Merge branch 'next' into for-linus

Prepare first set of updates for 3.10 merge window.

32 files changed, 3666 insertions, 2097 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index ea512f47b789..cbcb21e32771 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -20,6 +20,9 @@ if CPU_FREQ
 config CPU_FREQ_TABLE
 	tristate
 
+config CPU_FREQ_GOV_COMMON
+	bool
+
 config CPU_FREQ_STAT
 	tristate "CPU frequency translation statistics"
 	select CPU_FREQ_TABLE
@@ -141,6 +144,7 @@ config CPU_FREQ_GOV_USERSPACE
 config CPU_FREQ_GOV_ONDEMAND
 	tristate "'ondemand' cpufreq policy governor"
 	select CPU_FREQ_TABLE
+	select CPU_FREQ_GOV_COMMON
 	help
 	  'ondemand' - This driver adds a dynamic cpufreq policy governor.
 	  The governor does a periodic polling and 
@@ -159,6 +163,7 @@ config CPU_FREQ_GOV_ONDEMAND
 config CPU_FREQ_GOV_CONSERVATIVE
 	tristate "'conservative' cpufreq governor"
 	depends on CPU_FREQ
+	select CPU_FREQ_GOV_COMMON
 	help
 	  'conservative' - this driver is rather similar to the 'ondemand'
 	  governor both in its source code and its purpose, the difference is
@@ -180,7 +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 5961e6415f08..030ddf6dd3f1 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -21,8 +21,8 @@ config ARM_S3C2416_CPUFREQ
 	  If in doubt, say N.
 
 config ARM_S3C2416_CPUFREQ_VCORESCALE
-	bool "Allow voltage scaling for S3C2416 arm core (EXPERIMENTAL)"
-	depends on ARM_S3C2416_CPUFREQ && REGULATOR && EXPERIMENTAL
+	bool "Allow voltage scaling for S3C2416 arm core"
+	depends on ARM_S3C2416_CPUFREQ && REGULATOR
 	help
 	  Enable CPU voltage scaling when entering the dvs mode.
 	  It uses information gathered through existing hardware and
@@ -76,3 +76,40 @@ config ARM_EXYNOS5250_CPUFREQ
 	help
 	  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 934854ae5eb4..d7dc0ed6adb0 100644
--- a/drivers/cpufreq/Kconfig.x86
+++ b/drivers/cpufreq/Kconfig.x86
@@ -2,6 +2,19 @@
 # x86 CPU Frequency scaling drivers
 #
 
+config X86_INTEL_PSTATE
+       bool "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.
+
+	  If in doubt, say N.
+
 config X86_PCC_CPUFREQ
 	tristate "Processor Clocking Control interface driver"
 	depends on ACPI && ACPI_PROCESSOR
@@ -106,7 +119,7 @@ config X86_POWERNOW_K7_ACPI
 config X86_POWERNOW_K8
 	tristate "AMD Opteron/Athlon64 PowerNow!"
 	select CPU_FREQ_TABLE
-	depends on ACPI && ACPI_PROCESSOR
+	depends on ACPI && ACPI_PROCESSOR && X86_ACPI_CPUFREQ
 	help
 	  This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
 	  Support for K10 and newer processors is now in acpi-cpufreq.
@@ -174,7 +187,7 @@ config X86_SPEEDSTEP_ICH
 config X86_SPEEDSTEP_SMI
 	tristate "Intel SpeedStep on 440BX/ZX/MX chipsets (SMI interface)"
 	select CPU_FREQ_TABLE
-	depends on X86_32 && EXPERIMENTAL
+	depends on X86_32
 	help
 	  This adds the CPUFreq driver for certain mobile Intel Pentium III
 	  (Coppermine), all mobile Intel Pentium III-M (Tualatin)
@@ -206,7 +219,7 @@ config X86_P4_CLOCKMOD
 
 config X86_CPUFREQ_NFORCE2
 	tristate "nVidia nForce2 FSB changing"
-	depends on X86_32 && EXPERIMENTAL
+	depends on X86_32
 	help
 	  This adds the CPUFreq driver for FSB changing on nVidia nForce2
 	  platforms.
@@ -242,7 +255,7 @@ config X86_LONGHAUL
 config X86_E_POWERSAVER
 	tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
 	select CPU_FREQ_TABLE
-	depends on X86_32 && EXPERIMENTAL
+	depends on X86_32
 	help
 	  This adds the CPUFreq driver for VIA C7 processors.  However, this driver
 	  does not have any safeguards to prevent operating the CPU out of spec
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 1bc90e1306d8..863fd1865d45 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -9,6 +9,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_POWERSAVE)	+= cpufreq_powersave.o
 obj-$(CONFIG_CPU_FREQ_GOV_USERSPACE)	+= cpufreq_userspace.o
 obj-$(CONFIG_CPU_FREQ_GOV_ONDEMAND)	+= cpufreq_ondemand.o
 obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
+obj-$(CONFIG_CPU_FREQ_GOV_COMMON)		+= cpufreq_governor.o
 
 # CPUfreq cross-arch helpers
 obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o
@@ -18,11 +19,12 @@ obj-$(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
@@ -38,10 +40,11 @@ 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
-obj-$(CONFIG_UX500_SOC_DB8500)		+= db8500-cpufreq.o
+obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
 obj-$(CONFIG_ARM_S3C2416_CPUFREQ)	+= s3c2416-cpufreq.o
 obj-$(CONFIG_ARM_S3C64XX_CPUFREQ)	+= s3c64xx-cpufreq.o
 obj-$(CONFIG_ARM_S5PV210_CPUFREQ)	+= s5pv210-cpufreq.o
@@ -49,7 +52,11 @@ obj-$(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 0d048f6a2b23..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;
@@ -1030,4 +1036,11 @@ MODULE_PARM_DESC(acpi_pstate_strict,
 late_initcall(acpi_cpufreq_init);
 module_exit(acpi_cpufreq_exit);
 
+static const struct x86_cpu_id acpi_cpufreq_ids[] = {
+	X86_FEATURE_MATCH(X86_FEATURE_ACPI),
+	X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);
+
 MODULE_ALIAS("acpi");
diff --git a/drivers/cpufreq/cpufreq-cpu0.c b/drivers/cpufreq/cpufreq-cpu0.c
index e9158278c71d..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>
 
@@ -71,12 +71,15 @@ static int cpu0_set_target(struct cpufreq_policy *policy,
 	}
 
 	if (cpu_reg) {
+		rcu_read_lock();
 		opp = opp_find_freq_ceil(cpu_dev, &freq_Hz);
 		if (IS_ERR(opp)) {
+			rcu_read_unlock();
 			pr_err("failed to find OPP for %ld\n", freq_Hz);
 			return PTR_ERR(opp);
 		}
 		volt = opp_get_voltage(opp);
+		rcu_read_unlock();
 		tol = volt * voltage_tolerance / 100;
 		volt_old = regulator_get_voltage(cpu_reg);
 	}
@@ -143,7 +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);
@@ -174,34 +176,32 @@ static struct cpufreq_driver cpu0_cpufreq_driver = {
 	.attr = cpu0_cpufreq_attr,
 };
 
-static int __devinit 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;
@@ -236,12 +236,14 @@ static int __devinit cpu0_cpufreq_driver_init(void)
 		 */
 		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
 			;
+		rcu_read_lock();
 		opp = opp_find_freq_exact(cpu_dev,
 				freq_table[0].frequency * 1000, true);
 		min_uV = opp_get_voltage(opp);
 		opp = opp_find_freq_exact(cpu_dev,
 				freq_table[i-1].frequency * 1000, true);
 		max_uV = opp_get_voltage(opp);
+		rcu_read_unlock();
 		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
 		if (ret > 0)
 			transition_latency += ret * 1000;
@@ -262,7 +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 fb8a5279c5d8..b02824d092e7 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -15,6 +15,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -57,8 +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
@@ -68,38 +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,
@@ -127,7 +117,7 @@ static int __init init_cpufreq_transition_notifier_list(void)
 pure_initcall(init_cpufreq_transition_notifier_list);
 
 static int off __read_mostly;
-int cpufreq_disabled(void)
+static int cpufreq_disabled(void)
 {
 	return off;
 }
@@ -178,6 +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);
@@ -196,6 +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);
@@ -259,14 +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:
@@ -292,7 +295,6 @@ void cpufreq_notify_transition(struct cpufreq_freqs *freqs, unsigned int state)
 		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
 		pr_debug("FREQ: %lu - CPU: %lu", (unsigned long)freqs->new,
 			(unsigned long)freqs->cpu);
-		trace_power_frequency(POWER_PSTATE, freqs->new, freqs->cpu);
 		trace_cpu_frequency(freqs->new, freqs->cpu);
 		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
 				CPUFREQ_POSTCHANGE, freqs);
@@ -402,7 +404,7 @@ static int __cpufreq_set_policy(struct cpufreq_policy *data,
 static ssize_t store_##file_name					\
 (struct cpufreq_policy *policy, const char *buf, size_t count)		\
 {									\
-	unsigned int ret = -EINVAL;					\
+	unsigned int ret;						\
 	struct cpufreq_policy new_policy;				\
 									\
 	ret = cpufreq_get_policy(&new_policy, policy->cpu);		\
@@ -445,7 +447,7 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 	else if (policy->policy == CPUFREQ_POLICY_PERFORMANCE)
 		return sprintf(buf, "performance\n");
 	else if (policy->governor)
-		return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n",
+		return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n",
 				policy->governor->name);
 	return -EINVAL;
 }
@@ -457,7 +459,7 @@ static ssize_t show_scaling_governor(struct cpufreq_policy *policy, char *buf)
 static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 					const char *buf, size_t count)
 {
-	unsigned int ret = -EINVAL;
+	unsigned int ret;
 	char	str_governor[16];
 	struct cpufreq_policy new_policy;
 
@@ -491,7 +493,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
  */
 static ssize_t show_scaling_driver(struct cpufreq_policy *policy, char *buf)
 {
-	return scnprintf(buf, CPUFREQ_NAME_LEN, "%s\n", cpufreq_driver->name);
+	return scnprintf(buf, CPUFREQ_NAME_PLEN, "%s\n", cpufreq_driver->name);
 }
 
 /**
@@ -512,7 +514,7 @@ static ssize_t show_scaling_available_governors(struct cpufreq_policy *policy,
 		if (i >= (ssize_t) ((PAGE_SIZE / sizeof(char))
 		    - (CPUFREQ_NAME_LEN + 2)))
 			goto out;
-		i += scnprintf(&buf[i], CPUFREQ_NAME_LEN, "%s ", t->name);
+		i += scnprintf(&buf[i], CPUFREQ_NAME_PLEN, "%s ", t->name);
 	}
 out:
 	i += sprintf(&buf[i], "\n");
@@ -541,8 +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);
 }
 
@@ -581,7 +581,7 @@ static ssize_t show_scaling_setspeed(struct cpufreq_policy *policy, char *buf)
 }
 
 /**
- * show_scaling_driver - show the current cpufreq HW/BIOS limitation
+ * show_bios_limit - show the current cpufreq HW/BIOS limitation
  */
 static ssize_t show_bios_limit(struct cpufreq_policy *policy, char *buf)
 {
@@ -698,87 +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)
@@ -792,8 +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);
@@ -850,8 +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;
 	}
@@ -883,6 +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
@@ -895,12 +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
 
@@ -917,6 +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)) {
@@ -924,7 +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;
@@ -936,66 +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)
@@ -1005,8 +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);
@@ -1018,6 +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
@@ -1028,129 +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;
 }
 
@@ -1163,9 +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;
 }
@@ -1214,9 +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);
+	struct cpufreq_policy *policy;
 	unsigned int ret_freq = 0;
 
+	if (cpufreq_driver && cpufreq_driver->setpolicy && cpufreq_driver->get)
+		return cpufreq_driver->get(cpu);
+
+	policy = cpufreq_cpu_get(cpu);
 	if (policy) {
 		ret_freq = policy->cur;
 		cpufreq_cpu_put(policy);
@@ -1384,6 +1330,20 @@ static struct syscore_ops cpufreq_syscore_ops = {
 	.resume		= cpufreq_bp_resume,
 };
 
+/**
+ *	cpufreq_get_current_driver - return current driver's name
+ *
+ *	Return the name string of the currently loaded cpufreq driver
+ *	or NULL, if none.
+ */
+const char *cpufreq_get_current_driver(void)
+{
+	if (cpufreq_driver)
+		return cpufreq_driver->name;
+
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_get_current_driver);
 
 /*********************************************************************
  *                     NOTIFIER LISTS INTERFACE                      *
@@ -1406,6 +1366,9 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 {
 	int ret;
 
+	if (cpufreq_disabled())
+		return -EINVAL;
+
 	WARN_ON(!init_cpufreq_transition_notifier_list_called);
 
 	switch (list) {
@@ -1440,6 +1403,9 @@ int cpufreq_unregister_notifier(struct notifier_block *nb, unsigned int list)
 {
 	int ret;
 
+	if (cpufreq_disabled())
+		return -EINVAL;
+
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
 		ret = srcu_notifier_chain_unregister(
@@ -1468,13 +1434,24 @@ int __cpufreq_driver_target(struct cpufreq_policy *policy,
 			    unsigned int relation)
 {
 	int retval = -EINVAL;
+	unsigned int old_target_freq = target_freq;
 
 	if (cpufreq_disabled())
 		return -ENODEV;
 
-	pr_debug("target for CPU %u: %u kHz, relation %u\n", policy->cpu,
-		target_freq, relation);
-	if (cpu_online(policy->cpu) && cpufreq_driver->target)
+	/* Make sure that target_freq is within supported range */
+	if (target_freq > policy->max)
+		target_freq = policy->max;
+	if (target_freq < policy->min)
+		target_freq = policy->min;
+
+	pr_debug("target for CPU %u: %u kHz, relation %u, requested %u kHz\n",
+			policy->cpu, target_freq, relation, old_target_freq);
+
+	if (target_freq == policy->cur)
+		return 0;
+
+	if (cpufreq_driver->target)
 		retval = cpufreq_driver->target(policy, target_freq, relation);
 
 	return retval;
@@ -1509,12 +1486,17 @@ int __cpufreq_driver_getavg(struct cpufreq_policy *policy, unsigned int cpu)
 {
 	int ret = 0;
 
+	if (cpufreq_disabled())
+		return ret;
+
+	if (!cpufreq_driver->getavg)
+		return 0;
+
 	policy = cpufreq_cpu_get(policy->cpu);
 	if (!policy)
 		return -EINVAL;
 
-	if (cpu_online(cpu) && cpufreq_driver->getavg)
-		ret = cpufreq_driver->getavg(policy, cpu);
+	ret = cpufreq_driver->getavg(policy, cpu);
 
 	cpufreq_cpu_put(policy);
 	return ret;
@@ -1562,6 +1544,11 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 						policy->cpu, event);
 	ret = policy->governor->governor(policy, event);
 
+	if (event == CPUFREQ_GOV_START)
+		policy->governor->initialized++;
+	else if (event == CPUFREQ_GOV_STOP)
+		policy->governor->initialized--;
+
 	/* we keep one module reference alive for
 			each CPU governed by this CPU */
 	if ((event != CPUFREQ_GOV_START) || ret)
@@ -1585,6 +1572,7 @@ int cpufreq_register_governor(struct cpufreq_governor *governor)
 
 	mutex_lock(&cpufreq_governor_mutex);
 
+	governor->initialized = 0;
 	err = -EBUSY;
 	if (__find_governor(governor->name) == NULL) {
 		err = 0;
@@ -1782,7 +1770,7 @@ int cpufreq_update_policy(unsigned int cpu)
 			pr_debug("Driver did not initialize current freq");
 			data->cur = policy.cur;
 		} else {
-			if (data->cur != policy.cur)
+			if (data->cur != policy.cur && cpufreq_driver->target)
 				cpufreq_out_of_sync(cpu, data->cur,
 								policy.cur);
 		}
@@ -1814,9 +1802,6 @@ static int __cpuinit cpufreq_cpu_callback(struct notifier_block *nfb,
 			break;
 		case CPU_DOWN_PREPARE:
 		case CPU_DOWN_PREPARE_FROZEN:
-			if (unlikely(lock_policy_rwsem_write(cpu)))
-				BUG();
-
 			__cpufreq_remove_dev(dev, NULL);
 			break;
 		case CPU_DOWN_FAILED:
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index a152af7e1991..4fd0006b1291 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -11,83 +11,30 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
 #include <linux/cpufreq.h>
-#include <linux/cpu.h>
-#include <linux/jiffies.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/kernel_stat.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/hrtimer.h>
-#include <linux/tick.h>
-#include <linux/ktime.h>
-#include <linux/sched.h>
+#include <linux/notifier.h>
+#include <linux/percpu-defs.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
 
-/*
- * dbs is used in this file as a shortform for demandbased switching
- * It helps to keep variable names smaller, simpler
- */
+#include "cpufreq_governor.h"
 
+/* Conservative governor macros */
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_FREQUENCY_DOWN_THRESHOLD		(20)
-
-/*
- * The polling frequency of this governor depends on the capability of
- * the processor. Default polling frequency is 1000 times the transition
- * latency of the processor. The governor will work on any processor with
- * transition latency <= 10mS, using appropriate sampling
- * rate.
- * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work.
- * All times here are in uS.
- */
-#define MIN_SAMPLING_RATE_RATIO			(2)
-
-static unsigned int min_sampling_rate;
-
-#define LATENCY_MULTIPLIER			(1000)
-#define MIN_LATENCY_MULTIPLIER			(100)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
 #define MAX_SAMPLING_DOWN_FACTOR		(10)
-#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
-
-static void do_dbs_timer(struct work_struct *work);
-
-struct cpu_dbs_info_s {
-	cputime64_t prev_cpu_idle;
-	cputime64_t prev_cpu_wall;
-	cputime64_t prev_cpu_nice;
-	struct cpufreq_policy *cur_policy;
-	struct delayed_work work;
-	unsigned int down_skip;
-	unsigned int requested_freq;
-	int cpu;
-	unsigned int enable:1;
-	/*
-	 * percpu mutex that serializes governor limit change with
-	 * do_dbs_timer invocation. We do not want do_dbs_timer to run
-	 * when user is changing the governor or limits.
-	 */
-	struct mutex timer_mutex;
-};
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, cs_cpu_dbs_info);
 
-static unsigned int dbs_enable;	/* number of CPUs using this policy */
+static struct dbs_data cs_dbs_data;
+static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
 
-/*
- * dbs_mutex protects dbs_enable in governor start/stop.
- */
-static DEFINE_MUTEX(dbs_mutex);
-
-static struct dbs_tuners {
-	unsigned int sampling_rate;
-	unsigned int sampling_down_factor;
-	unsigned int up_threshold;
-	unsigned int down_threshold;
-	unsigned int ignore_nice;
-	unsigned int freq_step;
-} dbs_tuners_ins = {
+static struct cs_dbs_tuners cs_tuners = {
 	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
 	.down_threshold = DEF_FREQUENCY_DOWN_THRESHOLD,
 	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
@@ -95,95 +42,124 @@ static struct dbs_tuners {
 	.freq_step = 5,
 };
 
-static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
+/*
+ * Every sampling_rate, we check, if current idle time is less than 20%
+ * (default), then we try to increase frequency Every sampling_rate *
+ * sampling_down_factor, we check, if current idle time is more than 80%, then
+ * we try to decrease frequency
+ *
+ * Any frequency increase takes it to the maximum frequency. Frequency reduction
+ * happens at minimum steps of 5% (default) of maximum frequency
+ */
+static void cs_check_cpu(int cpu, unsigned int load)
 {
-	u64 idle_time;
-	u64 cur_wall_time;
-	u64 busy_time;
+	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
+	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+	unsigned int freq_target;
+
+	/*
+	 * break out if we 'cannot' reduce the speed as the user might
+	 * want freq_step to be zero
+	 */
+	if (cs_tuners.freq_step == 0)
+		return;
 
-	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+	/* Check for frequency increase */
+	if (load > cs_tuners.up_threshold) {
+		dbs_info->down_skip = 0;
 
-	busy_time  = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+		/* if we are already at full speed then break out early */
+		if (dbs_info->requested_freq == policy->max)
+			return;
 
-	idle_time = cur_wall_time - busy_time;
-	if (wall)
-		*wall = jiffies_to_usecs(cur_wall_time);
+		freq_target = (cs_tuners.freq_step * policy->max) / 100;
 
-	return jiffies_to_usecs(idle_time);
-}
+		/* max freq cannot be less than 100. But who knows.... */
+		if (unlikely(freq_target == 0))
+			freq_target = 5;
 
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
-{
-	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+		dbs_info->requested_freq += freq_target;
+		if (dbs_info->requested_freq > policy->max)
+			dbs_info->requested_freq = policy->max;
+
+		__cpufreq_driver_target(policy, dbs_info->requested_freq,
+			CPUFREQ_RELATION_H);
+		return;
+	}
+
+	/*
+	 * The optimal frequency is the frequency that is the lowest that can
+	 * support the current CPU usage without triggering the up policy. To be
+	 * safe, we focus 10 points under the threshold.
+	 */
+	if (load < (cs_tuners.down_threshold - 10)) {
+		freq_target = (cs_tuners.freq_step * policy->max) / 100;
 
-	if (idle_time == -1ULL)
-		return get_cpu_idle_time_jiffy(cpu, wall);
-	else
-		idle_time += get_cpu_iowait_time_us(cpu, wall);
+		dbs_info->requested_freq -= freq_target;
+		if (dbs_info->requested_freq < policy->min)
+			dbs_info->requested_freq = policy->min;
 
-	return idle_time;
+		/*
+		 * if we cannot reduce the frequency anymore, break out early
+		 */
+		if (policy->cur == policy->min)
+			return;
+
+		__cpufreq_driver_target(policy, dbs_info->requested_freq,
+				CPUFREQ_RELATION_H);
+		return;
+	}
 }
 
-/* keep track of frequency transitions */
-static int
-dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
-		     void *data)
+static void cs_dbs_timer(struct work_struct *work)
 {
-	struct cpufreq_freqs *freq = data;
-	struct cpu_dbs_info_s *this_dbs_info = &per_cpu(cs_cpu_dbs_info,
-							freq->cpu);
+	struct delayed_work *dw = to_delayed_work(work);
+	struct cs_cpu_dbs_info_s *dbs_info = container_of(work,
+			struct cs_cpu_dbs_info_s, cdbs.work.work);
+	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
+	struct cs_cpu_dbs_info_s *core_dbs_info = &per_cpu(cs_cpu_dbs_info,
+			cpu);
+	int delay = delay_for_sampling_rate(cs_tuners.sampling_rate);
+
+	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
+	if (need_load_eval(&core_dbs_info->cdbs, cs_tuners.sampling_rate))
+		dbs_check_cpu(&cs_dbs_data, cpu);
+
+	schedule_delayed_work_on(smp_processor_id(), dw, delay);
+	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
+}
 
+static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
+		void *data)
+{
+	struct cpufreq_freqs *freq = data;
+	struct cs_cpu_dbs_info_s *dbs_info =
+					&per_cpu(cs_cpu_dbs_info, freq->cpu);
 	struct cpufreq_policy *policy;
 
-	if (!this_dbs_info->enable)
+	if (!dbs_info->enable)
 		return 0;
 
-	policy = this_dbs_info->cur_policy;
+	policy = dbs_info->cdbs.cur_policy;
 
 	/*
-	 * we only care if our internally tracked freq moves outside
-	 * the 'valid' ranges of freqency available to us otherwise
-	 * we do not change it
+	 * we only care if our internally tracked freq moves outside the 'valid'
+	 * ranges of frequency available to us otherwise we do not change it
 	*/
-	if (this_dbs_info->requested_freq > policy->max
-			|| this_dbs_info->requested_freq < policy->min)
-		this_dbs_info->requested_freq = freq->new;
+	if (dbs_info->requested_freq > policy->max
+			|| dbs_info->requested_freq < policy->min)
+		dbs_info->requested_freq = freq->new;
 
 	return 0;
 }
 
-static struct notifier_block dbs_cpufreq_notifier_block = {
-	.notifier_call = dbs_cpufreq_notifier
-};
-
 /************************** sysfs interface ************************/
 static ssize_t show_sampling_rate_min(struct kobject *kobj,
 				      struct attribute *attr, char *buf)
 {
-	return sprintf(buf, "%u\n", min_sampling_rate);
+	return sprintf(buf, "%u\n", cs_dbs_data.min_sampling_rate);
 }
 
-define_one_global_ro(sampling_rate_min);
-
-/* cpufreq_conservative Governor Tunables */
-#define show_one(file_name, object)					\
-static ssize_t show_##file_name						\
-(struct kobject *kobj, struct attribute *attr, char *buf)		\
-{									\
-	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
-}
-show_one(sampling_rate, sampling_rate);
-show_one(sampling_down_factor, sampling_down_factor);
-show_one(up_threshold, up_threshold);
-show_one(down_threshold, down_threshold);
-show_one(ignore_nice_load, ignore_nice);
-show_one(freq_step, freq_step);
-
 static ssize_t store_sampling_down_factor(struct kobject *a,
 					  struct attribute *b,
 					  const char *buf, size_t count)
@@ -195,7 +171,7 @@ static ssize_t store_sampling_down_factor(struct kobject *a,
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
 
