwsem_write(sibling);
+
+	__cpufreq_governor(policy, CPUFREQ_GOV_START);
+	__cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
+
+	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
@@ -896,12 +846,12 @@ 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;
 	struct cpufreq_policy *policy;
 	unsigned long flags;
-	unsigned int j;
 #ifdef CONFIG_HOTPLUG_CPU
+	struct cpufreq_governor *gov;
 	int sibling;
 #endif
 
@@ -918,6 +868,19 @@ 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 */
+	spin_lock_irqsave(&cpufreq_driver_lock, flags);
+	for_each_online_cpu(sibling) {
+		struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
+		if (cp && cpumask_test_cpu(cpu, cp->related_cpus)) {
+			spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+			return cpufreq_add_policy_cpu(cpu, sibling, dev);
+		}
+	}
+	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+#endif
 #endif
 
 	if (!try_module_get(cpufreq_driver->owner)) {
@@ -925,7 +888,6 @@ 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;
@@ -937,66 +899,58 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 		goto err_free_cpumask;
 
 	policy->cpu = cpu;
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
 	/* Initially set CPU itself as the policy_cpu */
 	per_cpu(cpufreq_policy_cpu, cpu) = cpu;
-	ret = (lock_policy_rwsem_write(cpu) < 0);
-	WARN_ON(ret);
 
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
-	/* Set governor before ->init, so that driver could check it */
-#ifdef CONFIG_HOTPLUG_CPU
-	for_each_online_cpu(sibling) {
-		struct cpufreq_policy *cp = per_cpu(cpufreq_cpu_data, sibling);
-		if (cp && cp->governor &&
-		    (cpumask_test_cpu(cpu, cp->related_cpus))) {
-			policy->governor = cp->governor;
-			found = 1;
-			break;
-		}
-	}
-#endif
-	if (!found)
-		policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
 	/* call driver. From then on the cpufreq must be able
 	 * to accept all calls to ->verify and ->setpolicy for this CPU
 	 */
 	ret = cpufreq_driver->init(policy);
 	if (ret) {
 		pr_debug("initialization failed\n");
-		goto err_unlock_policy;
+		goto err_set_policy_cpu;
 	}
+
+	/* related cpus should atleast have policy->cpus */
+	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+
+	/*
+	 * 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);
+
 	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)
 		goto err_out_unregister;
 
-	unlock_policy_rwsem_write(cpu);
-
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
 	module_put(cpufreq_driver->owner);
 	pr_debug("initialization complete\n");
 
 	return 0;
 
-
 err_out_unregister:
 	spin_lock_irqsave(&cpufreq_driver_lock, flags);
 	for_each_cpu(j, policy->cpus)
@@ -1006,8 +960,8 @@ err_out_unregister:
 	kobject_put(&policy->kobj);
 	wait_for_completion(&policy->kobj_unregister);
 
-err_unlock_policy:
-	unlock_policy_rwsem_write(cpu);
+err_set_policy_cpu:
+	per_cpu(cpufreq_policy_cpu, cpu) = -1;
 	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
 	free_cpumask_var(policy->cpus);
@@ -1019,6 +973,22 @@ 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)
+		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
@@ -1029,129 +999,103 @@ 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);
+	per_cpu(cpufreq_cpu_data, cpu) = NULL;
+
+	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	if (!data) {
-		spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-		unlock_policy_rwsem_write(cpu);
+		pr_debug("%s: No cpu_data found\n", __func__);
 		return -EINVAL;
 	}
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
 
+	if (cpufreq_driver->target)
+		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
 
-#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;
-	}
+#ifdef CONFIG_HOTPLUG_CPU
+	if (!cpufreq_driver->setpolicy)
+		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
+			data->governor->name, CPUFREQ_NAME_LEN);
 #endif
 
-#ifdef CONFIG_SMP
+	WARN_ON(lock_policy_rwsem_write(cpu));
+	cpus = cpumask_weight(data->cpus);
+	cpumask_clear_cpu(cpu, data->cpus);
+	unlock_policy_rwsem_write(cpu);
 
-#ifdef CONFIG_HOTPLUG_CPU
-	strncpy(per_cpu(cpufreq_cpu_governor, cpu), data->governor->name,
-			CPUFREQ_NAME_LEN);
-#endif
+	if (cpu != data->cpu) {
+		sysfs_remove_link(&dev->kobj, "cpufreq");
+	} else if (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);
 
-	/* 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;
-		}
-	}
+			WARN_ON(lock_policy_rwsem_write(cpu));
+			cpumask_set_cpu(cpu, data->cpus);
 
-	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
+			spin_lock_irqsave(&cpufreq_driver_lock, flags);
+			per_cpu(cpufreq_cpu_data, cpu) = data;
+			spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	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;
 			unlock_policy_rwsem_write(cpu);
-			sysfs_remove_link(kobj, "cpufreq");
-			lock_policy_rwsem_write(cpu);
-			cpufreq_cpu_put(data);
-		}
-	}
-#else
-	spin_unlock_irqrestore(&cpufreq_driver_lock, flags);
-#endif
 
-	if (cpufreq_driver->target)
-		__cpufreq_governor(data, CPUFREQ_GOV_STOP);
+			ret = sysfs_create_link(&cpu_dev->kobj, &data->kobj,
+					"cpufreq");
+			return -EINVAL;
+		}
 
-	kobj = &data->kobj;
-	cmp = &data->kobj_unregister;
-	unlock_policy_rwsem_write(cpu);
-	kobject_put(kobj);
+		WARN_ON(lock_policy_rwsem_write(cpu));
+		update_policy_cpu(data, cpu_dev->id);
+		unlock_policy_rwsem_write(cpu);
+		pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
+				__func__, cpu_dev->id, cpu);
+	}
 
-	/* 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");
+	pr_debug("%s: removing link, cpu: %d\n", __func__, cpu);
+	cpufreq_cpu_put(data);
 
-	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_read(cpu);
+		kobj = &data->kobj;
+		cmp = &data->kobj_unregister;
+		unlock_policy_rwsem_read(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");
 
-#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);
+		if (cpufreq_driver->exit)
+			cpufreq_driver->exit(data);
 
-		/* finally remove our own symlink */
-		lock_policy_rwsem_write(cpu);
-		__cpufreq_remove_dev(dev, sif);
+		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);
 	}
-#endif
-
-	free_cpumask_var(data->related_cpus);
-	free_cpumask_var(data->cpus);
-	kfree(data);
 
+	per_cpu(cpufreq_policy_cpu, cpu) = -1;
 	return 0;
 }
 
@@ -1164,9 +1108,6 @@ static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 	if (cpu_is_offline(cpu))
 		return 0;
 
-	if (unlikely(lock_policy_rwsem_write(cpu)))
-		BUG();
-
 	retval = __cpufreq_remove_dev(dev, sif);
 	return retval;
 }
@@ -1215,9 +1156,13 @@ static void cpufreq_out_of_sync(unsigned int cpu, unsigned int old_freq,
  */
 unsigned int cpufreq_quick_get(unsigned int cpu)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(cpu);