-	dbs_tuners_ins.sampling_down_factor = input;
+	cs_tuners.sampling_down_factor = input;
 	return count;
 }
 
@@ -209,7 +185,7 @@ static ssize_t store_sampling_rate(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
-	dbs_tuners_ins.sampling_rate = max(input, min_sampling_rate);
+	cs_tuners.sampling_rate = max(input, cs_dbs_data.min_sampling_rate);
 	return count;
 }
 
@@ -220,11 +196,10 @@ static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
 	int ret;
 	ret = sscanf(buf, "%u", &input);
 
-	if (ret != 1 || input > 100 ||
-			input <= dbs_tuners_ins.down_threshold)
+	if (ret != 1 || input > 100 || input <= cs_tuners.down_threshold)
 		return -EINVAL;
 
-	dbs_tuners_ins.up_threshold = input;
+	cs_tuners.up_threshold = input;
 	return count;
 }
 
@@ -237,21 +212,19 @@ static ssize_t store_down_threshold(struct kobject *a, struct attribute *b,
 
 	/* cannot be lower than 11 otherwise freq will not fall */
 	if (ret != 1 || input < 11 || input > 100 ||
-			input >= dbs_tuners_ins.up_threshold)
+			input >= cs_tuners.up_threshold)
 		return -EINVAL;
 
-	dbs_tuners_ins.down_threshold = input;
+	cs_tuners.down_threshold = input;
 	return count;
 }
 
 static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 				      const char *buf, size_t count)
 {
-	unsigned int input;
+	unsigned int input, j;
 	int ret;
 
-	unsigned int j;
-
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
@@ -259,19 +232,20 @@ static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 	if (input > 1)
 		input = 1;
 
-	if (input == dbs_tuners_ins.ignore_nice) /* nothing to do */
+	if (input == cs_tuners.ignore_nice) /* nothing to do */
 		return count;
 
-	dbs_tuners_ins.ignore_nice = input;
+	cs_tuners.ignore_nice = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
-		struct cpu_dbs_info_s *dbs_info;
+		struct cs_cpu_dbs_info_s *dbs_info;
 		dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&dbs_info->prev_cpu_wall);
-		if (dbs_tuners_ins.ignore_nice)
-			dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
+						&dbs_info->cdbs.prev_cpu_wall);
+		if (cs_tuners.ignore_nice)
+			dbs_info->cdbs.prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 	}
 	return count;
 }
@@ -289,18 +263,28 @@ static ssize_t store_freq_step(struct kobject *a, struct attribute *b,
 	if (input > 100)
 		input = 100;
 
-	/* no need to test here if freq_step is zero as the user might actually
-	 * want this, they would be crazy though :) */
-	dbs_tuners_ins.freq_step = input;
+	/*
+	 * no need to test here if freq_step is zero as the user might actually
+	 * want this, they would be crazy though :)
+	 */
+	cs_tuners.freq_step = input;
 	return count;
 }
 
+show_one(cs, sampling_rate, sampling_rate);
+show_one(cs, sampling_down_factor, sampling_down_factor);
+show_one(cs, up_threshold, up_threshold);
+show_one(cs, down_threshold, down_threshold);
+show_one(cs, ignore_nice_load, ignore_nice);
+show_one(cs, freq_step, freq_step);
+
 define_one_global_rw(sampling_rate);
 define_one_global_rw(sampling_down_factor);
 define_one_global_rw(up_threshold);
 define_one_global_rw(down_threshold);
 define_one_global_rw(ignore_nice_load);
 define_one_global_rw(freq_step);
+define_one_global_ro(sampling_rate_min);
 
 static struct attribute *dbs_attributes[] = {
 	&sampling_rate_min.attr,
@@ -313,283 +297,38 @@ static struct attribute *dbs_attributes[] = {
 	NULL
 };
 
-static struct attribute_group dbs_attr_group = {
+static struct attribute_group cs_attr_group = {
 	.attrs = dbs_attributes,
 	.name = "conservative",
 };
 
 /************************** sysfs end ************************/
 
-static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
-{
-	unsigned int load = 0;
-	unsigned int max_load = 0;
-	unsigned int freq_target;
+define_get_cpu_dbs_routines(cs_cpu_dbs_info);
 
-	struct cpufreq_policy *policy;
-	unsigned int j;
-
-	policy = this_dbs_info->cur_policy;
-
-	/*
-	 * Every sampling_rate, we check, if current idle time is less
-	 * than 20% (default), then we try to increase frequency
-	 * Every sampling_rate*sampling_down_factor, we check, if current
-	 * idle time is more than 80%, then we try to decrease frequency
-	 *
-	 * Any frequency increase takes it to the maximum frequency.
-	 * Frequency reduction happens at minimum steps of
-	 * 5% (default) of maximum frequency
-	 */
-
-	/* Get Absolute Load */
-	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info_s *j_dbs_info;
-		cputime64_t cur_wall_time, cur_idle_time;
-		unsigned int idle_time, wall_time;
-
-		j_dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-
-		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
-
-		wall_time = (unsigned int)
-			(cur_wall_time - j_dbs_info->prev_cpu_wall);
-		j_dbs_info->prev_cpu_wall = cur_wall_time;
-
-		idle_time = (unsigned int)
-			(cur_idle_time - j_dbs_info->prev_cpu_idle);
-		j_dbs_info->prev_cpu_idle = cur_idle_time;
-
-		if (dbs_tuners_ins.ignore_nice) {
-			u64 cur_nice;
-			unsigned long cur_nice_jiffies;
-
-			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
-					 j_dbs_info->prev_cpu_nice;
-			/*
-			 * Assumption: nice time between sampling periods will
-			 * be less than 2^32 jiffies for 32 bit sys
-			 */
-			cur_nice_jiffies = (unsigned long)
-					cputime64_to_jiffies64(cur_nice);
-
-			j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-			idle_time += jiffies_to_usecs(cur_nice_jiffies);
-		}
-
-		if (unlikely(!wall_time || wall_time < idle_time))
-			continue;
-
-		load = 100 * (wall_time - idle_time) / wall_time;
-
-		if (load > max_load)
-			max_load = load;
-	}
-
-	/*
-	 * break out if we 'cannot' reduce the speed as the user might
-	 * want freq_step to be zero
-	 */
-	if (dbs_tuners_ins.freq_step == 0)
-		return;
-
-	/* Check for frequency increase */
-	if (max_load > dbs_tuners_ins.up_threshold) {
-		this_dbs_info->down_skip = 0;
-
-		/* if we are already at full speed then break out early */
-		if (this_dbs_info->requested_freq == policy->max)
-			return;
-
-		freq_target = (dbs_tuners_ins.freq_step * policy->max) / 100;
-
-		/* max freq cannot be less than 100. But who knows.... */
-		if (unlikely(freq_target == 0))
-			freq_target = 5;
-
-		this_dbs_info->requested_freq += freq_target;
-		if (this_dbs_info->requested_freq > policy->max)
-			this_dbs_info->requested_freq = policy->max;
-
-		__cpufreq_driver_target(policy, this_dbs_info->requested_freq,
-			CPUFREQ_RELATION_H);
-		return;
-	}
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that
-	 * can support the current CPU usage without triggering the up
-	 * policy. To be safe, we focus 10 points under the threshold.
-	 */
-	if (max_load < (dbs_tuners_ins.down_threshold - 10)) {
-		freq_target = (dbs_tuners_ins.freq_step * policy->max) / 100;
-
-		this_dbs_info->requested_freq -= freq_target;
-		if (this_dbs_info->requested_freq < policy->min)
-			this_dbs_info->requested_freq = policy->min;
-
-		/*
-		 * if we cannot reduce the frequency anymore, break out early
-		 */
-		if (policy->cur == policy->min)
-			return;
-
-		__cpufreq_driver_target(policy, this_dbs_info->requested_freq,
-				CPUFREQ_RELATION_H);
-		return;
-	}
-}
-
-static void do_dbs_timer(struct work_struct *work)
-{
-	struct cpu_dbs_info_s *dbs_info =
-		container_of(work, struct cpu_dbs_info_s, work.work);
-	unsigned int cpu = dbs_info->cpu;
-
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-
-	delay -= jiffies % delay;
-
-	mutex_lock(&dbs_info->timer_mutex);
-
-	dbs_check_cpu(dbs_info);
-
-	schedule_delayed_work_on(cpu, &dbs_info->work, delay);
-	mutex_unlock(&dbs_info->timer_mutex);
-}
-
-static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
-{
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-	delay -= jiffies % delay;
+static struct notifier_block cs_cpufreq_notifier_block = {
+	.notifier_call = dbs_cpufreq_notifier,
+};
 
-	dbs_info->enable = 1;
-	INIT_DEFERRABLE_WORK(&dbs_info->work, do_dbs_timer);
-	schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work, delay);
-}
+static struct cs_ops cs_ops = {
+	.notifier_block = &cs_cpufreq_notifier_block,
+};
 
-static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
-{
-	dbs_info->enable = 0;
-	cancel_delayed_work_sync(&dbs_info->work);
-}
+static struct dbs_data cs_dbs_data = {
+	.governor = GOV_CONSERVATIVE,
+	.attr_group = &cs_attr_group,
+	.tuners = &cs_tuners,
+	.get_cpu_cdbs = get_cpu_cdbs,
+	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+	.gov_dbs_timer = cs_dbs_timer,
+	.gov_check_cpu = cs_check_cpu,
+	.gov_ops = &cs_ops,
+};
 
-static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
 				   unsigned int event)
 {
-	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_info_s *this_dbs_info;
-	unsigned int j;
-	int rc;
-
-	this_dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if ((!cpu_online(cpu)) || (!policy->cur))
-			return -EINVAL;
-
-		mutex_lock(&dbs_mutex);
-
-		for_each_cpu(j, policy->cpus) {
-			struct cpu_dbs_info_s *j_dbs_info;
-			j_dbs_info = &per_cpu(cs_cpu_dbs_info, j);
-			j_dbs_info->cur_policy = policy;
-
-			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&j_dbs_info->prev_cpu_wall);
-			if (dbs_tuners_ins.ignore_nice)
-				j_dbs_info->prev_cpu_nice =
-						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-		}
-		this_dbs_info->cpu = cpu;
-		this_dbs_info->down_skip = 0;
-		this_dbs_info->requested_freq = policy->cur;
-
-		mutex_init(&this_dbs_info->timer_mutex);
-		dbs_enable++;
-		/*
-		 * Start the timerschedule work, when this governor
-		 * is used for first time
-		 */
-		if (dbs_enable == 1) {
-			unsigned int latency;
-			/* policy latency is in nS. Convert it to uS first */
-			latency = policy->cpuinfo.transition_latency / 1000;
-			if (latency == 0)
-				latency = 1;
-
-			rc = sysfs_create_group(cpufreq_global_kobject,
-						&dbs_attr_group);
-			if (rc) {
-				mutex_unlock(&dbs_mutex);
-				return rc;
-			}
-
-			/*
-			 * conservative does not implement micro like ondemand
-			 * governor, thus we are bound to jiffes/HZ
-			 */
-			min_sampling_rate =
-				MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10);
-			/* Bring kernel and HW constraints together */
-			min_sampling_rate = max(min_sampling_rate,
-					MIN_LATENCY_MULTIPLIER * latency);
-			dbs_tuners_ins.sampling_rate =
-				max(min_sampling_rate,
-				    latency * LATENCY_MULTIPLIER);
-
-			cpufreq_register_notifier(
-					&dbs_cpufreq_notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
-		}
-		mutex_unlock(&dbs_mutex);
-
-		dbs_timer_init(this_dbs_info);
-
-		break;
-
-	case CPUFREQ_GOV_STOP:
-		dbs_timer_exit(this_dbs_info);
-
-		mutex_lock(&dbs_mutex);
-		dbs_enable--;
-		mutex_destroy(&this_dbs_info->timer_mutex);
-
-		/*
-		 * Stop the timerschedule work, when this governor
-		 * is used for first time
-		 */
-		if (dbs_enable == 0)
-			cpufreq_unregister_notifier(
-					&dbs_cpufreq_notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
-
-		mutex_unlock(&dbs_mutex);
-		if (!dbs_enable)
-			sysfs_remove_group(cpufreq_global_kobject,
-					   &dbs_attr_group);
-
-		break;
-
-	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&this_dbs_info->timer_mutex);
-		if (policy->max < this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(
-					this_dbs_info->cur_policy,
-					policy->max, CPUFREQ_RELATION_H);
-		else if (policy->min > this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(
-					this_dbs_info->cur_policy,
-					policy->min, CPUFREQ_RELATION_L);
-		dbs_check_cpu(this_dbs_info);
-		mutex_unlock(&this_dbs_info->timer_mutex);
-
-		break;
-	}
-	return 0;
+	return cpufreq_governor_dbs(&cs_dbs_data, policy, event);
 }
 
 #ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
@@ -597,13 +336,14 @@ static
 #endif
 struct cpufreq_governor cpufreq_gov_conservative = {
 	.name			= "conservative",
-	.governor		= cpufreq_governor_dbs,
+	.governor		= cs_cpufreq_governor_dbs,
 	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
 	.owner			= THIS_MODULE,
 };
 
 static int __init cpufreq_gov_dbs_init(void)
 {
+	mutex_init(&cs_dbs_data.mutex);
 	return cpufreq_register_governor(&cpufreq_gov_conservative);
 }
 
@@ -612,7 +352,6 @@ static void __exit cpufreq_gov_dbs_exit(void)
 	cpufreq_unregister_governor(&cpufreq_gov_conservative);
 }
 
-
 MODULE_AUTHOR("Alexander Clouter <alex@digriz.org.uk>");
 MODULE_DESCRIPTION("'cpufreq_conservative' - A dynamic cpufreq governor for "
 		"Low Latency Frequency Transition capable processors "
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
new file mode 100644
index 000000000000..5a76086ff09b
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -0,0 +1,343 @@
+/*
+ * drivers/cpufreq/cpufreq_governor.c
+ *
+ * CPUFREQ governors common code
+ *
+ * Copyright	(C) 2001 Russell King
+ *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
+ *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
+ *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <asm/cputime.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/export.h>
+#include <linux/kernel_stat.h>
+#include <linux/mutex.h>
+#include <linux/tick.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+
+#include "cpufreq_governor.h"
+
+static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
+{
+	u64 idle_time;
+	u64 cur_wall_time;
+	u64 busy_time;
+
+	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
+
+	busy_time = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
+	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
+
+	idle_time = cur_wall_time - busy_time;
+	if (wall)
+		*wall = cputime_to_usecs(cur_wall_time);
+
+	return cputime_to_usecs(idle_time);
+}
+
+u64 get_cpu_idle_time(unsigned int cpu, u64 *wall)
+{
+	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+
+	if (idle_time == -1ULL)
+		return get_cpu_idle_time_jiffy(cpu, wall);
+	else
+		idle_time += get_cpu_iowait_time_us(cpu, wall);
+
+	return idle_time;
+}
+EXPORT_SYMBOL_GPL(get_cpu_idle_time);
+
+void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
+{
+	struct cpu_dbs_common_info *cdbs = dbs_data->get_cpu_cdbs(cpu);
+	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	struct cpufreq_policy *policy;
+	unsigned int max_load = 0;
+	unsigned int ignore_nice;
+	unsigned int j;
+
+	if (dbs_data->governor == GOV_ONDEMAND)
+		ignore_nice = od_tuners->ignore_nice;
+	else
+		ignore_nice = cs_tuners->ignore_nice;
+
+	policy = cdbs->cur_policy;
+
+	/* Get Absolute Load (in terms of freq for ondemand gov) */
+	for_each_cpu(j, policy->cpus) {
+		struct cpu_dbs_common_info *j_cdbs;
+		u64 cur_wall_time, cur_idle_time, cur_iowait_time;
+		unsigned int idle_time, wall_time, iowait_time;
+		unsigned int load;
+
+		j_cdbs = dbs_data->get_cpu_cdbs(j);
+
+		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
+
+		wall_time = (unsigned int)
+			(cur_wall_time - j_cdbs->prev_cpu_wall);
+		j_cdbs->prev_cpu_wall = cur_wall_time;
+
+		idle_time = (unsigned int)
+			(cur_idle_time - j_cdbs->prev_cpu_idle);
+		j_cdbs->prev_cpu_idle = cur_idle_time;
+
+		if (ignore_nice) {
+			u64 cur_nice;
+			unsigned long cur_nice_jiffies;
+
+			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
+					 cdbs->prev_cpu_nice;
+			/*
+			 * Assumption: nice time between sampling periods will
+			 * be less than 2^32 jiffies for 32 bit sys
+			 */
+			cur_nice_jiffies = (unsigned long)
+					cputime64_to_jiffies64(cur_nice);
+
+			cdbs->prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+			idle_time += jiffies_to_usecs(cur_nice_jiffies);
+		}
+
+		if (dbs_data->governor == GOV_ONDEMAND) {
+			struct od_cpu_dbs_info_s *od_j_dbs_info =
+				dbs_data->get_cpu_dbs_info_s(cpu);
+
+			cur_iowait_time = get_cpu_iowait_time_us(j,
+					&cur_wall_time);
+			if (cur_iowait_time == -1ULL)
+				cur_iowait_time = 0;
+
+			iowait_time = (unsigned int) (cur_iowait_time -
+					od_j_dbs_info->prev_cpu_iowait);
+			od_j_dbs_info->prev_cpu_iowait = cur_iowait_time;
+
+			/*
+			 * For the purpose of ondemand, waiting for disk IO is
+			 * an indication that you're performance critical, and
+			 * not that the system is actually idle. So subtract the
+			 * iowait time from the cpu idle time.
+			 */
+			if (od_tuners->io_is_busy && idle_time >= iowait_time)
+				idle_time -= iowait_time;
+		}
+
+		if (unlikely(!wall_time || wall_time < idle_time))
+			continue;
+
+		load = 100 * (wall_time - idle_time) / wall_time;
+
+		if (dbs_data->governor == GOV_ONDEMAND) {
+			int freq_avg = __cpufreq_driver_getavg(policy, j);
+			if (freq_avg <= 0)
+				freq_avg = policy->cur;
+
+			load *= freq_avg;
+		}
+
+		if (load > max_load)
+			max_load = load;
+	}
+
+	dbs_data->gov_check_cpu(cpu, max_load);
+}
+EXPORT_SYMBOL_GPL(dbs_check_cpu);
+
+static inline void dbs_timer_init(struct dbs_data *dbs_data, int cpu,
+				  unsigned int sampling_rate)
+{
+	int delay = delay_for_sampling_rate(sampling_rate);
+	struct cpu_dbs_common_info *cdbs = dbs_data->get_cpu_cdbs(cpu);
+
+	schedule_delayed_work_on(cpu, &cdbs->work, delay);
+}
+
+static inline void dbs_timer_exit(struct dbs_data *dbs_data, int cpu)
+{
+	struct cpu_dbs_common_info *cdbs = dbs_data->get_cpu_cdbs(cpu);
+
+	cancel_delayed_work_sync(&cdbs->work);
+}
+
+/* Will return if we need to evaluate cpu load again or not */
+bool need_load_eval(struct cpu_dbs_common_info *cdbs,
+		unsigned int sampling_rate)
+{
+	if (policy_is_shared(cdbs->cur_policy)) {
+		ktime_t time_now = ktime_get();
+		s64 delta_us = ktime_us_delta(time_now, cdbs->time_stamp);
+
+		/* Do nothing if we recently have sampled */
+		if (delta_us < (s64)(sampling_rate / 2))
+			return false;
+		else
+			cdbs->time_stamp = time_now;
+	}
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(need_load_eval);
+
+int cpufreq_governor_dbs(struct dbs_data *dbs_data,
+		struct cpufreq_policy *policy, unsigned int event)
+{
+	struct od_cpu_dbs_info_s *od_dbs_info = NULL;
+	struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
+	struct cs_ops *cs_ops = NULL;
+	struct od_ops *od_ops = NULL;
+	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+	struct cpu_dbs_common_info *cpu_cdbs;
+	unsigned int *sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
+	int rc;
+
+	cpu_cdbs = dbs_data->get_cpu_cdbs(cpu);
+
+	if (dbs_data->governor == GOV_CONSERVATIVE) {
+		cs_dbs_info = dbs_data->get_cpu_dbs_info_s(cpu);
+		sampling_rate = &cs_tuners->sampling_rate;
+		ignore_nice = cs_tuners->ignore_nice;
+		cs_ops = dbs_data->gov_ops;
+	} else {
+		od_dbs_info = dbs_data->get_cpu_dbs_info_s(cpu);
+		sampling_rate = &od_tuners->sampling_rate;
+		ignore_nice = od_tuners->ignore_nice;
+		od_ops = dbs_data->gov_ops;
+	}
+
+	switch (event) {
+	case CPUFREQ_GOV_START:
+		if (!policy->cur)
+			return -EINVAL;
+
+		mutex_lock(&dbs_data->mutex);
+
+		for_each_cpu(j, policy->cpus) {
+			struct cpu_dbs_common_info *j_cdbs =
+				dbs_data->get_cpu_cdbs(j);
+
+			j_cdbs->cpu = j;
+			j_cdbs->cur_policy = policy;
+			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
+					&j_cdbs->prev_cpu_wall);
+			if (ignore_nice)
+				j_cdbs->prev_cpu_nice =
+					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+
+			mutex_init(&j_cdbs->timer_mutex);
+			INIT_DEFERRABLE_WORK(&j_cdbs->work,
+					     dbs_data->gov_dbs_timer);
+		}
+
+		if (!policy->governor->initialized) {
+			rc = sysfs_create_group(cpufreq_global_kobject,
+					dbs_data->attr_group);
+			if (rc) {
+				mutex_unlock(&dbs_data->mutex);
+				return rc;
+			}
+		}
+
+		/*
+		 * conservative does not implement micro like ondemand
+		 * governor, thus we are bound to jiffes/HZ
+		 */
+		if (dbs_data->governor == GOV_CONSERVATIVE) {
+			cs_dbs_info->down_skip = 0;
+			cs_dbs_info->enable = 1;
+			cs_dbs_info->requested_freq = policy->cur;
+
+			if (!policy->governor->initialized) {
+				cpufreq_register_notifier(cs_ops->notifier_block,
+						CPUFREQ_TRANSITION_NOTIFIER);
+
+				dbs_data->min_sampling_rate =
+					MIN_SAMPLING_RATE_RATIO *
+					jiffies_to_usecs(10);
+			}
+		} else {
+			od_dbs_info->rate_mult = 1;
+			od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+			od_ops->powersave_bias_init_cpu(cpu);
+
+			if (!policy->governor->initialized)
+				od_tuners->io_is_busy = od_ops->io_busy();
+		}
+
+		if (policy->governor->initialized)
+			goto unlock;
+
+		/* policy latency is in nS. Convert it to uS first */
+		latency = policy->cpuinfo.transition_latency / 1000;
+		if (latency == 0)
+			latency = 1;
+
+		/* Bring kernel and HW constraints together */
+		dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
+				MIN_LATENCY_MULTIPLIER * latency);
+		*sampling_rate = max(dbs_data->min_sampling_rate, latency *
+				LATENCY_MULTIPLIER);
+unlock:
+		mutex_unlock(&dbs_data->mutex);
+
+		/* Initiate timer time stamp */
+		cpu_cdbs->time_stamp = ktime_get();
+
+		for_each_cpu(j, policy->cpus)
+			dbs_timer_init(dbs_data, j, *sampling_rate);
+		break;
+
+	case CPUFREQ_GOV_STOP:
+		if (dbs_data->governor == GOV_CONSERVATIVE)
+			cs_dbs_info->enable = 0;
+
+		for_each_cpu(j, policy->cpus)
+			dbs_timer_exit(dbs_data, j);
+
+		mutex_lock(&dbs_data->mutex);
+		mutex_destroy(&cpu_cdbs->timer_mutex);
+
+		if (policy->governor->initialized == 1) {
+			sysfs_remove_group(cpufreq_global_kobject,
+					dbs_data->attr_group);
+			if (dbs_data->governor == GOV_CONSERVATIVE)
+				cpufreq_unregister_notifier(cs_ops->notifier_block,
+						CPUFREQ_TRANSITION_NOTIFIER);
+		}
+		mutex_unlock(&dbs_data->mutex);
+
+		break;
+
+	case CPUFREQ_GOV_LIMITS:
+		mutex_lock(&cpu_cdbs->timer_mutex);
+		if (policy->max < cpu_cdbs->cur_policy->cur)
+			__cpufreq_driver_target(cpu_cdbs->cur_policy,
+					policy->max, CPUFREQ_RELATION_H);
+		else if (policy->min > cpu_cdbs->cur_policy->cur)
+			__cpufreq_driver_target(cpu_cdbs->cur_policy,
+					policy->min, CPUFREQ_RELATION_L);
+		dbs_check_cpu(dbs_data, cpu);
+		mutex_unlock(&cpu_cdbs->timer_mutex);
+		break;
+	}
+	return 0;
+}
+EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
diff --git a/drivers/cpufreq/cpufreq_governor.h b/drivers/cpufreq/cpufreq_governor.h
new file mode 100644
index 000000000000..46bde01eee62
--- /dev/null
+++ b/drivers/cpufreq/cpufreq_governor.h
@@ -0,0 +1,178 @@
+/*
+ * drivers/cpufreq/cpufreq_governor.h
+ *
+ * Header file for CPUFreq governors common code
+ *
+ * Copyright	(C) 2001 Russell King
+ *		(C) 2003 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>.
+ *		(C) 2003 Jun Nakajima <jun.nakajima@intel.com>
+ *		(C) 2009 Alexander Clouter <alex@digriz.org.uk>
+ *		(c) 2012 Viresh Kumar <viresh.kumar@linaro.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef _CPUFREQ_GOVERNER_H
+#define _CPUFREQ_GOVERNER_H
+
+#include <linux/cpufreq.h>
+#include <linux/kobject.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/sysfs.h>
+
+/*
+ * The polling frequency depends on the capability of the processor. Default
+ * polling frequency is 1000 times the transition latency of the processor. The
+ * governor will work on any processor with transition latency <= 10mS, using
+ * appropriate sampling rate.
+ *
+ * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
+ * this governor will not work. All times here are in uS.
+ */
+#define MIN_SAMPLING_RATE_RATIO			(2)
+#define LATENCY_MULTIPLIER			(1000)
+#define MIN_LATENCY_MULTIPLIER			(100)
+#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
+
+/* Ondemand Sampling types */
+enum {OD_NORMAL_SAMPLE, OD_SUB_SAMPLE};
+
+/* Macro creating sysfs show routines */
+#define show_one(_gov, file_name, object)				\
+static ssize_t show_##file_name						\
+(struct kobject *kobj, struct attribute *attr, char *buf)		\
+{									\
+	return sprintf(buf, "%u\n", _gov##_tuners.object);		\
+}
+
+#define define_get_cpu_dbs_routines(_dbs_info)				\
+static struct cpu_dbs_common_info *get_cpu_cdbs(int cpu)		\
+{									\
+	return &per_cpu(_dbs_info, cpu).cdbs;				\
+}									\
+									\
+static void *get_cpu_dbs_info_s(int cpu)				\
+{									\
+	return &per_cpu(_dbs_info, cpu);				\
+}
+
+/*
+ * Abbreviations:
+ * dbs: used as a shortform for demand based switching It helps to keep variable
+ *	names smaller, simpler
+ * cdbs: common dbs
+ * od_*: On-demand governor
+ * cs_*: Conservative governor
+ */
+
+/* Per cpu structures */
+struct cpu_dbs_common_info {
+	int cpu;
+	u64 prev_cpu_idle;
+	u64 prev_cpu_wall;
+	u64 prev_cpu_nice;
+	struct cpufreq_policy *cur_policy;
+	struct delayed_work work;
+	/*
+	 * percpu mutex that serializes governor limit change with gov_dbs_timer
+	 * invocation. We do not want gov_dbs_timer to run when user is changing
+	 * the governor or limits.
+	 */
+	struct mutex timer_mutex;
+	ktime_t time_stamp;
+};
+
+struct od_cpu_dbs_info_s {
+	struct cpu_dbs_common_info cdbs;
+	u64 prev_cpu_iowait;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int freq_lo;
+	unsigned int freq_lo_jiffies;
+	unsigned int freq_hi_jiffies;
+	unsigned int rate_mult;
+	unsigned int sample_type:1;
+};
+
+struct cs_cpu_dbs_info_s {
+	struct cpu_dbs_common_info cdbs;
+	unsigned int down_skip;
+	unsigned int requested_freq;
+	unsigned int enable:1;
+};
+
+/* Governers sysfs tunables */
+struct od_dbs_tuners {
+	unsigned int ignore_nice;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int adj_up_threshold;
+	unsigned int powersave_bias;
+	unsigned int io_is_busy;
+};
+
+struct cs_dbs_tuners {
+	unsigned int ignore_nice;
+	unsigned int sampling_rate;
+	unsigned int sampling_down_factor;
+	unsigned int up_threshold;
+	unsigned int down_threshold;
+	unsigned int freq_step;
+};
+
+/* Per Governer data */
+struct dbs_data {
+	/* Common across governors */
+	#define GOV_ONDEMAND		0
+	#define GOV_CONSERVATIVE	1
+	int governor;
+	unsigned int min_sampling_rate;
+	struct attribute_group *attr_group;
+	void *tuners;
+
+	/* dbs_mutex protects dbs_enable in governor start/stop */
+	struct mutex mutex;
+
+	struct cpu_dbs_common_info *(*get_cpu_cdbs)(int cpu);
+	void *(*get_cpu_dbs_info_s)(int cpu);
+	void (*gov_dbs_timer)(struct work_struct *work);
+	void (*gov_check_cpu)(int cpu, unsigned int load);
+
+	/* Governor specific ops, see below */
+	void *gov_ops;
+};
+
+/* Governor specific ops, will be passed to dbs_data->gov_ops */
+struct od_ops {
+	int (*io_busy)(void);
+	void (*powersave_bias_init_cpu)(int cpu);
+	unsigned int (*powersave_bias_target)(struct cpufreq_policy *policy,
+			unsigned int freq_next, unsigned int relation);
+	void (*freq_increase)(struct cpufreq_policy *p, unsigned int freq);
+};
+
+struct cs_ops {
+	struct notifier_block *notifier_block;
+};
+
+static inline int delay_for_sampling_rate(unsigned int sampling_rate)
+{
+	int delay = usecs_to_jiffies(sampling_rate);
+
+	/* We want all CPUs to do sampling nearly on same jiffy */
+	if (num_online_cpus() > 1)
+		delay -= jiffies % delay;
+
+	return delay;
+}
+
+u64 get_cpu_idle_time(unsigned int cpu, u64 *wall);
+void dbs_check_cpu(struct dbs_data *dbs_data, int cpu);
+bool need_load_eval(struct cpu_dbs_common_info *cdbs,
+		unsigned int sampling_rate);
+int cpufreq_governor_dbs(struct dbs_data *dbs_data,
+		struct cpufreq_policy *policy, unsigned int event);
+#endif /* _CPUFREQ_GOVERNER_H */
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index 396322f2a83f..f3eb26cd848f 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -10,24 +10,23 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/init.h>
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/cpufreq.h>
-#include <linux/cpu.h>
-#include <linux/jiffies.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
 #include <linux/kernel_stat.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
-#include <linux/hrtimer.h>
+#include <linux/percpu-defs.h>
+#include <linux/sysfs.h>
 #include <linux/tick.h>
-#include <linux/ktime.h>
-#include <linux/sched.h>
+#include <linux/types.h>
 
-/*
- * dbs is used in this file as a shortform for demandbased switching
- * It helps to keep variable names smaller, simpler
- */
+#include "cpufreq_governor.h"
 
+/* On-demand governor macros */
 #define DEF_FREQUENCY_DOWN_DIFFERENTIAL		(10)
 #define DEF_FREQUENCY_UP_THRESHOLD		(80)
 #define DEF_SAMPLING_DOWN_FACTOR		(1)
@@ -38,129 +37,51 @@
 #define MIN_FREQUENCY_UP_THRESHOLD		(11)
 #define MAX_FREQUENCY_UP_THRESHOLD		(100)
 
-/*
- * The polling frequency of this governor depends on the capability of
- * the processor. Default polling frequency is 1000 times the transition
- * latency of the processor. The governor will work on any processor with
- * transition latency <= 10mS, using appropriate sampling
- * rate.
- * For CPUs with transition latency > 10mS (mostly drivers with CPUFREQ_ETERNAL)
- * this governor will not work.
- * All times here are in uS.
- */
-#define MIN_SAMPLING_RATE_RATIO			(2)
-
-static unsigned int min_sampling_rate;
-
-#define LATENCY_MULTIPLIER			(1000)
-#define MIN_LATENCY_MULTIPLIER			(100)
-#define TRANSITION_LATENCY_LIMIT		(10 * 1000 * 1000)
-
-static void do_dbs_timer(struct work_struct *work);
-static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				unsigned int event);
+static struct dbs_data od_dbs_data;
+static DEFINE_PER_CPU(struct od_cpu_dbs_info_s, od_cpu_dbs_info);
 
 #ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
-static
+static struct cpufreq_governor cpufreq_gov_ondemand;
 #endif
-struct cpufreq_governor cpufreq_gov_ondemand = {
-       .name                   = "ondemand",
-       .governor               = cpufreq_governor_dbs,
-       .max_transition_latency = TRANSITION_LATENCY_LIMIT,
-       .owner                  = THIS_MODULE,
-};
-
-/* Sampling types */
-enum {DBS_NORMAL_SAMPLE, DBS_SUB_SAMPLE};
-
-struct cpu_dbs_info_s {
-	cputime64_t prev_cpu_idle;
-	cputime64_t prev_cpu_iowait;
-	cputime64_t prev_cpu_wall;
-	cputime64_t prev_cpu_nice;
-	struct cpufreq_policy *cur_policy;
-	struct delayed_work work;
-	struct cpufreq_frequency_table *freq_table;
-	unsigned int freq_lo;
-	unsigned int freq_lo_jiffies;
-	unsigned int freq_hi_jiffies;
-	unsigned int rate_mult;
-	int cpu;
-	unsigned int sample_type:1;
-	/*
-	 * percpu mutex that serializes governor limit change with
-	 * do_dbs_timer invocation. We do not want do_dbs_timer to run
-	 * when user is changing the governor or limits.
-	 */
-	struct mutex timer_mutex;
-};
-static DEFINE_PER_CPU(struct cpu_dbs_info_s, od_cpu_dbs_info);
 
-static unsigned int dbs_enable;	/* number of CPUs using this policy */
-
-/*
- * dbs_mutex protects dbs_enable in governor start/stop.
- */
-static DEFINE_MUTEX(dbs_mutex);
-
-static struct dbs_tuners {
-	unsigned int sampling_rate;
-	unsigned int up_threshold;
-	unsigned int down_differential;
-	unsigned int ignore_nice;
-	unsigned int sampling_down_factor;
-	unsigned int powersave_bias;
-	unsigned int io_is_busy;
-} dbs_tuners_ins = {
+static struct od_dbs_tuners od_tuners = {
 	.up_threshold = DEF_FREQUENCY_UP_THRESHOLD,
 	.sampling_down_factor = DEF_SAMPLING_DOWN_FACTOR,
-	.down_differential = DEF_FREQUENCY_DOWN_DIFFERENTIAL,
+	.adj_up_threshold = DEF_FREQUENCY_UP_THRESHOLD -
+			    DEF_FREQUENCY_DOWN_DIFFERENTIAL,
 	.ignore_nice = 0,
 	.powersave_bias = 0,
 };
 
-static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
-{
-	u64 idle_time;
-	u64 cur_wall_time;
-	u64 busy_time;
-
-	cur_wall_time = jiffies64_to_cputime64(get_jiffies_64());
-
-	busy_time  = kcpustat_cpu(cpu).cpustat[CPUTIME_USER];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL];
-	busy_time += kcpustat_cpu(cpu).cpustat[CPUTIME_NICE];
-
-	idle_time = cur_wall_time - busy_time;
-	if (wall)
-		*wall = jiffies_to_usecs(cur_wall_time);
-
-	return jiffies_to_usecs(idle_time);
-}
-
-static inline cputime64_t get_cpu_idle_time(unsigned int cpu, cputime64_t *wall)
+static void ondemand_powersave_bias_init_cpu(int cpu)
 {
-	u64 idle_time = get_cpu_idle_time_us(cpu, NULL);
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 
-	if (idle_time == -1ULL)
-		return get_cpu_idle_time_jiffy(cpu, wall);
-	else
-		idle_time += get_cpu_iowait_time_us(cpu, wall);
-
-	return idle_time;
+	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
+	dbs_info->freq_lo = 0;
 }
 
-static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wall)
+/*
+ * Not all CPUs want IO time to be accounted as busy; this depends on how
+ * efficient idling at a higher frequency/voltage is.
+ * Pavel Machek says this is not so for various generations of AMD and old
+ * Intel systems.
+ * Mike Chan (android.com) claims this is also not true for ARM.
+ * Because of this, whitelist specific known (series) of CPUs by default, and
+ * leave all others up to the user.
+ */
+static int should_io_be_busy(void)
 {
-	u64 iowait_time = get_cpu_iowait_time_us(cpu, wall);
-
-	if (iowait_time == -1ULL)
-		return 0;
-
-	return iowait_time;
+#if defined(CONFIG_X86)
+	/*
+	 * For Intel, Core 2 (model 15) and later have an efficient idle.
+	 */
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
+			boot_cpu_data.x86 == 6 &&
+			boot_cpu_data.x86_model >= 15)
+		return 1;
+#endif
+	return 0;
 }
 
 /*
@@ -169,14 +90,13 @@ static inline cputime64_t get_cpu_iowait_time(unsigned int cpu, cputime64_t *wal
  * freq_lo, and freq_lo_jiffies in percpu area for averaging freqs.
  */
 static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
-					  unsigned int freq_next,
-					  unsigned int relation)
+		unsigned int freq_next, unsigned int relation)
 {
 	unsigned int freq_req, freq_reduc, freq_avg;
 	unsigned int freq_hi, freq_lo;
 	unsigned int index = 0;
 	unsigned int jiffies_total, jiffies_hi, jiffies_lo;
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
 						   policy->cpu);
 
 	if (!dbs_info->freq_table) {
@@ -188,7 +108,7 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 	cpufreq_frequency_table_target(policy, dbs_info->freq_table, freq_next,
 			relation, &index);
 	freq_req = dbs_info->freq_table[index].frequency;
-	freq_reduc = freq_req * dbs_tuners_ins.powersave_bias / 1000;
+	freq_reduc = freq_req * od_tuners.powersave_bias / 1000;
 	freq_avg = freq_req - freq_reduc;
 
 	/* Find freq bounds for freq_avg in freq_table */
@@ -207,7 +127,7 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 		dbs_info->freq_lo_jiffies = 0;
 		return freq_lo;
 	}
-	jiffies_total = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
+	jiffies_total = usecs_to_jiffies(od_tuners.sampling_rate);
 	jiffies_hi = (freq_avg - freq_lo) * jiffies_total;
 	jiffies_hi += ((freq_hi - freq_lo) / 2);
 	jiffies_hi /= (freq_hi - freq_lo);
@@ -218,13 +138,6 @@ static unsigned int powersave_bias_target(struct cpufreq_policy *policy,
 	return freq_hi;
 }
 
-static void ondemand_powersave_bias_init_cpu(int cpu)
-{
-	struct cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-	dbs_info->freq_table = cpufreq_frequency_get_table(cpu);
-	dbs_info->freq_lo = 0;
-}
-
 static void ondemand_powersave_bias_init(void)
 {
 	int i;
@@ -233,83 +146,179 @@ static void ondemand_powersave_bias_init(void)
 	}
 }
 
-/************************** sysfs interface ************************/
+static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
+{
+	if (od_tuners.powersave_bias)
+		freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H);
+	else if (p->cur == p->max)
+		return;
 
-static ssize_t show_sampling_rate_min(struct kobject *kobj,
-				      struct attribute *attr, char *buf)
+	__cpufreq_driver_target(p, freq, od_tuners.powersave_bias ?
+			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
+}
+
+/*
+ * Every sampling_rate, we check, if current idle time is less than 20%
+ * (default), then we try to increase frequency. Every sampling_rate, we look
+ * for the lowest frequency which can sustain the load while keeping idle time
+ * over 30%. If such a frequency exist, we try to decrease to this frequency.
+ *
+ * Any frequency increase takes it to the maximum frequency. Frequency reduction
+ * happens at minimum steps of 5% (default) of current frequency
+ */
+static void od_check_cpu(int cpu, unsigned int load_freq)
+{
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
+	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+
+	dbs_info->freq_lo = 0;
+
+	/* Check for frequency increase */
+	if (load_freq > od_tuners.up_threshold * policy->cur) {
+		/* If switching to max speed, apply sampling_down_factor */
+		if (policy->cur < policy->max)
+			dbs_info->rate_mult =
+				od_tuners.sampling_down_factor;
+		dbs_freq_increase(policy, policy->max);
+		return;
+	}
+
+	/* Check for frequency decrease */
+	/* if we cannot reduce the frequency anymore, break out early */
+	if (policy->cur == policy->min)
+		return;
+
+	/*
+	 * The optimal frequency is the frequency that is the lowest that can
+	 * support the current CPU usage without triggering the up policy. To be
+	 * safe, we focus 10 points under the threshold.
+	 */
+	if (load_freq < od_tuners.adj_up_threshold * policy->cur) {
+		unsigned int freq_next;
+		freq_next = load_freq / od_tuners.adj_up_threshold;
+
+		/* No longer fully busy, reset rate_mult */
+		dbs_info->rate_mult = 1;
+
+		if (freq_next < policy->min)
+			freq_next = policy->min;
+
+		if (!od_tuners.powersave_bias) {
+			__cpufreq_driver_target(policy, freq_next,
+					CPUFREQ_RELATION_L);
+		} else {
+			int freq = powersave_bias_target(policy, freq_next,
+					CPUFREQ_RELATION_L);
+			__cpufreq_driver_target(policy, freq,
+					CPUFREQ_RELATION_L);
+		}
+	}
+}
+
+static void od_dbs_timer(struct work_struct *work)
 {
-	return sprintf(buf, "%u\n", min_sampling_rate);
+	struct delayed_work *dw = to_delayed_work(work);
+	struct od_cpu_dbs_info_s *dbs_info =
+		container_of(work, struct od_cpu_dbs_info_s, cdbs.work.work);
+	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
+	struct od_cpu_dbs_info_s *core_dbs_info = &per_cpu(od_cpu_dbs_info,
+			cpu);
+	int delay, sample_type = core_dbs_info->sample_type;
+	bool eval_load;
+
+	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
+	eval_load = need_load_eval(&core_dbs_info->cdbs,
+			od_tuners.sampling_rate);
+
+	/* Common NORMAL_SAMPLE setup */
+	core_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	if (sample_type == OD_SUB_SAMPLE) {
+		delay = core_dbs_info->freq_lo_jiffies;
+		if (eval_load)
+			__cpufreq_driver_target(core_dbs_info->cdbs.cur_policy,
+						core_dbs_info->freq_lo,
+						CPUFREQ_RELATION_H);
+	} else {
+		if (eval_load)
+			dbs_check_cpu(&od_dbs_data, cpu);
+		if (core_dbs_info->freq_lo) {
+			/* Setup timer for SUB_SAMPLE */
+			core_dbs_info->sample_type = OD_SUB_SAMPLE;
+			delay = core_dbs_info->freq_hi_jiffies;
+		} else {
+			delay = delay_for_sampling_rate(od_tuners.sampling_rate
+						* core_dbs_info->rate_mult);
+		}
+	}
+
+	schedule_delayed_work_on(smp_processor_id(), dw, delay);
+	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
 }
 
-define_one_global_ro(sampling_rate_min);
+/************************** sysfs interface ************************/
 
-/* cpufreq_ondemand Governor Tunables */
-#define show_one(file_name, object)					\
-static ssize_t show_##file_name						\
-(struct kobject *kobj, struct attribute *attr, char *buf)              \
-{									\
-	return sprintf(buf, "%u\n", dbs_tuners_ins.object);		\
+static ssize_t show_sampling_rate_min(struct kobject *kobj,
+				      struct attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", od_dbs_data.min_sampling_rate);
 }
-show_one(sampling_rate, sampling_rate);
-show_one(io_is_busy, io_is_busy);
-show_one(up_threshold, up_threshold);
-show_one(sampling_down_factor, sampling_down_factor);
-show_one(ignore_nice_load, ignore_nice);
-show_one(powersave_bias, powersave_bias);
 
 /**
  * update_sampling_rate - update sampling rate effective immediately if needed.
  * @new_rate: new sampling rate
  *
- * If new rate is smaller than the old, simply updaing
- * dbs_tuners_int.sampling_rate might not be appropriate. For example,
- * if the original sampling_rate was 1 second and the requested new sampling
- * rate is 10 ms because the user needs immediate reaction from ondemand
- * governor, but not sure if higher frequency will be required or not,
- * then, the governor may change the sampling rate too late; up to 1 second
- * later. Thus, if we are reducing the sampling rate, we need to make the
- * new value effective immediately.
+ * If new rate is smaller than the old, simply updating
+ * dbs_tuners_int.sampling_rate might not be appropriate. For example, if the
+ * original sampling_rate was 1 second and the requested new sampling rate is 10
+ * ms because the user needs immediate reaction from ondemand governor, but not
+ * sure if higher frequency will be required or not, then, the governor may
+ * change the sampling rate too late; up to 1 second later. Thus, if we are
+ * reducing the sampling rate, we need to make the new value effective
+ * immediately.
  */
 static void update_sampling_rate(unsigned int new_rate)
 {
 	int cpu;
 
-	dbs_tuners_ins.sampling_rate = new_rate
-				     = max(new_rate, min_sampling_rate);
+	od_tuners.sampling_rate = new_rate = max(new_rate,
+			od_dbs_data.min_sampling_rate);
 
 	for_each_online_cpu(cpu) {
 		struct cpufreq_policy *policy;
-		struct cpu_dbs_info_s *dbs_info;
+		struct od_cpu_dbs_info_s *dbs_info;
 		unsigned long next_sampling, appointed_at;
 
 		policy = cpufreq_cpu_get(cpu);
 		if (!policy)
 			continue;
-		dbs_info = &per_cpu(od_cpu_dbs_info, policy->cpu);
+		if (policy->governor != &cpufreq_gov_ondemand) {
+			cpufreq_cpu_put(policy);
+			continue;
+		}
+		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 		cpufreq_cpu_put(policy);
 
-		mutex_lock(&dbs_info->timer_mutex);
+		mutex_lock(&dbs_info->cdbs.timer_mutex);
 
-		if (!delayed_work_pending(&dbs_info->work)) {
-			mutex_unlock(&dbs_info->timer_mutex);
+		if (!delayed_work_pending(&dbs_info->cdbs.work)) {
+			mutex_unlock(&dbs_info->cdbs.timer_mutex);
 			continue;
 		}
 
-		next_sampling  = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->work.timer.expires;
-
+		next_sampling = jiffies + usecs_to_jiffies(new_rate);
+		appointed_at = dbs_info->cdbs.work.timer.expires;
 
 		if (time_before(next_sampling, appointed_at)) {
 
-			mutex_unlock(&dbs_info->timer_mutex);
-			cancel_delayed_work_sync(&dbs_info->work);
-			mutex_lock(&dbs_info->timer_mutex);
+			mutex_unlock(&dbs_info->cdbs.timer_mutex);
+			cancel_delayed_work_sync(&dbs_info->cdbs.work);
+			mutex_lock(&dbs_info->cdbs.timer_mutex);
 
-			schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work,
-						 usecs_to_jiffies(new_rate));
+			schedule_delayed_work_on(cpu, &dbs_info->cdbs.work,
+					usecs_to_jiffies(new_rate));
 
 		}
-		mutex_unlock(&dbs_info->timer_mutex);
+		mutex_unlock(&dbs_info->cdbs.timer_mutex);
 	}
 }
 
@@ -334,7 +343,7 @@ static ssize_t store_io_is_busy(struct kobject *a, struct attribute *b,
 	ret = sscanf(buf, "%u", &input);
 	if (ret != 1)
 		return -EINVAL;
-	dbs_tuners_ins.io_is_busy = !!input;
+	od_tuners.io_is_busy = !!input;
 	return count;
 }
 
@@ -349,7 +358,11 @@ static ssize_t store_up_threshold(struct kobject *a, struct attribute *b,
 			input < MIN_FREQUENCY_UP_THRESHOLD) {
 		return -EINVAL;
 	}
-	dbs_tuners_ins.up_threshold = input;
+	/* Calculate the new adj_up_threshold */
+	od_tuners.adj_up_threshold += input;
+	od_tuners.adj_up_threshold -= od_tuners.up_threshold;
+
+	od_tuners.up_threshold = input;
 	return count;
 }
 
@@ -362,12 +375,12 @@ static ssize_t store_sampling_down_factor(struct kobject *a,
 
 	if (ret != 1 || input > MAX_SAMPLING_DOWN_FACTOR || input < 1)
 		return -EINVAL;
-	dbs_tuners_ins.sampling_down_factor = input;
+	od_tuners.sampling_down_factor = input;
 
 	/* Reset down sampling multiplier in case it was active */
 	for_each_online_cpu(j) {
-		struct cpu_dbs_info_s *dbs_info;
-		dbs_info = &per_cpu(od_cpu_dbs_info, j);
+		struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
+				j);
 		dbs_info->rate_mult = 1;
 	}
 	return count;
@@ -388,19 +401,20 @@ static ssize_t store_ignore_nice_load(struct kobject *a, struct attribute *b,
 	if (input > 1)
 		input = 1;
 
-	if (input == dbs_tuners_ins.ignore_nice) { /* nothing to do */
+	if (input == od_tuners.ignore_nice) { /* nothing to do */
 		return count;
 	}
-	dbs_tuners_ins.ignore_nice = input;
+	od_tuners.ignore_nice = input;
 
 	/* we need to re-evaluate prev_cpu_idle */
 	for_each_online_cpu(j) {
-		struct cpu_dbs_info_s *dbs_info;
+		struct od_cpu_dbs_info_s *dbs_info;
 		dbs_info = &per_cpu(od_cpu_dbs_info, j);
-		dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&dbs_info->prev_cpu_wall);
-		if (dbs_tuners_ins.ignore_nice)
-			dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		dbs_info->cdbs.prev_cpu_idle = get_cpu_idle_time(j,
+						&dbs_info->cdbs.prev_cpu_wall);
+		if (od_tuners.ignore_nice)
+			dbs_info->cdbs.prev_cpu_nice =
+				kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
 	}
 	return count;
@@ -419,17 +433,25 @@ static ssize_t store_powersave_bias(struct kobject *a, struct attribute *b,
 	if (input > 1000)
 		input = 1000;
 
-	dbs_tuners_ins.powersave_bias = input;
+	od_tuners.powersave_bias = input;
 	ondemand_powersave_bias_init();
 	return count;
 }
 
+show_one(od, sampling_rate, sampling_rate);
+show_one(od, io_is_busy, io_is_busy);
+show_one(od, up_threshold, up_threshold);
+show_one(od, sampling_down_factor, sampling_down_factor);
+show_one(od, ignore_nice_load, ignore_nice);
+show_one(od, powersave_bias, powersave_bias);
+
 define_one_global_rw(sampling_rate);
 define_one_global_rw(io_is_busy);
 define_one_global_rw(up_threshold);
 define_one_global_rw(sampling_down_factor);
 define_one_global_rw(ignore_nice_load);
 define_one_global_rw(powersave_bias);
+define_one_global_ro(sampling_rate_min);
 
 static struct attribute *dbs_attributes[] = {
 	&sampling_rate_min.attr,
@@ -442,354 +464,72 @@ static struct attribute *dbs_attributes[] = {
 	NULL
 };
 
-static struct attribute_group dbs_attr_group = {
+static struct attribute_group od_attr_group = {
 	.attrs = dbs_attributes,
 	.name = "ondemand",
 };
 
 /************************** sysfs end ************************/
 
-static void dbs_freq_increase(struct cpufreq_policy *p, unsigned int freq)
-{
-	if (dbs_tuners_ins.powersave_bias)
-		freq = powersave_bias_target(p, freq, CPUFREQ_RELATION_H);
-	else if (p->cur == p->max)
-		return;
-
-	__cpufreq_driver_target(p, freq, dbs_tuners_ins.powersave_bias ?
-			CPUFREQ_RELATION_L : CPUFREQ_RELATION_H);
-}
-
-static void dbs_check_cpu(struct cpu_dbs_info_s *this_dbs_info)
-{
-	unsigned int max_load_freq;
-
-	struct cpufreq_policy *policy;
-	unsigned int j;
-
-	this_dbs_info->freq_lo = 0;
-	policy = this_dbs_info->cur_policy;
-
-	/*
-	 * Every sampling_rate, we check, if current idle time is less
-	 * than 20% (default), then we try to increase frequency
-	 * Every sampling_rate, we look for a the lowest
-	 * frequency which can sustain the load while keeping idle time over
-	 * 30%. If such a frequency exist, we try to decrease to this frequency.
-	 *
-	 * Any frequency increase takes it to the maximum frequency.
-	 * Frequency reduction happens at minimum steps of
-	 * 5% (default) of current frequency
-	 */
-
-	/* Get Absolute Load - in terms of freq */
-	max_load_freq = 0;
-
-	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_info_s *j_dbs_info;
-		cputime64_t cur_wall_time, cur_idle_time, cur_iowait_time;
-		unsigned int idle_time, wall_time, iowait_time;
-		unsigned int load, load_freq;
-		int freq_avg;
-
-		j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
-
-		cur_idle_time = get_cpu_idle_time(j, &cur_wall_time);
-		cur_iowait_time = get_cpu_iowait_time(j, &cur_wall_time);
-
-		wall_time = (unsigned int)
-			(cur_wall_time - j_dbs_info->prev_cpu_wall);
-		j_dbs_info->prev_cpu_wall = cur_wall_time;
-
-		idle_time = (unsigned int)
-			(cur_idle_time - j_dbs_info->prev_cpu_idle);
-		j_dbs_info->prev_cpu_idle = cur_idle_time;
-
-		iowait_time = (unsigned int)
-			(cur_iowait_time - j_dbs_info->prev_cpu_iowait);
-		j_dbs_info->prev_cpu_iowait = cur_iowait_time;
-
-		if (dbs_tuners_ins.ignore_nice) {
-			u64 cur_nice;
-			unsigned long cur_nice_jiffies;
-
-			cur_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE] -
-					 j_dbs_info->prev_cpu_nice;
-			/*
-			 * Assumption: nice time between sampling periods will
-			 * be less than 2^32 jiffies for 32 bit sys
-			 */
-			cur_nice_jiffies = (unsigned long)
-					cputime64_to_jiffies64(cur_nice);
-
-			j_dbs_info->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-			idle_time += jiffies_to_usecs(cur_nice_jiffies);
-		}
-
-		/*
-		 * For the purpose of ondemand, waiting for disk IO is an
-		 * indication that you're performance critical, and not that
-		 * the system is actually idle. So subtract the iowait time
-		 * from the cpu idle time.
-		 */
-
-		if (dbs_tuners_ins.io_is_busy && idle_time >= iowait_time)
-			idle_time -= iowait_time;
-
-		if (unlikely(!wall_time || wall_time < idle_time))
-			continue;
-
-		load = 100 * (wall_time - idle_time) / wall_time;
-
-		freq_avg = __cpufreq_driver_getavg(policy, j);
-		if (freq_avg <= 0)
-			freq_avg = policy->cur;
-
-		load_freq = load * freq_avg;
-		if (load_freq > max_load_freq)
-			max_load_freq = load_freq;
-	}
-
-	/* Check for frequency increase */
-	if (max_load_freq > dbs_tuners_ins.up_threshold * policy->cur) {
-		/* If switching to max speed, apply sampling_down_factor */
-		if (policy->cur < policy->max)
-			this_dbs_info->rate_mult =
-				dbs_tuners_ins.sampling_down_factor;
-		dbs_freq_increase(policy, policy->max);
-		return;
-	}
-
-	/* Check for frequency decrease */
-	/* if we cannot reduce the frequency anymore, break out early */
-	if (policy->cur == policy->min)
-		return;
-
-	/*
-	 * The optimal frequency is the frequency that is the lowest that
-	 * can support the current CPU usage without triggering the up
-	 * policy. To be safe, we focus 10 points under the threshold.
-	 */
-	if (max_load_freq <
-	    (dbs_tuners_ins.up_threshold - dbs_tuners_ins.down_differential) *
-	     policy->cur) {
-		unsigned int freq_next;
-		freq_next = max_load_freq /
-				(dbs_tuners_ins.up_threshold -
-				 dbs_tuners_ins.down_differential);
-
-		/* No longer fully busy, reset rate_mult */
-		this_dbs_info->rate_mult = 1;
-
-		if (freq_next < policy->min)
-			freq_next = policy->min;
+define_get_cpu_dbs_routines(od_cpu_dbs_info);
 
-		if (!dbs_tuners_ins.powersave_bias) {
-			__cpufreq_driver_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
-		} else {
-			int freq = powersave_bias_target(policy, freq_next,
-					CPUFREQ_RELATION_L);
-			__cpufreq_driver_target(policy, freq,
-				CPUFREQ_RELATION_L);
-		}
-	}
-}
-
-static void do_dbs_timer(struct work_struct *work)
-{
-	struct cpu_dbs_info_s *dbs_info =
-		container_of(work, struct cpu_dbs_info_s, work.work);
-	unsigned int cpu = dbs_info->cpu;
-	int sample_type = dbs_info->sample_type;
-
-	int delay;
-
-	mutex_lock(&dbs_info->timer_mutex);
-
-	/* Common NORMAL_SAMPLE setup */
-	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
-	if (!dbs_tuners_ins.powersave_bias ||
-	    sample_type == DBS_NORMAL_SAMPLE) {
-		dbs_check_cpu(dbs_info);
-		if (dbs_info->freq_lo) {
-			/* Setup timer for SUB_SAMPLE */
-			dbs_info->sample_type = DBS_SUB_SAMPLE;
-			delay = dbs_info->freq_hi_jiffies;
-		} else {
-			/* We want all CPUs to do sampling nearly on
-			 * same jiffy
-			 */
-			delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate
-				* dbs_info->rate_mult);
-
-			if (num_online_cpus() > 1)
-				delay -= jiffies % delay;
-		}
-	} else {
-		__cpufreq_driver_target(dbs_info->cur_policy,
-			dbs_info->freq_lo, CPUFREQ_RELATION_H);
-		delay = dbs_info->freq_lo_jiffies;
-	}
-	schedule_delayed_work_on(cpu, &dbs_info->work, delay);
-	mutex_unlock(&dbs_info->timer_mutex);
-}
-
-static inline void dbs_timer_init(struct cpu_dbs_info_s *dbs_info)
-{
-	/* We want all CPUs to do sampling nearly on same jiffy */
-	int delay = usecs_to_jiffies(dbs_tuners_ins.sampling_rate);
-
-	if (num_online_cpus() > 1)
-		delay -= jiffies % delay;
+static struct od_ops od_ops = {
+	.io_busy = should_io_be_busy,
+	.powersave_bias_init_cpu = ondemand_powersave_bias_init_cpu,
+	.powersave_bias_target = powersave_bias_target,
+	.freq_increase = dbs_freq_increase,
+};
 
-	dbs_info->sample_type = DBS_NORMAL_SAMPLE;
-	INIT_DEFERRABLE_WORK(&dbs_info->work, do_dbs_timer);
-	schedule_delayed_work_on(dbs_info->cpu, &dbs_info->work, delay);
-}
+static struct dbs_data od_dbs_data = {
+	.governor = GOV_ONDEMAND,
+	.attr_group = &od_attr_group,
+	.tuners = &od_tuners,
+	.get_cpu_cdbs = get_cpu_cdbs,
+	.get_cpu_dbs_info_s = get_cpu_dbs_info_s,
+	.gov_dbs_timer = od_dbs_timer,
+	.gov_check_cpu = od_check_cpu,
+	.gov_ops = &od_ops,
+};
 
-static inline void dbs_timer_exit(struct cpu_dbs_info_s *dbs_info)
+static int od_cpufreq_governor_dbs(struct cpufreq_policy *policy,
+		unsigned int event)
 {
-	cancel_delayed_work_sync(&dbs_info->work);
+	return cpufreq_governor_dbs(&od_dbs_data, policy, event);
 }
 
-/*
- * Not all CPUs want IO time to be accounted as busy; this dependson how
- * efficient idling at a higher frequency/voltage is.
- * Pavel Machek says this is not so for various generations of AMD and old
- * Intel systems.
- * Mike Chan (androidlcom) calis this is also not true for ARM.
- * Because of this, whitelist specific known (series) of CPUs by default, and
- * leave all others up to the user.
- */
-static int should_io_be_busy(void)
-{
-#if defined(CONFIG_X86)
-	/*
-	 * For Intel, Core 2 (model 15) andl later have an efficient idle.
-	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL &&
-	    boot_cpu_data.x86 == 6 &&
-	    boot_cpu_data.x86_model >= 15)
-		return 1;
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND
+static
 #endif
-	return 0;
-}
-
-static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-				   unsigned int event)
-{
-	unsigned int cpu = policy->cpu;
-	struct cpu_dbs_info_s *this_dbs_info;
-	unsigned int j;
-	int rc;
-
-	this_dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if ((!cpu_online(cpu)) || (!policy->cur))
-			return -EINVAL;
-
-		mutex_lock(&dbs_mutex);
-
-		dbs_enable++;
-		for_each_cpu(j, policy->cpus) {
-			struct cpu_dbs_info_s *j_dbs_info;
-			j_dbs_info = &per_cpu(od_cpu_dbs_info, j);
-			j_dbs_info->cur_policy = policy;
-
-			j_dbs_info->prev_cpu_idle = get_cpu_idle_time(j,
-						&j_dbs_info->prev_cpu_wall);
-			if (dbs_tuners_ins.ignore_nice)
-				j_dbs_info->prev_cpu_nice =
-						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
-		}
-		this_dbs_info->cpu = cpu;
-		this_dbs_info->rate_mult = 1;
-		ondemand_powersave_bias_init_cpu(cpu);
-		/*
-		 * Start the timerschedule work, when this governor
-		 * is used for first time
-		 */
-		if (dbs_enable == 1) {
-			unsigned int latency;
-
-			rc = sysfs_create_group(cpufreq_global_kobject,
-						&dbs_attr_group);
-			if (rc) {
-				mutex_unlock(&dbs_mutex);
-				return rc;
-			}
-
-			/* policy latency is in nS. Convert it to uS first */
-			latency = policy->cpuinfo.transition_latency / 1000;
-			if (latency == 0)
-				latency = 1;
-			/* Bring kernel and HW constraints together */
-			min_sampling_rate = max(min_sampling_rate,
-					MIN_LATENCY_MULTIPLIER * latency);
-			dbs_tuners_ins.sampling_rate =
-				max(min_sampling_rate,
-				    latency * LATENCY_MULTIPLIER);
-			dbs_tuners_ins.io_is_busy = should_io_be_busy();
-		}
-		mutex_unlock(&dbs_mutex);
-
-		mutex_init(&this_dbs_info->timer_mutex);
-		dbs_timer_init(this_dbs_info);
-		break;
-
-	case CPUFREQ_GOV_STOP:
-		dbs_timer_exit(this_dbs_info);
-
-		mutex_lock(&dbs_mutex);
-		mutex_destroy(&this_dbs_info->timer_mutex);
-		dbs_enable--;
-		mutex_unlock(&dbs_mutex);
-		if (!dbs_enable)
-			sysfs_remove_group(cpufreq_global_kobject,
-					   &dbs_attr_group);
-
-		break;
-
-	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&this_dbs_info->timer_mutex);
-		if (policy->max < this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(this_dbs_info->cur_policy,
-				policy->max, CPUFREQ_RELATION_H);
-		else if (policy->min > this_dbs_info->cur_policy->cur)
-			__cpufreq_driver_target(this_dbs_info->cur_policy,
-				policy->min, CPUFREQ_RELATION_L);
-		dbs_check_cpu(this_dbs_info);
-		mutex_unlock(&this_dbs_info->timer_mutex);
-		break;
-	}
-	return 0;
-}
+struct cpufreq_governor cpufreq_gov_ondemand = {
+	.name			= "ondemand",
+	.governor		= od_cpufreq_governor_dbs,
+	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
+	.owner			= THIS_MODULE,
+};
 
 static int __init cpufreq_gov_dbs_init(void)
 {
 	u64 idle_time;
 	int cpu = get_cpu();
 
+	mutex_init(&od_dbs_data.mutex);
 	idle_time = get_cpu_idle_time_us(cpu, NULL);
 	put_cpu();
 	if (idle_time != -1ULL) {
 		/* Idle micro accounting is supported. Use finer thresholds */
-		dbs_tuners_ins.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
-		dbs_tuners_ins.down_differential =
-					MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
+		od_tuners.up_threshold = MICRO_FREQUENCY_UP_THRESHOLD;
+		od_tuners.adj_up_threshold = MICRO_FREQUENCY_UP_THRESHOLD -
+					     MICRO_FREQUENCY_DOWN_DIFFERENTIAL;
 		/*
 		 * In nohz/micro accounting case we set the minimum frequency
 		 * not depending on HZ, but fixed (very low). The deferred
 		 * timer might skip some samples if idle/sleeping as needed.
 		*/
-		min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
+		od_dbs_data.min_sampling_rate = MICRO_FREQUENCY_MIN_SAMPLE_RATE;
 	} else {
 		/* For correct statistics, we need 10 ticks for each measure */
-		min_sampling_rate =
-			MIN_SAMPLING_RATE_RATIO * jiffies_to_usecs(10);
+		od_dbs_data.min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
+			jiffies_to_usecs(10);
 	}
 
 	return cpufreq_register_governor(&cpufreq_gov_ondemand);
@@ -800,7 +540,6 @@ static void __exit cpufreq_gov_dbs_exit(void)
 	cpufreq_unregister_governor(&cpufreq_gov_ondemand);
 }
 
-
 MODULE_AUTHOR("Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>");
 MODULE_AUTHOR("Alexey Starikovskiy <alexey.y.starikovskiy@intel.com>");
 MODULE_DESCRIPTION("'cpufreq_ondemand' - A dynamic cpufreq governor for "
diff --git a/drivers/cpufreq/cpufreq_performance.c b/drivers/cpufreq/cpufreq_performance.c
index f13a8a9af6a1..ceee06849b91 100644
--- a/drivers/cpufreq/cpufreq_performance.c
+++ b/drivers/cpufreq/cpufreq_performance.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/cpufreq.h>
diff --git a/drivers/cpufreq/cpufreq_powersave.c b/drivers/cpufreq/cpufreq_powersave.c
index 4c2eb512f2bc..2d948a171155 100644
--- a/drivers/cpufreq/cpufreq_powersave.c
+++ b/drivers/cpufreq/cpufreq_powersave.c
@@ -10,6 +10,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/cpufreq.h>
diff --git a/drivers/cpufreq/cpufreq_stats.c b/drivers/cpufreq/cpufreq_stats.c
index 399831690fed..2fd779eb1ed1 100644
--- a/drivers/cpufreq/cpufreq_stats.c
+++ b/drivers/cpufreq/cpufreq_stats.c
@@ -24,12 +24,6 @@
 
 static spinlock_t cpufreq_stats_lock;
 
-#define CPUFREQ_STATDEVICE_ATTR(_name, _mode, _show) \
-static struct freq_attr _attr_##_name = {\
-	.attr = {.name = __stringify(_name), .mode = _mode, }, \
-	.show = _show,\
-};
-
 struct cpufreq_stats {
 	unsigned int cpu;
 	unsigned int total_trans;
@@ -37,7 +31,7 @@ struct cpufreq_stats {
 	unsigned int max_state;
 	unsigned int state_num;
 	unsigned int last_index;
-	cputime64_t *time_in_state;
+	u64 *time_in_state;
 	unsigned int *freq_table;
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	unsigned int *trans_table;
@@ -136,17 +130,17 @@ static ssize_t show_trans_table(struct cpufreq_policy *policy, char *buf)
 		return PAGE_SIZE;
 	return len;
 }
-CPUFREQ_STATDEVICE_ATTR(trans_table, 0444, show_trans_table);
+cpufreq_freq_attr_ro(trans_table);
 #endif
 
-CPUFREQ_STATDEVICE_ATTR(total_trans, 0444, show_total_trans);
-CPUFREQ_STATDEVICE_ATTR(time_in_state, 0444, show_time_in_state);
+cpufreq_freq_attr_ro(total_trans);
+cpufreq_freq_attr_ro(time_in_state);
 
 static struct attribute *default_attrs[] = {
-	&_attr_total_trans.attr,
-	&_attr_time_in_state.attr,
+	&total_trans.attr,
+	&time_in_state.attr,
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
-	&_attr_trans_table.attr,
+	&trans_table.attr,
 #endif
 	NULL
 };
@@ -170,11 +164,13 @@ 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 +179,14 @@ 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 (!cpufreq_frequency_get_table(cpu))
+		return;
+
+	if (policy && !policy_is_shared(policy)) {
+		pr_debug("%s: Free sysfs stat\n", __func__);
 		sysfs_remove_group(&policy->kobj, &stats_attr_group);
+	}
 	if (policy)
 		cpufreq_cpu_put(policy);
 }
@@ -223,7 +225,7 @@ static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
 		count++;
 	}
 
-	alloc_size = count * sizeof(int) + count * sizeof(cputime64_t);
+	alloc_size = count * sizeof(int) + count * sizeof(u64);
 
 #ifdef CONFIG_CPU_FREQ_STAT_DETAILS
 	alloc_size += count * count * sizeof(int);
@@ -262,6 +264,19 @@ 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 +284,12 @@ 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);
@@ -364,18 +385,21 @@ static int __init cpufreq_stats_init(void)
 	if (ret)
 		return ret;
 
+	register_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
+	for_each_online_cpu(cpu)
+		cpufreq_update_policy(cpu);
+
 	ret = cpufreq_register_notifier(&notifier_trans_block,
 				CPUFREQ_TRANSITION_NOTIFIER);
 	if (ret) {
 		cpufreq_unregister_notifier(&notifier_policy_block,
 				CPUFREQ_POLICY_NOTIFIER);
+		unregister_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
+		for_each_online_cpu(cpu)
+			cpufreq_stats_free_table(cpu);
 		return ret;
 	}
 
-	register_hotcpu_notifier(&cpufreq_stat_cpu_notifier);
-	for_each_online_cpu(cpu) {
-		cpufreq_update_policy(cpu);
-	}
 	return 0;
 }
 static void __exit cpufreq_stats_exit(void)
diff --git a/drivers/cpufreq/cpufreq_userspace.c b/drivers/cpufreq/cpufreq_userspace.c
index bedac1aa9be3..bbeb9c0720a6 100644
--- a/drivers/cpufreq/cpufreq_userspace.c
+++ b/drivers/cpufreq/cpufreq_userspace.c
@@ -11,6 +11,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/smp.h>
@@ -116,8 +118,6 @@ static int cpufreq_governor_userspace(struct cpufreq_policy *policy,
 
 	switch (event) {
 	case CPUFREQ_GOV_START:
-		if (!cpu_online(cpu))
-			return -EINVAL;
 		BUG_ON(!policy->cur);
 		mutex_lock(&userspace_mutex);
 
diff --git a/drivers/cpufreq/db8500-cpufreq.c b/drivers/cpufreq/db8500-cpufreq.c
deleted file mode 100644
index 74b830b635a6..000000000000
--- a/drivers/cpufreq/db8500-cpufreq.c
+++ /dev/null
@@ -1,170 +0,0 @@
-/*
- * Copyright (C) STMicroelectronics 2009
- * Copyright (C) ST-Ericsson SA 2010
- *
- * License Terms: GNU General Public License v2
- * Author: Sundar Iyer <sundar.iyer@stericsson.com>
- * Author: Martin Persson <martin.persson@stericsson.com>
- * Author: Jonas Aaberg <jonas.aberg@stericsson.com>
- *
- */
-#include <linux/kernel.h>
-#include <linux/cpufreq.h>
-#include <linux/delay.h>
-#include <linux/slab.h>
-#include <linux/mfd/dbx500-prcmu.h>
-#include <mach/id.h>
-
-static struct cpufreq_frequency_table freq_table[] = {
-	[0] = {
-		.index = 0,
-		.frequency = 200000,
-	},
-	[1] = {
-		.index = 1,
-		.frequency = 400000,
-	},
-	[2] = {
-		.index = 2,
-		.frequency = 800000,
-	},
-	[3] = {
-		/* Used for MAX_OPP, if available */
-		.index = 3,
-		.frequency = CPUFREQ_TABLE_END,
-	},
-	[4] = {
-		.index = 4,
-		.frequency = CPUFREQ_TABLE_END,
-	},
-};
-
-static enum arm_opp idx2opp[] = {
-	ARM_EXTCLK,
-	ARM_50_OPP,
-	ARM_100_OPP,
-	ARM_MAX_OPP
-};
-
-static struct freq_attr *db8500_cpufreq_attr[] = {
-	&cpufreq_freq_attr_scaling_available_freqs,
-	NULL,
-};
-
-static int db8500_cpufreq_verify_speed(struct cpufreq_policy *policy)
-{
-	return cpufreq_frequency_table_verify(policy, freq_table);
-}
-
-static int db8500_cpufreq_target(struct cpufreq_policy *policy,
-				unsigned int target_freq,
-				unsigned int relation)
-{
-	struct cpufreq_freqs freqs;
-	unsigned int idx;
-
-	/* scale the target frequency to one of the extremes supported */
-	if (target_freq < policy->cpuinfo.min_freq)
-		target_freq = policy->cpuinfo.min_freq;
-	if (target_freq > policy->cpuinfo.max_freq)
-		target_freq = policy->cpuinfo.max_freq;
-
-	/* Lookup the next frequency */
-	if (cpufreq_frequency_table_target
-	    (policy, freq_table, target_freq, relation, &idx)) {
-		return -EINVAL;
-	}
-
-	freqs.old = policy->cur;
-	freqs.new = freq_table[idx].frequency;
-
-	if (freqs.old == freqs.new)
-		return 0;
-
-	/* pre-change notification */
-	for_each_cpu(freqs.cpu, policy->cpus)
-		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
-
-	/* request the PRCM unit for opp change */
-	if (prcmu_set_arm_opp(idx2opp[idx])) {
-		pr_err("db8500-cpufreq:  Failed to set OPP level\n");
-		return -EINVAL;
-	}
-
-	/* post change notification */
-	for_each_cpu(freqs.cpu, policy->cpus)
-		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
-
-	return 0;
-}
-
-static unsigned int db8500_cpufreq_getspeed(unsigned int cpu)
-{
-	int i;
-	/* request the prcm to get the current ARM opp */
-	for (i = 0; prcmu_get_arm_opp() != idx2opp[i]; i++)
-		;
-	return freq_table[i].frequency;
-}
-
-static int __cpuinit db8500_cpufreq_init(struct cpufreq_policy *policy)
-{
-	int i, res;
-
-	BUILD_BUG_ON(ARRAY_SIZE(idx2opp) + 1 != ARRAY_SIZE(freq_table));
-
-	if (prcmu_has_arm_maxopp())
-		freq_table[3].frequency = 1000000;
-
-	pr_info("db8500-cpufreq : Available frequencies:\n");
-	for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
-		pr_info("  %d Mhz\n", freq_table[i].frequency/1000);
-
-	/* get policy fields based on the table */
-	res = cpufreq_frequency_table_cpuinfo(policy, freq_table);
-	if (!res)
-		cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
-	else {
-		pr_err("db8500-cpufreq : Failed to read policy table\n");
-		return res;
-	}
-
-	policy->min = policy->cpuinfo.min_freq;
-	policy->max = policy->cpuinfo.max_freq;
-	policy->cur = db8500_cpufreq_getspeed(policy->cpu);
-	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
-
-	/*
-	 * FIXME : Need to take time measurement across the target()
-	 *	   function with no/some/all drivers in the notification
-	 *	   list.
-	 */
-	policy->cpuinfo.transition_latency = 20 * 1000; /* in ns */
-
-	/* policy sharing between dual CPUs */
-	cpumask_copy(policy->cpus, cpu_present_mask);
-
-	policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
-
-	return 0;
-}
-
-static struct cpufreq_driver db8500_cpufreq_driver = {
-	.flags  = CPUFREQ_STICKY,
-	.verify = db8500_cpufreq_verify_speed,
-	.target = db8500_cpufreq_target,
-	.get    = db8500_cpufreq_getspeed,
-	.init   = db8500_cpufreq_init,
-	.name   = "DB8500",
-	.attr   = db8500_cpufreq_attr,
-};
-
-static int __init db8500_cpufreq_register(void)
-{
-	if (!cpu_is_u8500_family())
-		return -ENODEV;
-
-	pr_info("cpufreq for DB8500 started\n");
-	return cpufreq_register_driver(&db8500_cpufreq_driver);
-}
-device_initcall(db8500_cpufreq_register);
diff --git a/drivers/cpufreq/dbx500-cpufreq.c b/drivers/cpufreq/dbx500-cpufreq.c
new file mode 100644
index 000000000000..72f0c3efa76e
--- /dev/null
+++ b/drivers/cpufreq/dbx500-cpufreq.c
@@ -0,0 +1,174 @@
+/*
+ * Copyright (C) STMicroelectronics 2009
+ * Copyright (C) ST-Ericsson SA 2010-2012
+ *
+ * License Terms: GNU General Public License v2
+ * Author: Sundar Iyer <sundar.iyer@stericsson.com>
+ * Author: Martin Persson <martin.persson@stericsson.com>
+ * Author: Jonas Aaberg <jonas.aberg@stericsson.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+
+static struct cpufreq_frequency_table *freq_table;
+static struct clk *armss_clk;
+
+static struct freq_attr *dbx500_cpufreq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static int dbx500_cpufreq_verify_speed(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, freq_table);
+}
+
+static int dbx500_cpufreq_target(struct cpufreq_policy *policy,
+				unsigned int target_freq,
+				unsigned int relation)
+{
+	struct cpufreq_freqs freqs;
+	unsigned int idx;
+	int ret;
+
+	/* scale the target frequency to one of the extremes supported */
+	if (target_freq < policy->cpuinfo.min_freq)
+		target_freq = policy->cpuinfo.min_freq;
+	if (target_freq > policy->cpuinfo.max_freq)
+		target_freq = policy->cpuinfo.max_freq;
+
+	/* Lookup the next frequency */
+	if (cpufreq_frequency_table_target(policy, freq_table, target_freq,
+					relation, &idx))
+		return -EINVAL;
+
+	freqs.old = policy->cur;
+	freqs.new = freq_table[idx].frequency;
+
+	if (freqs.old == freqs.new)
+		return 0;
+
+	/* pre-change notification */
+	for_each_cpu(freqs.cpu, policy->cpus)
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	/* update armss clk frequency */
+	ret = clk_set_rate(armss_clk, freqs.new * 1000);
+
+	if (ret) {
+		pr_err("dbx500-cpufreq: Failed to set armss_clk to %d Hz: error %d\n",
+		       freqs.new * 1000, ret);
+		return ret;
+	}
+
+	/* post change notification */
+	for_each_cpu(freqs.cpu, policy->cpus)
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+
+	return 0;
+}
+
+static unsigned int dbx500_cpufreq_getspeed(unsigned int cpu)
+{
+	int i = 0;
+	unsigned long freq = clk_get_rate(armss_clk) / 1000;
+
+	while (freq_table[i].frequency != CPUFREQ_TABLE_END) {
+		if (freq <= freq_table[i].frequency)
+			return freq_table[i].frequency;
+		i++;
+	}
+
+	/* We could not find a corresponding frequency. */
+	pr_err("dbx500-cpufreq: Failed to find cpufreq speed\n");
+	return 0;
+}
+
+static int __cpuinit dbx500_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int res;
+
+	/* get policy fields based on the table */
+	res = cpufreq_frequency_table_cpuinfo(policy, freq_table);
+	if (!res)
+		cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
+	else {
+		pr_err("dbx500-cpufreq: Failed to read policy table\n");
+		return res;
+	}
+
+	policy->min = policy->cpuinfo.min_freq;
+	policy->max = policy->cpuinfo.max_freq;
+	policy->cur = dbx500_cpufreq_getspeed(policy->cpu);
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+
+	/*
+	 * FIXME : Need to take time measurement across the target()
+	 *	   function with no/some/all drivers in the notification
+	 *	   list.
+	 */
+	policy->cpuinfo.transition_latency = 20 * 1000; /* in ns */
+
+	/* policy sharing between dual CPUs */
+	cpumask_setall(policy->cpus);
+
+	return 0;
+}
+
+static struct cpufreq_driver dbx500_cpufreq_driver = {
+	.flags  = CPUFREQ_STICKY | CPUFREQ_CONST_LOOPS,
+	.verify = dbx500_cpufreq_verify_speed,
+	.target = dbx500_cpufreq_target,
+	.get    = dbx500_cpufreq_getspeed,
+	.init   = dbx500_cpufreq_init,
+	.name   = "DBX500",
+	.attr   = dbx500_cpufreq_attr,
+};
+
+static int dbx500_cpufreq_probe(struct platform_device *pdev)
+{
+	int i = 0;
+
+	freq_table = dev_get_platdata(&pdev->dev);
+	if (!freq_table) {
+		pr_err("dbx500-cpufreq: Failed to fetch cpufreq table\n");
+		return -ENODEV;
+	}
+
+	armss_clk = clk_get(&pdev->dev, "armss");
+	if (IS_ERR(armss_clk)) {
+		pr_err("dbx500-cpufreq: Failed to get armss clk\n");
+		return PTR_ERR(armss_clk);
+	}
+
+	pr_info("dbx500-cpufreq: Available frequencies:\n");
+	while (freq_table[i].frequency != CPUFREQ_TABLE_END) {
+		pr_info("  %d Mhz\n", freq_table[i].frequency/1000);
+		i++;
+	}
+
+	return cpufreq_register_driver(&dbx500_cpufreq_driver);
+}
+
+static struct platform_driver dbx500_cpufreq_plat_driver = {
+	.driver = {
+		.name = "cpufreq-ux500",
+		.owner = THIS_MODULE,
+	},
+	.probe = dbx500_cpufreq_probe,
+};
+
+static int __init dbx500_cpufreq_register(void)
+{
+	return platform_driver_register(&dbx500_cpufreq_plat_driver);
+}
+device_initcall(dbx500_cpufreq_register);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("cpufreq driver for DBX500");
diff --git a/drivers/cpufreq/exynos-cpufreq.c b/drivers/cpufreq/exynos-cpufreq.c
index af2d81e10f71..78057a357ddb 100644
--- a/drivers/cpufreq/exynos-cpufreq.c
+++ b/drivers/cpufreq/exynos-cpufreq.c
@@ -18,10 +18,10 @@
 #include <linux/cpufreq.h>
 #include <linux/suspend.h>
 
-#include <mach/cpufreq.h>
-
 #include <plat/cpu.h>
 
+#include "exynos-cpufreq.h"
+
 static struct exynos_dvfs_info *exynos_info;
 
 static struct regulator *arm_regulator;
@@ -31,62 +31,67 @@ static unsigned int locking_frequency;
 static bool frequency_locked;
 static DEFINE_MUTEX(cpufreq_lock);
 
-int exynos_verify_speed(struct cpufreq_policy *policy)
+static int exynos_verify_speed(struct cpufreq_policy *policy)
 {
 	return cpufreq_frequency_table_verify(policy,
 					      exynos_info->freq_table);
 }
 
-unsigned int exynos_getspeed(unsigned int cpu)
+static unsigned int exynos_getspeed(unsigned int cpu)
 {
 	return clk_get_rate(exynos_info->cpu_clk) / 1000;
 }
 
-static int exynos_target(struct cpufreq_policy *policy,
-			  unsigned int target_freq,
-			  unsigned int relation)
+static int exynos_cpufreq_get_index(unsigned int freq)
+{
+	struct cpufreq_frequency_table *freq_table = exynos_info->freq_table;
+	int index;
+
+	for (index = 0;
+		freq_table[index].frequency != CPUFREQ_TABLE_END; index++)
+		if (freq_table[index].frequency == freq)
+			break;
+
+	if (freq_table[index].frequency == CPUFREQ_TABLE_END)
+		return -EINVAL;
+
+	return index;
+}
+
+static int exynos_cpufreq_scale(unsigned int target_freq)
 {
-	unsigned int index, old_index;
-	unsigned int arm_volt, safe_arm_volt = 0;
-	int ret = 0;
 	struct cpufreq_frequency_table *freq_table = exynos_info->freq_table;
 	unsigned int *volt_table = exynos_info->volt_table;
+	struct cpufreq_policy *policy = cpufreq_cpu_get(0);
+	unsigned int arm_volt, safe_arm_volt = 0;
 	unsigned int mpll_freq_khz = exynos_info->mpll_freq_khz;
-
-	mutex_lock(&cpufreq_lock);
+	int index, old_index;
+	int ret = 0;
 
 	freqs.old = policy->cur;
+	freqs.new = target_freq;
+	freqs.cpu = policy->cpu;
 
-	if (frequency_locked && target_freq != locking_frequency) {
-		ret = -EAGAIN;
+	if (freqs.new == freqs.old)
 		goto out;
-	}
 
 	/*
 	 * The policy max have been changed so that we cannot get proper
 	 * old_index with cpufreq_frequency_table_target(). Thus, ignore
 	 * policy and get the index from the raw freqeuncy table.
 	 */
-	for (old_index = 0;
-		freq_table[old_index].frequency != CPUFREQ_TABLE_END;
-		old_index++)
-		if (freq_table[old_index].frequency == freqs.old)
-			break;
-
-	if (freq_table[old_index].frequency == CPUFREQ_TABLE_END) {
-		ret = -EINVAL;
+	old_index = exynos_cpufreq_get_index(freqs.old);
+	if (old_index < 0) {
+		ret = old_index;
 		goto out;
 	}
 
-	if (cpufreq_frequency_table_target(policy, freq_table,
-					   target_freq, relation, &index)) {
-		ret = -EINVAL;
+	index = exynos_cpufreq_get_index(target_freq);
+	if (index < 0) {
+		ret = index;
 		goto out;
 	}
 
-	freqs.new = freq_table[index].frequency;
-	freqs.cpu = policy->cpu;
-
 	/*
 	 * ARM clock source will be changed APLL to MPLL temporary
 	 * To support this level, need to control regulator for
@@ -100,22 +105,34 @@ static int exynos_target(struct cpufreq_policy *policy,
 	}
 	arm_volt = volt_table[index];
 
-	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+	for_each_cpu(freqs.cpu, policy->cpus)
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
 
 	/* When the new frequency is higher than current frequency */
 	if ((freqs.new > freqs.old) && !safe_arm_volt) {
 		/* Firstly, voltage up to increase frequency */
-		regulator_set_voltage(arm_regulator, arm_volt,
-				arm_volt);
+		ret = regulator_set_voltage(arm_regulator, arm_volt, arm_volt);
+		if (ret) {
+			pr_err("%s: failed to set cpu voltage to %d\n",
+				__func__, arm_volt);
+			goto out;
+		}
 	}
 
-	if (safe_arm_volt)
-		regulator_set_voltage(arm_regulator, safe_arm_volt,
+	if (safe_arm_volt) {
+		ret = regulator_set_voltage(arm_regulator, safe_arm_volt,
 				      safe_arm_volt);
-	if (freqs.new != freqs.old)
-		exynos_info->set_freq(old_index, index);
+		if (ret) {
+			pr_err("%s: failed to set cpu voltage to %d\n",
+				__func__, safe_arm_volt);
+			goto out;
+		}
+	}
+
+	exynos_info->set_freq(old_index, index);
 
-	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	for_each_cpu(freqs.cpu, policy->cpus)
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 
 	/* When the new frequency is lower than current frequency */
 	if ((freqs.new < freqs.old) ||
@@ -123,8 +140,44 @@ static int exynos_target(struct cpufreq_policy *policy,
 		/* down the voltage after frequency change */
 		regulator_set_voltage(arm_regulator, arm_volt,
 				arm_volt);
+		if (ret) {
+			pr_err("%s: failed to set cpu voltage to %d\n",
+				__func__, arm_volt);
+			goto out;
+		}
+	}
+
+out:
+
+	cpufreq_cpu_put(policy);
+
+	return ret;
+}
+
+static int exynos_target(struct cpufreq_policy *policy,
+			  unsigned int target_freq,
+			  unsigned int relation)
+{
+	struct cpufreq_frequency_table *freq_table = exynos_info->freq_table;
+	unsigned int index;
+	unsigned int new_freq;
+	int ret = 0;
+
+	mutex_lock(&cpufreq_lock);
+
+	if (frequency_locked)
+		goto out;
+
+	if (cpufreq_frequency_table_target(policy, freq_table,
+					   target_freq, relation, &index)) {
+		ret = -EINVAL;
+		goto out;
 	}
 
+	new_freq = freq_table[index].frequency;
+
+	ret = exynos_cpufreq_scale(new_freq);
+
 out:
 	mutex_unlock(&cpufreq_lock);
 
@@ -161,51 +214,26 @@ static int exynos_cpufreq_resume(struct cpufreq_policy *policy)
 static int exynos_cpufreq_pm_notifier(struct notifier_block *notifier,
 				       unsigned long pm_event, void *v)
 {
-	struct cpufreq_policy *policy = cpufreq_cpu_get(0); /* boot CPU */
-	static unsigned int saved_frequency;
-	unsigned int temp;
+	int ret;
 
-	mutex_lock(&cpufreq_lock);
 	switch (pm_event) {
 	case PM_SUSPEND_PREPARE:
-		if (frequency_locked)
-			goto out;
-
+		mutex_lock(&cpufreq_lock);
 		frequency_locked = true;
+		mutex_unlock(&cpufreq_lock);
 
-		if (locking_frequency) {
-			saved_frequency = exynos_getspeed(0);
+		ret = exynos_cpufreq_scale(locking_frequency);
+		if (ret < 0)
+			return NOTIFY_BAD;
 
-			mutex_unlock(&cpufreq_lock);
-			exynos_target(policy, locking_frequency,
-				      CPUFREQ_RELATION_H);
-			mutex_lock(&cpufreq_lock);
-		}
 		break;
 
 	case PM_POST_SUSPEND:
-		if (saved_frequency) {
-			/*
-			 * While frequency_locked, only locking_frequency
-			 * is valid for target(). In order to use
-			 * saved_frequency while keeping frequency_locked,
-			 * we temporarly overwrite locking_frequency.
-			 */
-			temp = locking_frequency;
-			locking_frequency = saved_frequency;
-
-			mutex_unlock(&cpufreq_lock);
-			exynos_target(policy, locking_frequency,
-				      CPUFREQ_RELATION_H);
-			mutex_lock(&cpufreq_lock);
-
-			locking_frequency = temp;
-		}
+		mutex_lock(&cpufreq_lock);
 		frequency_locked = false;
+		mutex_unlock(&cpufreq_lock);
 		break;
 	}
-out:
-	mutex_unlock(&cpufreq_lock);
 
 	return NOTIFY_OK;
 }
@@ -220,34 +248,34 @@ static int exynos_cpufreq_cpu_init(struct cpufreq_policy *policy)
 
 	cpufreq_frequency_table_get_attr(exynos_info->freq_table, policy->cpu);
 
-	locking_frequency = exynos_getspeed(0);
-
 	/* set the transition latency value */
 	policy->cpuinfo.transition_latency = 100000;
 
-	/*
-	 * EXYNOS4 multi-core processors has 2 cores
-	 * that the frequency cannot be set independently.
-	 * Each cpu is bound to the same speed.
-	 * So the affected cpu is all of the cpus.
-	 */
-	if (num_online_cpus() == 1) {
-		cpumask_copy(policy->related_cpus, cpu_possible_mask);
-		cpumask_copy(policy->cpus, cpu_online_mask);
-	} else {
-		cpumask_setall(policy->cpus);
-	}
+	cpumask_setall(policy->cpus);
 
 	return cpufreq_frequency_table_cpuinfo(policy, exynos_info->freq_table);
 }
 
+static int exynos_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
+static struct freq_attr *exynos_cpufreq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
 static struct cpufreq_driver exynos_driver = {
 	.flags		= CPUFREQ_STICKY,
 	.verify		= exynos_verify_speed,
 	.target		= exynos_target,
 	.get		= exynos_getspeed,
 	.init		= exynos_cpufreq_cpu_init,
+	.exit		= exynos_cpufreq_cpu_exit,
 	.name		= "exynos_cpufreq",
+	.attr		= exynos_cpufreq_attr,
 #ifdef CONFIG_PM
 	.suspend	= exynos_cpufreq_suspend,
 	.resume		= exynos_cpufreq_resume,
@@ -285,6 +313,8 @@ static int __init exynos_cpufreq_init(void)
 		goto err_vdd_arm;
 	}
 
+	locking_frequency = exynos_getspeed(0);
+
 	register_pm_notifier(&exynos_cpufreq_nb);
 
 	if (cpufreq_register_driver(&exynos_driver)) {
@@ -296,8 +326,7 @@ static int __init exynos_cpufreq_init(void)
 err_cpufreq:
 	unregister_pm_notifier(&exynos_cpufreq_nb);
 
-	if (!IS_ERR(arm_regulator))
-		regulator_put(arm_regulator);
+	regulator_put(arm_regulator);
 err_vdd_arm:
 	kfree(exynos_info);
 	pr_debug("%s: failed initialization\n", __func__);
diff --git a/drivers/cpufreq/exynos-cpufreq.h b/drivers/cpufreq/exynos-cpufreq.h
new file mode 100644
index 000000000000..92b852ee5ddc
--- /dev/null
+++ b/drivers/cpufreq/exynos-cpufreq.h
@@ -0,0 +1,48 @@
+/*
+ * Copyright (c) 2010 Samsung Electronics Co., Ltd.
+ *		http://www.samsung.com
+ *
+ * EXYNOS - CPUFreq support
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+*/
+
+enum cpufreq_level_index {
+	L0, L1, L2, L3, L4,
+	L5, L6, L7, L8, L9,
+	L10, L11, L12, L13, L14,
+	L15, L16, L17, L18, L19,
+	L20,
+};
+
+#define APLL_FREQ(f, a0, a1, a2, a3, a4, a5, a6, a7, b0, b1, b2, m, p, s) \
+	{ \
+		.freq = (f) * 1000, \
+		.clk_div_cpu0 = ((a0) | (a1) << 4 | (a2) << 8 | (a3) << 12 | \
+			(a4) << 16 | (a5) << 20 | (a6) << 24 | (a7) << 28), \
+		.clk_div_cpu1 = (b0 << 0 | b1 << 4 | b2 << 8), \
+		.mps = ((m) << 16 | (p) << 8 | (s)), \
+	}
+
+struct apll_freq {
+	unsigned int freq;
+	u32 clk_div_cpu0;
+	u32 clk_div_cpu1;
+	u32 mps;
+};
+
+struct exynos_dvfs_info {
+	unsigned long	mpll_freq_khz;
+	unsigned int	pll_safe_idx;
+	struct clk	*cpu_clk;
+	unsigned int	*volt_table;
+	struct cpufreq_frequency_table	*freq_table;
+	void (*set_freq)(unsigned int, unsigned int);
+	bool (*need_apll_change)(unsigned int, unsigned int);
+};
+
+extern int exynos4210_cpufreq_init(struct exynos_dvfs_info *);
+extern int exynos4x12_cpufreq_init(struct exynos_dvfs_info *);
+extern int exynos5250_cpufreq_init(struct exynos_dvfs_info *);
diff --git a/drivers/cpufreq/exynos4210-cpufreq.c b/drivers/cpufreq/exynos4210-cpufreq.c
index fb148fa27678..add7fbec4fc9 100644
--- a/drivers/cpufreq/exynos4210-cpufreq.c
+++ b/drivers/cpufreq/exynos4210-cpufreq.c
@@ -18,99 +18,40 @@
 #include <linux/cpufreq.h>
 
 #include <mach/regs-clock.h>
-#include <mach/cpufreq.h>
 
-#define CPUFREQ_LEVEL_END	L5
-
-static int max_support_idx = L0;
-static int min_support_idx = (CPUFREQ_LEVEL_END - 1);
+#include "exynos-cpufreq.h"
 
 static struct clk *cpu_clk;
 static struct clk *moutcore;
 static struct clk *mout_mpll;
 static struct clk *mout_apll;
 
-struct cpufreq_clkdiv {
-	unsigned int index;
-	unsigned int clkdiv;
-};
-
-static unsigned int exynos4210_volt_table[CPUFREQ_LEVEL_END] = {
+static unsigned int exynos4210_volt_table[] = {
 	1250000, 1150000, 1050000, 975000, 950000,
 };
 
-
-static struct cpufreq_clkdiv exynos4210_clkdiv_table[CPUFREQ_LEVEL_END];
-
 static struct cpufreq_frequency_table exynos4210_freq_table[] = {
-	{L0, 1200*1000},
-	{L1, 1000*1000},
-	{L2, 800*1000},
-	{L3, 500*1000},
-	{L4, 200*1000},
+	{L0, 1200 * 1000},
+	{L1, 1000 * 1000},
+	{L2,  800 * 1000},
+	{L3,  500 * 1000},
+	{L4,  200 * 1000},
 	{0, CPUFREQ_TABLE_END},
 };
 
-static unsigned int clkdiv_cpu0[CPUFREQ_LEVEL_END][7] = {
+static struct apll_freq apll_freq_4210[] = {
 	/*
-	 * Clock divider value for following
-	 * { DIVCORE, DIVCOREM0, DIVCOREM1, DIVPERIPH,
-	 *		DIVATB, DIVPCLK_DBG, DIVAPLL }
+	 * values:
+	 * freq
+	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, RESERVED
+	 * clock divider for COPY, HPM, RESERVED
+	 * PLL M, P, S
 	 */
-
-	/* ARM L0: 1200MHz */
-	{ 0, 3, 7, 3, 4, 1, 7 },
-
-	/* ARM L1: 1000MHz */
-	{ 0, 3, 7, 3, 4, 1, 7 },
-
-	/* ARM L2: 800MHz */
-	{ 0, 3, 7, 3, 3, 1, 7 },
-
-	/* ARM L3: 500MHz */
-	{ 0, 3, 7, 3, 3, 1, 7 },
-
-	/* ARM L4: 200MHz */
-	{ 0, 1, 3, 1, 3, 1, 0 },
-};
-
-static unsigned int clkdiv_cpu1[CPUFREQ_LEVEL_END][2] = {
-	/*
-	 * Clock divider value for following
-	 * { DIVCOPY, DIVHPM }
-	 */
-
-	/* ARM L0: 1200MHz */
-	{ 5, 0 },
-
-	/* ARM L1: 1000MHz */
-	{ 4, 0 },
-
-	/* ARM L2: 800MHz */
-	{ 3, 0 },
-
-	/* ARM L3: 500MHz */
-	{ 3, 0 },
-
-	/* ARM L4: 200MHz */
-	{ 3, 0 },
-};
-
-static unsigned int exynos4210_apll_pms_table[CPUFREQ_LEVEL_END] = {
-	/* APLL FOUT L0: 1200MHz */
-	((150 << 16) | (3 << 8) | 1),
-
-	/* APLL FOUT L1: 1000MHz */
-	((250 << 16) | (6 << 8) | 1),
-
-	/* APLL FOUT L2: 800MHz */
-	((200 << 16) | (6 << 8) | 1),
-
-	/* APLL FOUT L3: 500MHz */
-	((250 << 16) | (6 << 8) | 2),
-
-	/* APLL FOUT L4: 200MHz */
-	((200 << 16) | (6 << 8) | 3),
+	APLL_FREQ(1200, 0, 3, 7, 3, 4, 1, 7, 0, 5, 0, 0, 150, 3, 1),
+	APLL_FREQ(1000, 0, 3, 7, 3, 4, 1, 7, 0, 4, 0, 0, 250, 6, 1),
+	APLL_FREQ(800,  0, 3, 7, 3, 3, 1, 7, 0, 3, 0, 0, 200, 6, 1),
+	APLL_FREQ(500,  0, 3, 7, 3, 3, 1, 7, 0, 3, 0, 0, 250, 6, 2),
+	APLL_FREQ(200,  0, 1, 3, 1, 3, 1, 0, 0, 3, 0, 0, 200, 6, 3),
 };
 
 static void exynos4210_set_clkdiv(unsigned int div_index)
@@ -119,7 +60,7 @@ static void exynos4210_set_clkdiv(unsigned int div_index)
 
 	/* Change Divider - CPU0 */
 
-	tmp = exynos4210_clkdiv_table[div_index].clkdiv;
+	tmp = apll_freq_4210[div_index].clk_div_cpu0;
 
 	__raw_writel(tmp, EXYNOS4_CLKDIV_CPU);
 
@@ -129,12 +70,7 @@ static void exynos4210_set_clkdiv(unsigned int div_index)
 
 	/* Change Divider - CPU1 */
 
-	tmp = __raw_readl(EXYNOS4_CLKDIV_CPU1);
-
-	tmp &= ~((0x7 << 4) | 0x7);
-
-	tmp |= ((clkdiv_cpu1[div_index][0] << 4) |
-		(clkdiv_cpu1[div_index][1] << 0));
+	tmp = apll_freq_4210[div_index].clk_div_cpu1;
 
 	__raw_writel(tmp, EXYNOS4_CLKDIV_CPU1);
 
@@ -162,7 +98,7 @@ static void exynos4210_set_apll(unsigned int index)
 	/* 3. Change PLL PMS values */
 	tmp = __raw_readl(EXYNOS4_APLL_CON0);
 	tmp &= ~((0x3ff << 16) | (0x3f << 8) | (0x7 << 0));
-	tmp |= exynos4210_apll_pms_table[index];
+	tmp |= apll_freq_4210[index].mps;
 	__raw_writel(tmp, EXYNOS4_APLL_CON0);
 
 	/* 4. wait_lock_time */
@@ -179,10 +115,10 @@ static void exynos4210_set_apll(unsigned int index)
 	} while (tmp != (0x1 << EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT));
 }
 
-bool exynos4210_pms_change(unsigned int old_index, unsigned int new_index)
+static bool exynos4210_pms_change(unsigned int old_index, unsigned int new_index)
 {
-	unsigned int old_pm = (exynos4210_apll_pms_table[old_index] >> 8);
-	unsigned int new_pm = (exynos4210_apll_pms_table[new_index] >> 8);
+	unsigned int old_pm = apll_freq_4210[old_index].mps >> 8;
+	unsigned int new_pm = apll_freq_4210[new_index].mps >> 8;
 
 	return (old_pm == new_pm) ? 0 : 1;
 }
@@ -200,7 +136,7 @@ static void exynos4210_set_frequency(unsigned int old_index,
 			/* 2. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(EXYNOS4_APLL_CON0);
 			tmp &= ~(0x7 << 0);
-			tmp |= (exynos4210_apll_pms_table[new_index] & 0x7);
+			tmp |= apll_freq_4210[new_index].mps & 0x7;
 			__raw_writel(tmp, EXYNOS4_APLL_CON0);
 		} else {
 			/* Clock Configuration Procedure */
@@ -214,7 +150,7 @@ static void exynos4210_set_frequency(unsigned int old_index,
 			/* 1. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(EXYNOS4_APLL_CON0);
 			tmp &= ~(0x7 << 0);
-			tmp |= (exynos4210_apll_pms_table[new_index] & 0x7);
+			tmp |= apll_freq_4210[new_index].mps & 0x7;
 			__raw_writel(tmp, EXYNOS4_APLL_CON0);
 
 			/* 2. Change the system clock divider values */
@@ -231,8 +167,6 @@ static void exynos4210_set_frequency(unsigned int old_index,
 
 int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
 {
-	int i;
-	unsigned int tmp;
 	unsigned long rate;
 
 	cpu_clk = clk_get(NULL, "armclk");
@@ -253,33 +187,9 @@ int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
 	if (IS_ERR(mout_apll))
 		goto err_mout_apll;
 
-	tmp = __raw_readl(EXYNOS4_CLKDIV_CPU);
-
-	for (i = L0; i <  CPUFREQ_LEVEL_END; i++) {
-		tmp &= ~(EXYNOS4_CLKDIV_CPU0_CORE_MASK |
-			EXYNOS4_CLKDIV_CPU0_COREM0_MASK |
-			EXYNOS4_CLKDIV_CPU0_COREM1_MASK |
-			EXYNOS4_CLKDIV_CPU0_PERIPH_MASK |
-			EXYNOS4_CLKDIV_CPU0_ATB_MASK |
-			EXYNOS4_CLKDIV_CPU0_PCLKDBG_MASK |
-			EXYNOS4_CLKDIV_CPU0_APLL_MASK);
-
-		tmp |= ((clkdiv_cpu0[i][0] << EXYNOS4_CLKDIV_CPU0_CORE_SHIFT) |
-			(clkdiv_cpu0[i][1] << EXYNOS4_CLKDIV_CPU0_COREM0_SHIFT) |
-			(clkdiv_cpu0[i][2] << EXYNOS4_CLKDIV_CPU0_COREM1_SHIFT) |
-			(clkdiv_cpu0[i][3] << EXYNOS4_CLKDIV_CPU0_PERIPH_SHIFT) |
-			(clkdiv_cpu0[i][4] << EXYNOS4_CLKDIV_CPU0_ATB_SHIFT) |
-			(clkdiv_cpu0[i][5] << EXYNOS4_CLKDIV_CPU0_PCLKDBG_SHIFT) |
-			(clkdiv_cpu0[i][6] << EXYNOS4_CLKDIV_CPU0_APLL_SHIFT));
-
-		exynos4210_clkdiv_table[i].clkdiv = tmp;
-	}
-
 	info->mpll_freq_khz = rate;
-	info->pm_lock_idx = L2;
+	/* 800Mhz */
 	info->pll_safe_idx = L2;
-	info->max_support_idx = max_support_idx;
-	info->min_support_idx = min_support_idx;
 	info->cpu_clk = cpu_clk;
 	info->volt_table = exynos4210_volt_table;
 	info->freq_table = exynos4210_freq_table;
@@ -289,14 +199,11 @@ int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
 	return 0;
 
 err_mout_apll:
-	if (!IS_ERR(mout_mpll))
-		clk_put(mout_mpll);
+	clk_put(mout_mpll);
 err_mout_mpll:
-	if (!IS_ERR(moutcore))
-		clk_put(moutcore);
+	clk_put(moutcore);
 err_moutcore:
-	if (!IS_ERR(cpu_clk))
-		clk_put(cpu_clk);
+	clk_put(cpu_clk);
 
 	pr_debug("%s: failed initialization\n", __func__);
 	return -EINVAL;
diff --git a/drivers/cpufreq/exynos4x12-cpufreq.c b/drivers/cpufreq/exynos4x12-cpufreq.c
index 8c5a7afa5b0b..08b7477b0aa2 100644
--- a/drivers/cpufreq/exynos4x12-cpufreq.c
+++ b/drivers/cpufreq/exynos4x12-cpufreq.c
@@ -18,28 +18,21 @@
 #include <linux/cpufreq.h>
 
 #include <mach/regs-clock.h>
-#include <mach/cpufreq.h>
 
-#define CPUFREQ_LEVEL_END	(L13 + 1)
-
-static int max_support_idx;
-static int min_support_idx = (CPUFREQ_LEVEL_END - 1);
+#include "exynos-cpufreq.h"
 
 static struct clk *cpu_clk;
 static struct clk *moutcore;
 static struct clk *mout_mpll;
 static struct clk *mout_apll;
 
-struct cpufreq_clkdiv {
-	unsigned int	index;
-	unsigned int	clkdiv;
-	unsigned int	clkdiv1;
+static unsigned int exynos4x12_volt_table[] = {
+	1350000, 1287500, 1250000, 1187500, 1137500, 1087500, 1037500,
+	1000000,  987500,  975000,  950000,  925000,  900000,  900000
 };
 
-static unsigned int exynos4x12_volt_table[CPUFREQ_LEVEL_END];
-
 static struct cpufreq_frequency_table exynos4x12_freq_table[] = {
-	{L0, 1500 * 1000},
+	{L0, CPUFREQ_ENTRY_INVALID},
 	{L1, 1400 * 1000},
 	{L2, 1300 * 1000},
 	{L3, 1200 * 1000},
@@ -56,247 +49,54 @@ static struct cpufreq_frequency_table exynos4x12_freq_table[] = {
 	{0, CPUFREQ_TABLE_END},
 };
 
-static struct cpufreq_clkdiv exynos4x12_clkdiv_table[CPUFREQ_LEVEL_END];
+static struct apll_freq *apll_freq_4x12;
 
-static unsigned int clkdiv_cpu0_4212[CPUFREQ_LEVEL_END][8] = {
+static struct apll_freq apll_freq_4212[] = {
 	/*
-	 * Clock divider value for following
-	 * { DIVCORE, DIVCOREM0, DIVCOREM1, DIVPERIPH,
-	 *		DIVATB, DIVPCLK_DBG, DIVAPLL, DIVCORE2 }
+	 * values:
+	 * freq
+	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, CORE2
+	 * clock divider for COPY, HPM, RESERVED
+	 * PLL M, P, S
 	 */
-	/* ARM L0: 1500 MHz */
-	{ 0, 3, 7, 0, 6, 1, 2, 0 },
-
-	/* ARM L1: 1400 MHz */
-	{ 0, 3, 7, 0, 6, 1, 2, 0 },
-
-	/* ARM L2: 1300 MHz */
-	{ 0, 3, 7, 0, 5, 1, 2, 0 },
-
-	/* ARM L3: 1200 MHz */
-	{ 0, 3, 7, 0, 5, 1, 2, 0 },
-
-	/* ARM L4: 1100 MHz */
-	{ 0, 3, 6, 0, 4, 1, 2, 0 },
-
-	/* ARM L5: 1000 MHz */
-	{ 0, 2, 5, 0, 4, 1, 1, 0 },
-
-	/* ARM L6: 900 MHz */
-	{ 0, 2, 5, 0, 3, 1, 1, 0 },
-
-	/* ARM L7: 800 MHz */
-	{ 0, 2, 5, 0, 3, 1, 1, 0 },
-
-	/* ARM L8: 700 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L9: 600 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L10: 500 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L11: 400 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L12: 300 MHz */
-	{ 0, 2, 4, 0, 2, 1, 1, 0 },
-
-	/* ARM L13: 200 MHz */
-	{ 0, 1, 3, 0, 1, 1, 1, 0 },
+	APLL_FREQ(1500, 0, 3, 7, 0, 6, 1, 2, 0, 6, 2, 0, 250, 4, 0),
+	APLL_FREQ(1400, 0, 3, 7, 0, 6, 1, 2, 0, 6, 2, 0, 175, 3, 0),
+	APLL_FREQ(1300, 0, 3, 7, 0, 5, 1, 2, 0, 5, 2, 0, 325, 6, 0),
+	APLL_FREQ(1200, 0, 3, 7, 0, 5, 1, 2, 0, 5, 2, 0, 200, 4, 0),
+	APLL_FREQ(1100, 0, 3, 6, 0, 4, 1, 2, 0, 4, 2, 0, 275, 6, 0),
+	APLL_FREQ(1000, 0, 2, 5, 0, 4, 1, 1, 0, 4, 2, 0, 125, 3, 0),
+	APLL_FREQ(900,  0, 2, 5, 0, 3, 1, 1, 0, 3, 2, 0, 150, 4, 0),
+	APLL_FREQ(800,  0, 2, 5, 0, 3, 1, 1, 0, 3, 2, 0, 100, 3, 0),
+	APLL_FREQ(700,  0, 2, 4, 0, 3, 1, 1, 0, 3, 2, 0, 175, 3, 1),
+	APLL_FREQ(600,  0, 2, 4, 0, 3, 1, 1, 0, 3, 2, 0, 200, 4, 1),
+	APLL_FREQ(500,  0, 2, 4, 0, 3, 1, 1, 0, 3, 2, 0, 125, 3, 1),
+	APLL_FREQ(400,  0, 2, 4, 0, 3, 1, 1, 0, 3, 2, 0, 100, 3, 1),
+	APLL_FREQ(300,  0, 2, 4, 0, 2, 1, 1, 0, 3, 2, 0, 200, 4, 2),
+	APLL_FREQ(200,  0, 1, 3, 0, 1, 1, 1, 0, 3, 2, 0, 100, 3, 2),
 };
 
-static unsigned int clkdiv_cpu0_4412[CPUFREQ_LEVEL_END][8] = {
+static struct apll_freq apll_freq_4412[] = {
 	/*
-	 * Clock divider value for following
-	 * { DIVCORE, DIVCOREM0, DIVCOREM1, DIVPERIPH,
-	 *		DIVATB, DIVPCLK_DBG, DIVAPLL, DIVCORE2 }
-	 */
-	/* ARM L0: 1500 MHz */
-	{ 0, 3, 7, 0, 6, 1, 2, 0 },
-
-	/* ARM L1: 1400 MHz */
-	{ 0, 3, 7, 0, 6, 1, 2, 0 },
-
-	/* ARM L2: 1300 MHz */
-	{ 0, 3, 7, 0, 5, 1, 2, 0 },
-
-	/* ARM L3: 1200 MHz */
-	{ 0, 3, 7, 0, 5, 1, 2, 0 },
-
-	/* ARM L4: 1100 MHz */
-	{ 0, 3, 6, 0, 4, 1, 2, 0 },
-
-	/* ARM L5: 1000 MHz */
-	{ 0, 2, 5, 0, 4, 1, 1, 0 },
-
-	/* ARM L6: 900 MHz */
-	{ 0, 2, 5, 0, 3, 1, 1, 0 },
-
-	/* ARM L7: 800 MHz */
-	{ 0, 2, 5, 0, 3, 1, 1, 0 },
-
-	/* ARM L8: 700 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L9: 600 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L10: 500 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L11: 400 MHz */
-	{ 0, 2, 4, 0, 3, 1, 1, 0 },
-
-	/* ARM L12: 300 MHz */
-	{ 0, 2, 4, 0, 2, 1, 1, 0 },
-
-	/* ARM L13: 200 MHz */
-	{ 0, 1, 3, 0, 1, 1, 1, 0 },
-};
-
-static unsigned int clkdiv_cpu1_4212[CPUFREQ_LEVEL_END][2] = {
-	/* Clock divider value for following
-	 * { DIVCOPY, DIVHPM }
+	 * values:
+	 * freq
+	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, CORE2
+	 * clock divider for COPY, HPM, CORES
+	 * PLL M, P, S
 	 */
-	/* ARM L0: 1500 MHz */
-	{ 6, 0 },
-
-	/* ARM L1: 1400 MHz */
-	{ 6, 0 },
-
-	/* ARM L2: 1300 MHz */
-	{ 5, 0 },
-
-	/* ARM L3: 1200 MHz */
-	{ 5, 0 },
-
-	/* ARM L4: 1100 MHz */
-	{ 4, 0 },
-
-	/* ARM L5: 1000 MHz */
-	{ 4, 0 },
-
-	/* ARM L6: 900 MHz */
-	{ 3, 0 },
-
-	/* ARM L7: 800 MHz */
-	{ 3, 0 },
-
-	/* ARM L8: 700 MHz */
-	{ 3, 0 },
-
-	/* ARM L9: 600 MHz */
-	{ 3, 0 },
-
-	/* ARM L10: 500 MHz */
-	{ 3, 0 },
-
-	/* ARM L11: 400 MHz */
-	{ 3, 0 },
-
-	/* ARM L12: 300 MHz */
-	{ 3, 0 },
-
-	/* ARM L13: 200 MHz */
-	{ 3, 0 },
-};
-
-static unsigned int clkdiv_cpu1_4412[CPUFREQ_LEVEL_END][3] = {
-	/* Clock divider value for following
-	 * { DIVCOPY, DIVHPM, DIVCORES }
-	 */
-	/* ARM L0: 1500 MHz */
-	{ 6, 0, 7 },
-
-	/* ARM L1: 1400 MHz */
-	{ 6, 0, 6 },
-
-	/* ARM L2: 1300 MHz */
-	{ 5, 0, 6 },
-
-	/* ARM L3: 1200 MHz */
-	{ 5, 0, 5 },
-
-	/* ARM L4: 1100 MHz */
-	{ 4, 0, 5 },
-
-	/* ARM L5: 1000 MHz */
-	{ 4, 0, 4 },
-
-	/* ARM L6: 900 MHz */
-	{ 3, 0, 4 },
-
-	/* ARM L7: 800 MHz */
-	{ 3, 0, 3 },
-
-	/* ARM L8: 700 MHz */
-	{ 3, 0, 3 },
-
-	/* ARM L9: 600 MHz */
-	{ 3, 0, 2 },
-
-	/* ARM L10: 500 MHz */
-	{ 3, 0, 2 },
-
-	/* ARM L11: 400 MHz */
-	{ 3, 0, 1 },
-
-	/* ARM L12: 300 MHz */
-	{ 3, 0, 1 },
-
-	/* ARM L13: 200 MHz */
-	{ 3, 0, 0 },
-};
-
-static unsigned int exynos4x12_apll_pms_table[CPUFREQ_LEVEL_END] = {
-	/* APLL FOUT L0: 1500 MHz */
-	((250 << 16) | (4 << 8) | (0x0)),
-
-	/* APLL FOUT L1: 1400 MHz */
-	((175 << 16) | (3 << 8) | (0x0)),
-
-	/* APLL FOUT L2: 1300 MHz */
-	((325 << 16) | (6 << 8) | (0x0)),
-
-	/* APLL FOUT L3: 1200 MHz */
-	((200 << 16) | (4 << 8) | (0x0)),
-
-	/* APLL FOUT L4: 1100 MHz */
-	((275 << 16) | (6 << 8) | (0x0)),
-
-	/* APLL FOUT L5: 1000 MHz */
-	((125 << 16) | (3 << 8) | (0x0)),
-
-	/* APLL FOUT L6: 900 MHz */
-	((150 << 16) | (4 << 8) | (0x0)),
-
-	/* APLL FOUT L7: 800 MHz */
-	((100 << 16) | (3 << 8) | (0x0)),
-
-	/* APLL FOUT L8: 700 MHz */
-	((175 << 16) | (3 << 8) | (0x1)),
-
-	/* APLL FOUT L9: 600 MHz */
-	((200 << 16) | (4 << 8) | (0x1)),
-
-	/* APLL FOUT L10: 500 MHz */
-	((125 << 16) | (3 << 8) | (0x1)),
-
-	/* APLL FOUT L11 400 MHz */
-	((100 << 16) | (3 << 8) | (0x1)),
-
-	/* APLL FOUT L12: 300 MHz */
-	((200 << 16) | (4 << 8) | (0x2)),
-
-	/* APLL FOUT L13: 200 MHz */
-	((100 << 16) | (3 << 8) | (0x2)),
-};
-
-static const unsigned int asv_voltage_4x12[CPUFREQ_LEVEL_END] = {
-	1350000, 1287500, 1250000, 1187500, 1137500, 1087500, 1037500,
-	1000000,  987500,  975000,  950000,  925000,  900000,  900000
+	APLL_FREQ(1500, 0, 3, 7, 0, 6, 1, 2, 0, 6, 0, 7, 250, 4, 0),
+	APLL_FREQ(1400, 0, 3, 7, 0, 6, 1, 2, 0, 6, 0, 6, 175, 3, 0),
+	APLL_FREQ(1300, 0, 3, 7, 0, 5, 1, 2, 0, 5, 0, 6, 325, 6, 0),
+	APLL_FREQ(1200, 0, 3, 7, 0, 5, 1, 2, 0, 5, 0, 5, 200, 4, 0),
+	APLL_FREQ(1100, 0, 3, 6, 0, 4, 1, 2, 0, 4, 0, 5, 275, 6, 0),
+	APLL_FREQ(1000, 0, 2, 5, 0, 4, 1, 1, 0, 4, 0, 4, 125, 3, 0),
+	APLL_FREQ(900,  0, 2, 5, 0, 3, 1, 1, 0, 3, 0, 4, 150, 4, 0),
+	APLL_FREQ(800,  0, 2, 5, 0, 3, 1, 1, 0, 3, 0, 3, 100, 3, 0),
+	APLL_FREQ(700,  0, 2, 4, 0, 3, 1, 1, 0, 3, 0, 3, 175, 3, 1),
+	APLL_FREQ(600,  0, 2, 4, 0, 3, 1, 1, 0, 3, 0, 2, 200, 4, 1),
+	APLL_FREQ(500,  0, 2, 4, 0, 3, 1, 1, 0, 3, 0, 2, 125, 3, 1),
+	APLL_FREQ(400,  0, 2, 4, 0, 3, 1, 1, 0, 3, 0, 1, 100, 3, 1),
+	APLL_FREQ(300,  0, 2, 4, 0, 2, 1, 1, 0, 3, 0, 1, 200, 4, 2),
+	APLL_FREQ(200,  0, 1, 3, 0, 1, 1, 1, 0, 3, 0, 0, 100, 3, 2),
 };
 
 static void exynos4x12_set_clkdiv(unsigned int div_index)
@@ -306,7 +106,7 @@ static void exynos4x12_set_clkdiv(unsigned int div_index)
 
 	/* Change Divider - CPU0 */
 
-	tmp = exynos4x12_clkdiv_table[div_index].clkdiv;
+	tmp = apll_freq_4x12[div_index].clk_div_cpu0;
 
 	__raw_writel(tmp, EXYNOS4_CLKDIV_CPU);
 
@@ -314,7 +114,7 @@ static void exynos4x12_set_clkdiv(unsigned int div_index)
 		cpu_relax();
 
 	/* Change Divider - CPU1 */
-	tmp = exynos4x12_clkdiv_table[div_index].clkdiv1;
+	tmp = apll_freq_4x12[div_index].clk_div_cpu1;
 
 	__raw_writel(tmp, EXYNOS4_CLKDIV_CPU1);
 	if (soc_is_exynos4212())
@@ -341,14 +141,14 @@ static void exynos4x12_set_apll(unsigned int index)
 	} while (tmp != 0x2);
 
 	/* 2. Set APLL Lock time */
-	pdiv = ((exynos4x12_apll_pms_table[index] >> 8) & 0x3f);
+	pdiv = ((apll_freq_4x12[index].mps >> 8) & 0x3f);
 
 	__raw_writel((pdiv * 250), EXYNOS4_APLL_LOCK);
 
 	/* 3. Change PLL PMS values */
 	tmp = __raw_readl(EXYNOS4_APLL_CON0);
 	tmp &= ~((0x3ff << 16) | (0x3f << 8) | (0x7 << 0));
-	tmp |= exynos4x12_apll_pms_table[index];
+	tmp |= apll_freq_4x12[index].mps;
 	__raw_writel(tmp, EXYNOS4_APLL_CON0);
 
 	/* 4. wait_lock_time */
@@ -367,10 +167,10 @@ static void exynos4x12_set_apll(unsigned int index)
 	} while (tmp != (0x1 << EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT));
 }
 
-bool exynos4x12_pms_change(unsigned int old_index, unsigned int new_index)
+static bool exynos4x12_pms_change(unsigned int old_index, unsigned int new_index)
 {
-	unsigned int old_pm = exynos4x12_apll_pms_table[old_index] >> 8;
-	unsigned int new_pm = exynos4x12_apll_pms_table[new_index] >> 8;
+	unsigned int old_pm = apll_freq_4x12[old_index].mps >> 8;
+	unsigned int new_pm = apll_freq_4x12[new_index].mps >> 8;
 
 	return (old_pm == new_pm) ? 0 : 1;
 }
@@ -387,7 +187,7 @@ static void exynos4x12_set_frequency(unsigned int old_index,
 			/* 2. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(EXYNOS4_APLL_CON0);
 			tmp &= ~(0x7 << 0);
-			tmp |= (exynos4x12_apll_pms_table[new_index] & 0x7);
+			tmp |= apll_freq_4x12[new_index].mps & 0x7;
 			__raw_writel(tmp, EXYNOS4_APLL_CON0);
 
 		} else {
@@ -402,7 +202,7 @@ static void exynos4x12_set_frequency(unsigned int old_index,
 			/* 1. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(EXYNOS4_APLL_CON0);
 			tmp &= ~(0x7 << 0);
-			tmp |= (exynos4x12_apll_pms_table[new_index] & 0x7);
+			tmp |= apll_freq_4x12[new_index].mps & 0x7;
 			__raw_writel(tmp, EXYNOS4_APLL_CON0);
 			/* 2. Change the system clock divider values */
 			exynos4x12_set_clkdiv(new_index);
@@ -416,27 +216,10 @@ static void exynos4x12_set_frequency(unsigned int old_index,
 	}
 }
 
-static void __init set_volt_table(void)
-{
-	unsigned int i;
-
-	max_support_idx = L1;
-
-	/* Not supported */
-	exynos4x12_freq_table[L0].frequency = CPUFREQ_ENTRY_INVALID;
-
-	for (i = 0 ; i < CPUFREQ_LEVEL_END ; i++)
-		exynos4x12_volt_table[i] = asv_voltage_4x12[i];
-}
-
 int exynos4x12_cpufreq_init(struct exynos_dvfs_info *info)
 {
-	int i;
-	unsigned int tmp;
 	unsigned long rate;
 
-	set_volt_table();
-
 	cpu_clk = clk_get(NULL, "armclk");
 	if (IS_ERR(cpu_clk))
 		return PTR_ERR(cpu_clk);
@@ -455,66 +238,14 @@ int exynos4x12_cpufreq_init(struct exynos_dvfs_info *info)
 	if (IS_ERR(mout_apll))
 		goto err_mout_apll;
 
-	for (i = L0; i <  CPUFREQ_LEVEL_END; i++) {
-
-		exynos4x12_clkdiv_table[i].index = i;
-
-		tmp = __raw_readl(EXYNOS4_CLKDIV_CPU);
-
-		tmp &= ~(EXYNOS4_CLKDIV_CPU0_CORE_MASK |
-			EXYNOS4_CLKDIV_CPU0_COREM0_MASK |
-			EXYNOS4_CLKDIV_CPU0_COREM1_MASK |
-			EXYNOS4_CLKDIV_CPU0_PERIPH_MASK |
-			EXYNOS4_CLKDIV_CPU0_ATB_MASK |
-			EXYNOS4_CLKDIV_CPU0_PCLKDBG_MASK |
-			EXYNOS4_CLKDIV_CPU0_APLL_MASK);
-
-		if (soc_is_exynos4212()) {
-			tmp |= ((clkdiv_cpu0_4212[i][0] << EXYNOS4_CLKDIV_CPU0_CORE_SHIFT) |
-				(clkdiv_cpu0_4212[i][1] << EXYNOS4_CLKDIV_CPU0_COREM0_SHIFT) |
-				(clkdiv_cpu0_4212[i][2] << EXYNOS4_CLKDIV_CPU0_COREM1_SHIFT) |
-				(clkdiv_cpu0_4212[i][3] << EXYNOS4_CLKDIV_CPU0_PERIPH_SHIFT) |
-				(clkdiv_cpu0_4212[i][4] << EXYNOS4_CLKDIV_CPU0_ATB_SHIFT) |
-				(clkdiv_cpu0_4212[i][5] << EXYNOS4_CLKDIV_CPU0_PCLKDBG_SHIFT) |
-				(clkdiv_cpu0_4212[i][6] << EXYNOS4_CLKDIV_CPU0_APLL_SHIFT));
-		} else {
-			tmp &= ~EXYNOS4_CLKDIV_CPU0_CORE2_MASK;
-
-			tmp |= ((clkdiv_cpu0_4412[i][0] << EXYNOS4_CLKDIV_CPU0_CORE_SHIFT) |
-				(clkdiv_cpu0_4412[i][1] << EXYNOS4_CLKDIV_CPU0_COREM0_SHIFT) |
-				(clkdiv_cpu0_4412[i][2] << EXYNOS4_CLKDIV_CPU0_COREM1_SHIFT) |
-				(clkdiv_cpu0_4412[i][3] << EXYNOS4_CLKDIV_CPU0_PERIPH_SHIFT) |
-				(clkdiv_cpu0_4412[i][4] << EXYNOS4_CLKDIV_CPU0_ATB_SHIFT) |
-				(clkdiv_cpu0_4412[i][5] << EXYNOS4_CLKDIV_CPU0_PCLKDBG_SHIFT) |
-				(clkdiv_cpu0_4412[i][6] << EXYNOS4_CLKDIV_CPU0_APLL_SHIFT) |
-				(clkdiv_cpu0_4412[i][7] << EXYNOS4_CLKDIV_CPU0_CORE2_SHIFT));
-		}
-
-		exynos4x12_clkdiv_table[i].clkdiv = tmp;
-
-		tmp = __raw_readl(EXYNOS4_CLKDIV_CPU1);
-
-		if (soc_is_exynos4212()) {
-			tmp &= ~(EXYNOS4_CLKDIV_CPU1_COPY_MASK |
-				EXYNOS4_CLKDIV_CPU1_HPM_MASK);
-			tmp |= ((clkdiv_cpu1_4212[i][0] << EXYNOS4_CLKDIV_CPU1_COPY_SHIFT) |
-				(clkdiv_cpu1_4212[i][1] << EXYNOS4_CLKDIV_CPU1_HPM_SHIFT));
-		} else {
-			tmp &= ~(EXYNOS4_CLKDIV_CPU1_COPY_MASK |
-				EXYNOS4_CLKDIV_CPU1_HPM_MASK |
-				EXYNOS4_CLKDIV_CPU1_CORES_MASK);
-			tmp |= ((clkdiv_cpu1_4412[i][0] << EXYNOS4_CLKDIV_CPU1_COPY_SHIFT) |
-				(clkdiv_cpu1_4412[i][1] << EXYNOS4_CLKDIV_CPU1_HPM_SHIFT) |
-				(clkdiv_cpu1_4412[i][2] << EXYNOS4_CLKDIV_CPU1_CORES_SHIFT));
-		}
-		exynos4x12_clkdiv_table[i].clkdiv1 = tmp;
-	}
+	if (soc_is_exynos4212())
+		apll_freq_4x12 = apll_freq_4212;
+	else
+		apll_freq_4x12 = apll_freq_4412;
 
 	info->mpll_freq_khz = rate;
-	info->pm_lock_idx = L5;
+	/* 800Mhz */
 	info->pll_safe_idx = L7;
-	info->max_support_idx = max_support_idx;
-	info->min_support_idx = min_support_idx;
 	info->cpu_clk = cpu_clk;
 	info->volt_table = exynos4x12_volt_table;
 	info->freq_table = exynos4x12_freq_table;
diff --git a/drivers/cpufreq/exynos5250-cpufreq.c b/drivers/cpufreq/exynos5250-cpufreq.c
index e64c253cb169..9fae466d7746 100644
--- a/drivers/cpufreq/exynos5250-cpufreq.c
+++ b/drivers/cpufreq/exynos5250-cpufreq.c
@@ -19,25 +19,21 @@
 
 #include <mach/map.h>
 #include <mach/regs-clock.h>
-#include <mach/cpufreq.h>
 
-#define CPUFREQ_LEVEL_END	(L15 + 1)
+#include "exynos-cpufreq.h"
 
-static int max_support_idx;
-static int min_support_idx = (CPUFREQ_LEVEL_END - 1);
 static struct clk *cpu_clk;
 static struct clk *moutcore;
 static struct clk *mout_mpll;
 static struct clk *mout_apll;
 
-struct cpufreq_clkdiv {
-	unsigned int	index;
-	unsigned int	clkdiv;
-	unsigned int	clkdiv1;
+static unsigned int exynos5250_volt_table[] = {
+	1300000, 1250000, 1225000, 1200000, 1150000,
+	1125000, 1100000, 1075000, 1050000, 1025000,
+	1012500, 1000000,  975000,  950000,  937500,
+	925000
 };
 
-static unsigned int exynos5250_volt_table[CPUFREQ_LEVEL_END];
-
 static struct cpufreq_frequency_table exynos5250_freq_table[] = {
 	{L0, 1700 * 1000},
 	{L1, 1600 * 1000},
@@ -47,8 +43,8 @@ static struct cpufreq_frequency_table exynos5250_freq_table[] = {
 	{L5, 1200 * 1000},
 	{L6, 1100 * 1000},
 	{L7, 1000 * 1000},
-	{L8, 900 * 1000},
-	{L9, 800 * 1000},
+	{L8,  900 * 1000},
+	{L9,  800 * 1000},
 	{L10, 700 * 1000},
 	{L11, 600 * 1000},
 	{L12, 500 * 1000},
@@ -58,78 +54,30 @@ static struct cpufreq_frequency_table exynos5250_freq_table[] = {
 	{0, CPUFREQ_TABLE_END},
 };
 
-static struct cpufreq_clkdiv exynos5250_clkdiv_table[CPUFREQ_LEVEL_END];
-
-static unsigned int clkdiv_cpu0_5250[CPUFREQ_LEVEL_END][8] = {
+static struct apll_freq apll_freq_5250[] = {
 	/*
-	 * Clock divider value for following
-	 * { ARM, CPUD, ACP, PERIPH, ATB, PCLK_DBG, APLL, ARM2 }
-	 */
-	{ 0, 3, 7, 7, 7, 3, 5, 0 },	/* 1700 MHz */
-	{ 0, 3, 7, 7, 7, 1, 4, 0 },	/* 1600 MHz */
-	{ 0, 2, 7, 7, 7, 1, 4, 0 },	/* 1500 MHz */
-	{ 0, 2, 7, 7, 6, 1, 4, 0 },	/* 1400 MHz */
-	{ 0, 2, 7, 7, 6, 1, 3, 0 },	/* 1300 MHz */
-	{ 0, 2, 7, 7, 5, 1, 3, 0 },	/* 1200 MHz */
-	{ 0, 3, 7, 7, 5, 1, 3, 0 },	/* 1100 MHz */
-	{ 0, 1, 7, 7, 4, 1, 2, 0 },	/* 1000 MHz */
-	{ 0, 1, 7, 7, 4, 1, 2, 0 },	/* 900 MHz */
-	{ 0, 1, 7, 7, 4, 1, 2, 0 },	/* 800 MHz */
-	{ 0, 1, 7, 7, 3, 1, 1, 0 },	/* 700 MHz */
-	{ 0, 1, 7, 7, 3, 1, 1, 0 },	/* 600 MHz */
-	{ 0, 1, 7, 7, 2, 1, 1, 0 },	/* 500 MHz */
-	{ 0, 1, 7, 7, 2, 1, 1, 0 },	/* 400 MHz */
-	{ 0, 1, 7, 7, 1, 1, 1, 0 },	/* 300 MHz */
-	{ 0, 1, 7, 7, 1, 1, 1, 0 },	/* 200 MHz */
-};
-
-static unsigned int clkdiv_cpu1_5250[CPUFREQ_LEVEL_END][2] = {
-	/* Clock divider value for following
-	 * { COPY, HPM }
+	 * values:
+	 * freq
+	 * clock divider for ARM, CPUD, ACP, PERIPH, ATB, PCLK_DBG, APLL, ARM2
+	 * clock divider for COPY, HPM, RESERVED
+	 * PLL M, P, S
 	 */
-	{ 0, 2 },	/* 1700 MHz */
-	{ 0, 2 },	/* 1600 MHz */
-	{ 0, 2 },	/* 1500 MHz */
-	{ 0, 2 },	/* 1400 MHz */
-	{ 0, 2 },	/* 1300 MHz */
-	{ 0, 2 },	/* 1200 MHz */
-	{ 0, 2 },	/* 1100 MHz */
-	{ 0, 2 },	/* 1000 MHz */
-	{ 0, 2 },	/* 900 MHz */
-	{ 0, 2 },	/* 800 MHz */
-	{ 0, 2 },	/* 700 MHz */
-	{ 0, 2 },	/* 600 MHz */
-	{ 0, 2 },	/* 500 MHz */
-	{ 0, 2 },	/* 400 MHz */
-	{ 0, 2 },	/* 300 MHz */
-	{ 0, 2 },	/* 200 MHz */
-};
-
-static unsigned int exynos5_apll_pms_table[CPUFREQ_LEVEL_END] = {
-	((425 << 16) | (6 << 8) | 0),	/* 1700 MHz */
-	((200 << 16) | (3 << 8) | 0),	/* 1600 MHz */
-	((250 << 16) | (4 << 8) | 0),	/* 1500 MHz */
-	((175 << 16) | (3 << 8) | 0),	/* 1400 MHz */
-	((325 << 16) | (6 << 8) | 0),	/* 1300 MHz */
-	((200 << 16) | (4 << 8) | 0),	/* 1200 MHz */
-	((275 << 16) | (6 << 8) | 0),	/* 1100 MHz */
-	((125 << 16) | (3 << 8) | 0),	/* 1000 MHz */
-	((150 << 16) | (4 << 8) | 0),	/* 900 MHz */
-	((100 << 16) | (3 << 8) | 0),	/* 800 MHz */
-	((175 << 16) | (3 << 8) | 1),	/* 700 MHz */
-	((200 << 16) | (4 << 8) | 1),	/* 600 MHz */
-	((125 << 16) | (3 << 8) | 1),	/* 500 MHz */
-	((100 << 16) | (3 << 8) | 1),	/* 400 MHz */
-	((200 << 16) | (4 << 8) | 2),	/* 300 MHz */
-	((100 << 16) | (3 << 8) | 2),	/* 200 MHz */
-};
-
-/* ASV group voltage table */
-static const unsigned int asv_voltage_5250[CPUFREQ_LEVEL_END] = {
-	1300000, 1250000, 1225000, 1200000, 1150000,
-	1125000, 1100000, 1075000, 1050000, 1025000,
-	1012500, 1000000,  975000,  950000,  937500,
-	925000
+	APLL_FREQ(1700, 0, 3, 7, 7, 7, 3, 5, 0, 0, 2, 0, 425, 6, 0),
+	APLL_FREQ(1600, 0, 3, 7, 7, 7, 1, 4, 0, 0, 2, 0, 200, 3, 0),
+	APLL_FREQ(1500, 0, 2, 7, 7, 7, 1, 4, 0, 0, 2, 0, 250, 4, 0),
+	APLL_FREQ(1400, 0, 2, 7, 7, 6, 1, 4, 0, 0, 2, 0, 175, 3, 0),
+	APLL_FREQ(1300, 0, 2, 7, 7, 6, 1, 3, 0, 0, 2, 0, 325, 6, 0),
+	APLL_FREQ(1200, 0, 2, 7, 7, 5, 1, 3, 0, 0, 2, 0, 200, 4, 0),
+	APLL_FREQ(1100, 0, 3, 7, 7, 5, 1, 3, 0, 0, 2, 0, 275, 6, 0),
+	APLL_FREQ(1000, 0, 1, 7, 7, 4, 1, 2, 0, 0, 2, 0, 125, 3, 0),
+	APLL_FREQ(900,  0, 1, 7, 7, 4, 1, 2, 0, 0, 2, 0, 150, 4, 0),
+	APLL_FREQ(800,  0, 1, 7, 7, 4, 1, 2, 0, 0, 2, 0, 100, 3, 0),
+	APLL_FREQ(700,  0, 1, 7, 7, 3, 1, 1, 0, 0, 2, 0, 175, 3, 1),
+	APLL_FREQ(600,  0, 1, 7, 7, 3, 1, 1, 0, 0, 2, 0, 200, 4, 1),
+	APLL_FREQ(500,  0, 1, 7, 7, 2, 1, 1, 0, 0, 2, 0, 125, 3, 1),
+	APLL_FREQ(400,  0, 1, 7, 7, 2, 1, 1, 0, 0, 2, 0, 100, 3, 1),
+	APLL_FREQ(300,  0, 1, 7, 7, 1, 1, 1, 0, 0, 2, 0, 200, 4, 2),
+	APLL_FREQ(200,  0, 1, 7, 7, 1, 1, 1, 0, 0, 2, 0, 100, 3, 2),
 };
 
 static void set_clkdiv(unsigned int div_index)
@@ -138,7 +86,7 @@ static void set_clkdiv(unsigned int div_index)
 
 	/* Change Divider - CPU0 */
 
-	tmp = exynos5250_clkdiv_table[div_index].clkdiv;
+	tmp = apll_freq_5250[div_index].clk_div_cpu0;
 
 	__raw_writel(tmp, EXYNOS5_CLKDIV_CPU0);
 
@@ -146,7 +94,7 @@ static void set_clkdiv(unsigned int div_index)
 		cpu_relax();
 
 	/* Change Divider - CPU1 */
-	tmp = exynos5250_clkdiv_table[div_index].clkdiv1;
+	tmp = apll_freq_5250[div_index].clk_div_cpu1;
 
 	__raw_writel(tmp, EXYNOS5_CLKDIV_CPU1);
 
@@ -169,14 +117,14 @@ static void set_apll(unsigned int new_index,
 	} while (tmp != 0x2);
 
 	/* 2. Set APLL Lock time */
-	pdiv = ((exynos5_apll_pms_table[new_index] >> 8) & 0x3f);
+	pdiv = ((apll_freq_5250[new_index].mps >> 8) & 0x3f);
 
 	__raw_writel((pdiv * 250), EXYNOS5_APLL_LOCK);
 
 	/* 3. Change PLL PMS values */
 	tmp = __raw_readl(EXYNOS5_APLL_CON0);
 	tmp &= ~((0x3ff << 16) | (0x3f << 8) | (0x7 << 0));
-	tmp |= exynos5_apll_pms_table[new_index];
+	tmp |= apll_freq_5250[new_index].mps;
 	__raw_writel(tmp, EXYNOS5_APLL_CON0);
 
 	/* 4. wait_lock_time */
@@ -196,10 +144,10 @@ static void set_apll(unsigned int new_index,
 
 }
 
-bool exynos5250_pms_change(unsigned int old_index, unsigned int new_index)
+static bool exynos5250_pms_change(unsigned int old_index, unsigned int new_index)
 {
-	unsigned int old_pm = (exynos5_apll_pms_table[old_index] >> 8);
-	unsigned int new_pm = (exynos5_apll_pms_table[new_index] >> 8);
+	unsigned int old_pm = apll_freq_5250[old_index].mps >> 8;
+	unsigned int new_pm = apll_freq_5250[new_index].mps >> 8;
 
 	return (old_pm == new_pm) ? 0 : 1;
 }
@@ -216,7 +164,7 @@ static void exynos5250_set_frequency(unsigned int old_index,
 			/* 2. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(EXYNOS5_APLL_CON0);
 			tmp &= ~(0x7 << 0);
-			tmp |= (exynos5_apll_pms_table[new_index] & 0x7);
+			tmp |= apll_freq_5250[new_index].mps & 0x7;
 			__raw_writel(tmp, EXYNOS5_APLL_CON0);
 
 		} else {
@@ -231,7 +179,7 @@ static void exynos5250_set_frequency(unsigned int old_index,
 			/* 1. Change just s value in apll m,p,s value */
 			tmp = __raw_readl(EXYNOS5_APLL_CON0);
 			tmp &= ~(0x7 << 0);
-			tmp |= (exynos5_apll_pms_table[new_index] & 0x7);
+			tmp |= apll_freq_5250[new_index].mps & 0x7;
 			__raw_writel(tmp, EXYNOS5_APLL_CON0);
 			/* 2. Change the system clock divider values */
 			set_clkdiv(new_index);
@@ -245,24 +193,10 @@ static void exynos5250_set_frequency(unsigned int old_index,
 	}
 }
 
-static void __init set_volt_table(void)
-{
-	unsigned int i;
-
-	max_support_idx = L0;
-
-	for (i = 0 ; i < CPUFREQ_LEVEL_END ; i++)
-		exynos5250_volt_table[i] = asv_voltage_5250[i];
-}
-
 int exynos5250_cpufreq_init(struct exynos_dvfs_info *info)
 {
-	int i;
-	unsigned int tmp;
 	unsigned long rate;
 
-	set_volt_table();
-
 	cpu_clk = clk_get(NULL, "armclk");
 	if (IS_ERR(cpu_clk))
 		return PTR_ERR(cpu_clk);
@@ -281,44 +215,9 @@ int exynos5250_cpufreq_init(struct exynos_dvfs_info *info)
 	if (IS_ERR(mout_apll))
 		goto err_mout_apll;
 
-	for (i = L0; i < CPUFREQ_LEVEL_END; i++) {
-
-		exynos5250_clkdiv_table[i].index = i;
-
-		tmp = __raw_readl(EXYNOS5_CLKDIV_CPU0);
-
-		tmp &= ~((0x7 << 0) | (0x7 << 4) | (0x7 << 8) |
-			(0x7 << 12) | (0x7 << 16) | (0x7 << 20) |
-			(0x7 << 24) | (0x7 << 28));
-
-		tmp |= ((clkdiv_cpu0_5250[i][0] << 0) |
-			(clkdiv_cpu0_5250[i][1] << 4) |
-			(clkdiv_cpu0_5250[i][2] << 8) |
-			(clkdiv_cpu0_5250[i][3] << 12) |
-			(clkdiv_cpu0_5250[i][4] << 16) |
-			(clkdiv_cpu0_5250[i][5] << 20) |
-			(clkdiv_cpu0_5250[i][6] << 24) |
-			(clkdiv_cpu0_5250[i][7] << 28));
-
-		exynos5250_clkdiv_table[i].clkdiv = tmp;
-
-		tmp = __raw_readl(EXYNOS5_CLKDIV_CPU1);
-
-		tmp &= ~((0x7 << 0) | (0x7 << 4));
-
-		tmp |= ((clkdiv_cpu1_5250[i][0] << 0) |
-			(clkdiv_cpu1_5250[i][1] << 4));
-
-		exynos5250_clkdiv_table[i].clkdiv1 = tmp;
-	}
-
 	info->mpll_freq_khz = rate;
-	/* 1000Mhz */
-	info->pm_lock_idx = L7;
 	/* 800Mhz */
 	info->pll_safe_idx = L9;
-	info->max_support_idx = max_support_idx;
-	info->min_support_idx = min_support_idx;
 	info->cpu_clk = cpu_clk;
 	info->volt_table = exynos5250_volt_table;
 	info->freq_table = exynos5250_freq_table;
diff --git a/drivers/cpufreq/freq_table.c b/drivers/cpufreq/freq_table.c
index 90431cb92804..d7a79662e24c 100644
--- a/drivers/cpufreq/freq_table.c
+++ b/drivers/cpufreq/freq_table.c
@@ -9,6 +9,8 @@
  *
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -61,9 +63,6 @@ int cpufreq_frequency_table_verify(struct cpufreq_policy *policy,
 	pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n",
 					policy->min, policy->max, policy->cpu);
 
-	if (!cpu_online(policy->cpu))
-		return -EINVAL;
-
 	cpufreq_verify_within_limits(policy, policy->cpuinfo.min_freq,
 				     policy->cpuinfo.max_freq);
 
@@ -119,9 +118,6 @@ int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 		break;
 	}
 
-	if (!cpu_online(policy->cpu))
-		return -EINVAL;
-
 	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
 		unsigned int freq = table[i].frequency;
 		if (freq == CPUFREQ_ENTRY_INVALID)
@@ -225,6 +221,15 @@ 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);
diff --git a/drivers/cpufreq/highbank-cpufreq.c b/drivers/cpufreq/highbank-cpufreq.c
new file mode 100644
index 000000000000..b61b5a3fad64
--- /dev/null
+++ b/drivers/cpufreq/highbank-cpufreq.c
@@ -0,0 +1,114 @@
+/*
+ * Copyright (C) 2012 Calxeda, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This driver provides the clk notifier callbacks that are used when
+ * the cpufreq-cpu0 driver changes to frequency to alert the highbank
+ * EnergyCore Management Engine (ECME) about the need to change
+ * voltage. The ECME interfaces with the actual voltage regulators.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/of.h>
+#include <linux/mailbox.h>
+#include <linux/platform_device.h>
+
+#define HB_CPUFREQ_CHANGE_NOTE	0x80000001
+#define HB_CPUFREQ_IPC_LEN	7
+#define HB_CPUFREQ_VOLT_RETRIES	15
+
+static int hb_voltage_change(unsigned int freq)
+{
+	u32 msg[HB_CPUFREQ_IPC_LEN] = {HB_CPUFREQ_CHANGE_NOTE, freq / 1000000};
+
+	return pl320_ipc_transmit(msg);
+}
+
+static int hb_cpufreq_clk_notify(struct notifier_block *nb,
+				unsigned long action, void *hclk)
+{
+	struct clk_notifier_data *clk_data = hclk;
+	int i = 0;
+
+	if (action == PRE_RATE_CHANGE) {
+		if (clk_data->new_rate > clk_data->old_rate)
+			while (hb_voltage_change(clk_data->new_rate))
+				if (i++ > HB_CPUFREQ_VOLT_RETRIES)
+					return NOTIFY_BAD;
+	} else if (action == POST_RATE_CHANGE) {
+		if (clk_data->new_rate < clk_data->old_rate)
+			while (hb_voltage_change(clk_data->new_rate))
+				if (i++ > HB_CPUFREQ_VOLT_RETRIES)
+					return NOTIFY_BAD;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block hb_cpufreq_clk_nb = {
+	.notifier_call = hb_cpufreq_clk_notify,
+};
+
+static int hb_cpufreq_driver_init(void)
+{
+	struct platform_device_info devinfo = { .name = "cpufreq-cpu0", };
+	struct device *cpu_dev;
+	struct clk *cpu_clk;
+	struct device_node *np;
+	int ret;
+
+	if (!of_machine_is_compatible("calxeda,highbank"))
+		return -ENODEV;
+
+	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 highbank cpufreq node\n");
+		return -ENOENT;
+	}
+
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev) {
+		pr_err("failed to get highbank cpufreq device\n");
+		ret = -ENODEV;
+		goto out_put_node;
+	}
+
+	cpu_dev->of_node = np;
+
+	cpu_clk = 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;
+	}
+
+	ret = clk_notifier_register(cpu_clk, &hb_cpufreq_clk_nb);
+	if (ret) {
+		pr_err("failed to register clk notifier: %d\n", ret);
+		goto out_put_node;
+	}
+
+	/* Instantiate cpufreq-cpu0 */
+	platform_device_register_full(&devinfo);
+
+out_put_node:
+	of_node_put(np);
+	return ret;
+}
+module_init(hb_cpufreq_driver_init);
+
+MODULE_AUTHOR("Mark Langsdorf <mark.langsdorf@calxeda.com>");
+MODULE_DESCRIPTION("Calxeda Highbank cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c
new file mode 100644
index 000000000000..54e336de373b
--- /dev/null
+++ b/drivers/cpufreq/imx6q-cpufreq.c
@@ -0,0 +1,336 @@
+/*
+ * Copyright (C) 2013 Freescale Semiconductor, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/delay.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>
+
+#define PU_SOC_VOLTAGE_NORMAL	1250000
+#define PU_SOC_VOLTAGE_HIGH	1275000
+#define FREQ_1P2_GHZ		1200000000
+
+static struct regulator *arm_reg;
+static struct regulator *pu_reg;
+static struct regulator *soc_reg;
+
+static struct clk *arm_clk;
+static struct clk *pll1_sys_clk;
+static struct clk *pll1_sw_clk;
+static struct clk *step_clk;
+static struct clk *pll2_pfd2_396m_clk;
+
+static struct device *cpu_dev;
+static struct cpufreq_frequency_table *freq_table;
+static unsigned int transition_latency;
+
+static int imx6q_verify_speed(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, freq_table);
+}
+
+static unsigned int imx6q_get_speed(unsigned int cpu)
+{
+	return clk_get_rate(arm_clk) / 1000;
+}
+
+static int imx6q_set_target(struct cpufreq_policy *policy,
+			    unsigned int target_freq, unsigned int relation)
+{
+	struct cpufreq_freqs freqs;
+	struct opp *opp;
+	unsigned long freq_hz, volt, volt_old;
+	unsigned int index, cpu;
+	int ret;
+
+	ret = cpufreq_frequency_table_target(policy, freq_table, target_freq,
+					     relation, &index);
+	if (ret) {
+		dev_err(cpu_dev, "failed to match target frequency %d: %d\n",
+			target_freq, ret);
+		return ret;
+	}
+
+	freqs.new = freq_table[index].frequency;
+	freq_hz = freqs.new * 1000;
+	freqs.old = clk_get_rate(arm_clk) / 1000;
+
+	if (freqs.old == freqs.new)
+		return 0;
+
+	for_each_online_cpu(cpu) {
+		freqs.cpu = cpu;
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+	}
+
+	rcu_read_lock();
+	opp = opp_find_freq_ceil(cpu_dev, &freq_hz);
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
+		dev_err(cpu_dev, "failed to find OPP for %ld\n", freq_hz);
+		return PTR_ERR(opp);
+	}
+
+	volt = opp_get_voltage(opp);
+	rcu_read_unlock();
+	volt_old = regulator_get_voltage(arm_reg);
+
+	dev_dbg(cpu_dev, "%u MHz, %ld mV --> %u MHz, %ld mV\n",
+		freqs.old / 1000, volt_old / 1000,
+		freqs.new / 1000, volt / 1000);
+
+	/* scaling up?  scale voltage before frequency */
+	if (freqs.new > freqs.old) {
+		ret = regulator_set_voltage_tol(arm_reg, volt, 0);
+		if (ret) {
+			dev_err(cpu_dev,
+				"failed to scale vddarm up: %d\n", ret);
+			return ret;
+		}
+
+		/*
+		 * Need to increase vddpu and vddsoc for safety
+		 * if we are about to run at 1.2 GHz.
+		 */
+		if (freqs.new == FREQ_1P2_GHZ / 1000) {
+			regulator_set_voltage_tol(pu_reg,
+					PU_SOC_VOLTAGE_HIGH, 0);
+			regulator_set_voltage_tol(soc_reg,
+					PU_SOC_VOLTAGE_HIGH, 0);
+		}
+	}
+
+	/*
+	 * The setpoints are selected per PLL/PDF frequencies, so we need to
+	 * reprogram PLL for frequency scaling.  The procedure of reprogramming
+	 * PLL1 is as below.
+	 *
+	 *  - Enable pll2_pfd2_396m_clk and reparent pll1_sw_clk to it
+	 *  - Reprogram pll1_sys_clk and reparent pll1_sw_clk back to it
+	 *  - Disable pll2_pfd2_396m_clk
+	 */
+	clk_prepare_enable(pll2_pfd2_396m_clk);
+	clk_set_parent(step_clk, pll2_pfd2_396m_clk);
+	clk_set_parent(pll1_sw_clk, step_clk);
+	if (freq_hz > clk_get_rate(pll2_pfd2_396m_clk)) {
+		clk_set_rate(pll1_sys_clk, freqs.new * 1000);
+		/*
+		 * If we are leaving 396 MHz set-point, we need to enable
+		 * pll1_sys_clk and disable pll2_pfd2_396m_clk to keep
+		 * their use count correct.
+		 */
+		if (freqs.old * 1000 <= clk_get_rate(pll2_pfd2_396m_clk)) {
+			clk_prepare_enable(pll1_sys_clk);
+			clk_disable_unprepare(pll2_pfd2_396m_clk);
+		}
+		clk_set_parent(pll1_sw_clk, pll1_sys_clk);
+		clk_disable_unprepare(pll2_pfd2_396m_clk);
+	} else {
+		/*
+		 * Disable pll1_sys_clk if pll2_pfd2_396m_clk is sufficient
+		 * to provide the frequency.
+		 */
+		clk_disable_unprepare(pll1_sys_clk);
+	}
+
+	/* Ensure the arm clock divider is what we expect */
+	ret = clk_set_rate(arm_clk, freqs.new * 1000);
+	if (ret) {
+		dev_err(cpu_dev, "failed to set clock rate: %d\n", ret);
+		regulator_set_voltage_tol(arm_reg, volt_old, 0);
+		return ret;
+	}
+
+	/* scaling down?  scale voltage after frequency */
+	if (freqs.new < freqs.old) {
+		ret = regulator_set_voltage_tol(arm_reg, volt, 0);
+		if (ret)
+			dev_warn(cpu_dev,
+				 "failed to scale vddarm down: %d\n", ret);
+
+		if (freqs.old == FREQ_1P2_GHZ / 1000) {
+			regulator_set_voltage_tol(pu_reg,
+					PU_SOC_VOLTAGE_NORMAL, 0);
+			regulator_set_voltage_tol(soc_reg,
+					PU_SOC_VOLTAGE_NORMAL, 0);
+		}
+	}
+
+	for_each_online_cpu(cpu) {
+		freqs.cpu = cpu;
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	}
+
+	return 0;
+}
+
+static int imx6q_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	ret = cpufreq_frequency_table_cpuinfo(policy, freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "invalid frequency table: %d\n", ret);
+		return ret;
+	}
+
+	policy->cpuinfo.transition_latency = transition_latency;
+	policy->cur = clk_get_rate(arm_clk) / 1000;
+	cpumask_setall(policy->cpus);
+	cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
+
+	return 0;
+}
+
+static int imx6q_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
+static struct freq_attr *imx6q_cpufreq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static struct cpufreq_driver imx6q_cpufreq_driver = {
+	.verify = imx6q_verify_speed,
+	.target = imx6q_set_target,
+	.get = imx6q_get_speed,
+	.init = imx6q_cpufreq_init,
+	.exit = imx6q_cpufreq_exit,
+	.name = "imx6q-cpufreq",
+	.attr = imx6q_cpufreq_attr,
+};
+
+static int imx6q_cpufreq_probe(struct platform_device *pdev)
+{
+	struct device_node *np;
+	struct opp *opp;
+	unsigned long min_volt, max_volt;
+	int num, ret;
+
+	cpu_dev = &pdev->dev;
+
+	np = of_find_node_by_path("/cpus/cpu@0");
+	if (!np) {
+		dev_err(cpu_dev, "failed to find cpu0 node\n");
+		return -ENOENT;
+	}
+
+	cpu_dev->of_node = np;
+
+	arm_clk = devm_clk_get(cpu_dev, "arm");
+	pll1_sys_clk = devm_clk_get(cpu_dev, "pll1_sys");
+	pll1_sw_clk = devm_clk_get(cpu_dev, "pll1_sw");
+	step_clk = devm_clk_get(cpu_dev, "step");
+	pll2_pfd2_396m_clk = devm_clk_get(cpu_dev, "pll2_pfd2_396m");
+	if (IS_ERR(arm_clk) || IS_ERR(pll1_sys_clk) || IS_ERR(pll1_sw_clk) ||
+	    IS_ERR(step_clk) || IS_ERR(pll2_pfd2_396m_clk)) {
+		dev_err(cpu_dev, "failed to get clocks\n");
+		ret = -ENOENT;
+		goto put_node;
+	}
+
+	arm_reg = devm_regulator_get(cpu_dev, "arm");
+	pu_reg = devm_regulator_get(cpu_dev, "pu");
+	soc_reg = devm_regulator_get(cpu_dev, "soc");
+	if (IS_ERR(arm_reg) || IS_ERR(pu_reg) || IS_ERR(soc_reg)) {
+		dev_err(cpu_dev, "failed to get regulators\n");
+		ret = -ENOENT;
+		goto put_node;
+	}
+
+	/* We expect an OPP table supplied by platform */
+	num = opp_get_opp_count(cpu_dev);
+	if (num < 0) {
+		ret = num;
+		dev_err(cpu_dev, "no OPP table is found: %d\n", ret);
+		goto put_node;
+	}
+
+	ret = opp_init_cpufreq_table(cpu_dev, &freq_table);
+	if (ret) {
+		dev_err(cpu_dev, "failed to init cpufreq table: %d\n", ret);
+		goto put_node;
+	}
+
+	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+		transition_latency = CPUFREQ_ETERNAL;
+
+	/*
+	 * OPP is maintained in order of increasing frequency, and
+	 * freq_table initialised from OPP is therefore sorted in the
+	 * same order.
+	 */
+	rcu_read_lock();
+	opp = opp_find_freq_exact(cpu_dev,
+				  freq_table[0].frequency * 1000, true);
+	min_volt = opp_get_voltage(opp);
+	opp = opp_find_freq_exact(cpu_dev,
+				  freq_table[--num].frequency * 1000, true);
+	max_volt = opp_get_voltage(opp);
+	rcu_read_unlock();
+	ret = regulator_set_voltage_time(arm_reg, min_volt, max_volt);
+	if (ret > 0)
+		transition_latency += ret * 1000;
+
+	/* Count vddpu and vddsoc latency in for 1.2 GHz support */
+	if (freq_table[num].frequency == FREQ_1P2_GHZ / 1000) {
+		ret = regulator_set_voltage_time(pu_reg, PU_SOC_VOLTAGE_NORMAL,
+						 PU_SOC_VOLTAGE_HIGH);
+		if (ret > 0)
+			transition_latency += ret * 1000;
+		ret = regulator_set_voltage_time(soc_reg, PU_SOC_VOLTAGE_NORMAL,
+						 PU_SOC_VOLTAGE_HIGH);
+		if (ret > 0)
+			transition_latency += ret * 1000;
+	}
+
+	ret = cpufreq_register_driver(&imx6q_cpufreq_driver);
+	if (ret) {
+		dev_err(cpu_dev, "failed register driver: %d\n", ret);
+		goto free_freq_table;
+	}
+
+	of_node_put(np);
+	return 0;
+
+free_freq_table:
+	opp_free_cpufreq_table(cpu_dev, &freq_table);
+put_node:
+	of_node_put(np);
+	return ret;
+}
+
+static int imx6q_cpufreq_remove(struct platform_device *pdev)
+{
+	cpufreq_unregister_driver(&imx6q_cpufreq_driver);
+	opp_free_cpufreq_table(cpu_dev, &freq_table);
+
+	return 0;
+}
+
+static struct platform_driver imx6q_cpufreq_platdrv = {
+	.driver = {
+		.name	= "imx6q-cpufreq",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= imx6q_cpufreq_probe,
+	.remove		= imx6q_cpufreq_remove,
+};
+module_platform_driver(imx6q_cpufreq_platdrv);
+
+MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
+MODULE_DESCRIPTION("Freescale i.MX6Q cpufreq driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
new file mode 100644
index 000000000000..f6dd1e761129
--- /dev/null
+++ b/drivers/cpufreq/intel_pstate.c
@@ -0,0 +1,809 @@
+/*
+ * cpufreq_snb.c: Native P state management for Intel processors
+ *
+ * (C) Copyright 2012 Intel Corporation
+ * Author: Dirk Brandewie <dirk.j.brandewie@intel.com>
+ *
+ * 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; version 2
+ * of the License.
+ */
+
+#include <linux/kernel.h>
+#include <linux/kernel_stat.h>
+#include <linux/module.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/list.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/debugfs.h>
+#include <trace/events/power.h>
+
+#include <asm/div64.h>
+#include <asm/msr.h>
+#include <asm/cpu_device_id.h>
+
+#define SAMPLE_COUNT		3
+
+#define FRAC_BITS 8
+#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
+#define fp_toint(X) ((X) >> FRAC_BITS)
+
+static inline int32_t mul_fp(int32_t x, int32_t y)
+{
+	return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
+}
+
+static inline int32_t div_fp(int32_t x, int32_t y)
+{
+	return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
+}
+
+struct sample {
+	ktime_t start_time;
+	ktime_t end_time;
+	int core_pct_busy;
+	int pstate_pct_busy;
+	u64 duration_us;
+	u64 idletime_us;
+	u64 aperf;
+	u64 mperf;
+	int freq;
+};
+
+struct pstate_data {
+	int	current_pstate;
+	int	min_pstate;
+	int	max_pstate;
+	int	turbo_pstate;
+};
+
+struct _pid {
+	int setpoint;
+	int32_t integral;
+	int32_t p_gain;
+	int32_t i_gain;
+	int32_t d_gain;
+	int deadband;
+	int last_err;
+};
+
+struct cpudata {
+	int cpu;
+
+	char name[64];
+
+	struct timer_list timer;
+
+	struct pstate_adjust_policy *pstate_policy;
+	struct pstate_data pstate;
+	struct _pid pid;
+	struct _pid idle_pid;
+
+	int min_pstate_count;
+	int idle_mode;
+
+	ktime_t prev_sample;
+	u64	prev_idle_time_us;
+	u64	prev_aperf;
+	u64	prev_mperf;
+	int	sample_ptr;
+	struct sample samples[SAMPLE_COUNT];
+};
+
+static struct cpudata **all_cpu_data;
+struct pstate_adjust_policy {
+	int sample_rate_ms;
+	int deadband;
+	int setpoint;
+	int p_gain_pct;
+	int d_gain_pct;
+	int i_gain_pct;
+};
+
+static struct pstate_adjust_policy default_policy = {
+	.sample_rate_ms = 10,
+	.deadband = 0,
+	.setpoint = 109,
+	.p_gain_pct = 17,
+	.d_gain_pct = 0,
+	.i_gain_pct = 4,
+};
+
+struct perf_limits {
+	int no_turbo;
+	int max_perf_pct;
+	int min_perf_pct;
+	int32_t max_perf;
+	int32_t min_perf;
+};
+
+static struct perf_limits limits = {
+	.no_turbo = 0,
+	.max_perf_pct = 100,
+	.max_perf = int_tofp(1),
+	.min_perf_pct = 0,
+	.min_perf = 0,
+};
+
+static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
+			int deadband, int integral) {
+	pid->setpoint = setpoint;
+	pid->deadband  = deadband;
+	pid->integral  = int_tofp(integral);
+	pid->last_err  = setpoint - busy;
+}
+
+static inline void pid_p_gain_set(struct _pid *pid, int percent)
+{
+	pid->p_gain = div_fp(int_tofp(percent), int_tofp(100));
+}
+
+static inline void pid_i_gain_set(struct _pid *pid, int percent)
+{
+	pid->i_gain = div_fp(int_tofp(percent), int_tofp(100));
+}
+
+static inline void pid_d_gain_set(struct _pid *pid, int percent)
+{
+
+	pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
+}
+
+static signed int pid_calc(struct _pid *pid, int busy)
+{
+	signed int err, result;
+	int32_t pterm, dterm, fp_error;
+	int32_t integral_limit;
+
+	err = pid->setpoint - busy;
+	fp_error = int_tofp(err);
+
+	if (abs(err) <= pid->deadband)
+		return 0;
+
+	pterm = mul_fp(pid->p_gain, fp_error);
+
+	pid->integral += fp_error;
+
+	/* limit the integral term */
+	integral_limit = int_tofp(30);
+	if (pid->integral > integral_limit)
+		pid->integral = integral_limit;
+	if (pid->integral < -integral_limit)
+		pid->integral = -integral_limit;
+
+	dterm = mul_fp(pid->d_gain, (err - pid->last_err));
+	pid->last_err = err;
+
+	result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
+
+	return (signed int)fp_toint(result);
+}
+
+static inline void intel_pstate_busy_pid_reset(struct cpudata *cpu)
+{
+	pid_p_gain_set(&cpu->pid, cpu->pstate_policy->p_gain_pct);
+	pid_d_gain_set(&cpu->pid, cpu->pstate_policy->d_gain_pct);
+	pid_i_gain_set(&cpu->pid, cpu->pstate_policy->i_gain_pct);
+
+	pid_reset(&cpu->pid,
+		cpu->pstate_policy->setpoint,
+		100,
+		cpu->pstate_policy->deadband,
+		0);
+}
+
+static inline void intel_pstate_idle_pid_reset(struct cpudata *cpu)
+{
+	pid_p_gain_set(&cpu->idle_pid, cpu->pstate_policy->p_gain_pct);
+	pid_d_gain_set(&cpu->idle_pid, cpu->pstate_policy->d_gain_pct);
+	pid_i_gain_set(&cpu->idle_pid, cpu->pstate_policy->i_gain_pct);
+
+	pid_reset(&cpu->idle_pid,
+		75,
+		50,
+		cpu->pstate_policy->deadband,
+		0);
+}
+
+static inline void intel_pstate_reset_all_pid(void)
+{
+	unsigned int cpu;
+	for_each_online_cpu(cpu) {
+		if (all_cpu_data[cpu])
+			intel_pstate_busy_pid_reset(all_cpu_data[cpu]);
+	}
+}
+
+/************************** debugfs begin ************************/
+static int pid_param_set(void *data, u64 val)
+{
+	*(u32 *)data = val;
+	intel_pstate_reset_all_pid();
+	return 0;
+}
+static int pid_param_get(void *data, u64 *val)
+{
+	*val = *(u32 *)data;
+	return 0;
+}
+DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get,
+			pid_param_set, "%llu\n");
+
+struct pid_param {
+	char *name;
+	void *value;
+};
+
+static struct pid_param pid_files[] = {
+	{"sample_rate_ms", &default_policy.sample_rate_ms},
+	{"d_gain_pct", &default_policy.d_gain_pct},
+	{"i_gain_pct", &default_policy.i_gain_pct},
+	{"deadband", &default_policy.deadband},
+	{"setpoint", &default_policy.setpoint},
+	{"p_gain_pct", &default_policy.p_gain_pct},
+	{NULL, NULL}
+};
+
+static struct dentry *debugfs_parent;
+static void intel_pstate_debug_expose_params(void)
+{
+	int i = 0;
+
+	debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
+	if (IS_ERR_OR_NULL(debugfs_parent))
+		return;
+	while (pid_files[i].name) {
+		debugfs_create_file(pid_files[i].name, 0660,
+				debugfs_parent, pid_files[i].value,
+				&fops_pid_param);
+		i++;
+	}
+}
+
+/************************** debugfs end ************************/
+
+/************************** sysfs begin ************************/
+#define show_one(file_name, object)					\
+	static ssize_t show_##file_name					\
+	(struct kobject *kobj, struct attribute *attr, char *buf)	\
+	{								\
+		return sprintf(buf, "%u\n", limits.object);		\
+	}
+
+static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
+				const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf(buf, "%u", &input);
+	if (ret != 1)
+		return -EINVAL;
+	limits.no_turbo = clamp_t(int, input, 0 , 1);
+
+	return count;
+}
+
+static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
+				const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf(buf, "%u", &input);
+	if (ret != 1)
+		return -EINVAL;
+
+	limits.max_perf_pct = clamp_t(int, input, 0 , 100);
+	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
+	return count;
+}
+
+static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
+				const char *buf, size_t count)
+{
+	unsigned int input;
+	int ret;
+	ret = sscanf(buf, "%u", &input);
+	if (ret != 1)
+		return -EINVAL;
+	limits.min_perf_pct = clamp_t(int, input, 0 , 100);
+	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
+
+	return count;
+}
+
+show_one(no_turbo, no_turbo);
+show_one(max_perf_pct, max_perf_pct);
+show_one(min_perf_pct, min_perf_pct);
+
+define_one_global_rw(no_turbo);
+define_one_global_rw(max_perf_pct);
+define_one_global_rw(min_perf_pct);
+
+static struct attribute *intel_pstate_attributes[] = {
+	&no_turbo.attr,
+	&max_perf_pct.attr,
+	&min_perf_pct.attr,
+	NULL
+};
+
+static struct attribute_group intel_pstate_attr_group = {
+	.attrs = intel_pstate_attributes,
+};
+static struct kobject *intel_pstate_kobject;
+
+static void intel_pstate_sysfs_expose_params(void)
+{
+	int rc;
+
+	intel_pstate_kobject = kobject_create_and_add("intel_pstate",
+						&cpu_subsys.dev_root->kobj);
+	BUG_ON(!intel_pstate_kobject);
+	rc = sysfs_create_group(intel_pstate_kobject,
+				&intel_pstate_attr_group);
+	BUG_ON(rc);
+}
+
+/************************** sysfs end ************************/
+
+static int intel_pstate_min_pstate(void)
+{
+	u64 value;
+	rdmsrl(0xCE, value);
+	return (value >> 40) & 0xFF;
+}
+
+static int intel_pstate_max_pstate(void)
+{
+	u64 value;
+	rdmsrl(0xCE, value);
+	return (value >> 8) & 0xFF;
+}
+
+static int intel_pstate_turbo_pstate(void)
+{
+	u64 value;
+	int nont, ret;
+	rdmsrl(0x1AD, value);
+	nont = intel_pstate_max_pstate();
+	ret = ((value) & 255);
+	if (ret <= nont)
+		ret = nont;
+	return ret;
+}
+
+static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
+{
+	int max_perf = cpu->pstate.turbo_pstate;
+	int min_perf;
+	if (limits.no_turbo)
+		max_perf = cpu->pstate.max_pstate;
+
+	max_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
+	*max = clamp_t(int, max_perf,
+			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
+
+	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf));
+	*min = clamp_t(int, min_perf,
+			cpu->pstate.min_pstate, max_perf);
+}
+
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate)
+{
+	int max_perf, min_perf;
+
+	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
+
+	pstate = clamp_t(int, pstate, min_perf, max_perf);
+
+	if (pstate == cpu->pstate.current_pstate)
+		return;
+
+#ifndef MODULE
+	trace_cpu_frequency(pstate * 100000, cpu->cpu);
+#endif
+	cpu->pstate.current_pstate = pstate;
+	wrmsrl(MSR_IA32_PERF_CTL, pstate << 8);
+
+}
+
+static inline void intel_pstate_pstate_increase(struct cpudata *cpu, int steps)
+{
+	int target;
+	target = cpu->pstate.current_pstate + steps;
+
+	intel_pstate_set_pstate(cpu, target);
+}
+
+static inline void intel_pstate_pstate_decrease(struct cpudata *cpu, int steps)
+{
+	int target;
+	target = cpu->pstate.current_pstate - steps;
+	intel_pstate_set_pstate(cpu, target);
+}
+
+static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
+{
+	sprintf(cpu->name, "Intel 2nd generation core");
+
+	cpu->pstate.min_pstate = intel_pstate_min_pstate();
+	cpu->pstate.max_pstate = intel_pstate_max_pstate();
+	cpu->pstate.turbo_pstate = intel_pstate_turbo_pstate();
+
+	/*
+	 * goto max pstate so we don't slow up boot if we are built-in if we are
+	 * a module we will take care of it during normal operation
+	 */
+	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
+}
+
+static inline void intel_pstate_calc_busy(struct cpudata *cpu,
+					struct sample *sample)
+{
+	u64 core_pct;
+	sample->pstate_pct_busy = 100 - div64_u64(
+					sample->idletime_us * 100,
+					sample->duration_us);
+	core_pct = div64_u64(sample->aperf * 100, sample->mperf);
+	sample->freq = cpu->pstate.turbo_pstate * core_pct * 1000;
+
+	sample->core_pct_busy = div_s64((sample->pstate_pct_busy * core_pct),
+					100);
+}
+
+static inline void intel_pstate_sample(struct cpudata *cpu)
+{
+	ktime_t now;
+	u64 idle_time_us;
+	u64 aperf, mperf;
+
+	now = ktime_get();
+	idle_time_us = get_cpu_idle_time_us(cpu->cpu, NULL);
+
+	rdmsrl(MSR_IA32_APERF, aperf);
+	rdmsrl(MSR_IA32_MPERF, mperf);
+	/* for the first sample, don't actually record a sample, just
+	 * set the baseline */
+	if (cpu->prev_idle_time_us > 0) {
+		cpu->sample_ptr = (cpu->sample_ptr + 1) % SAMPLE_COUNT;
+		cpu->samples[cpu->sample_ptr].start_time = cpu->prev_sample;
+		cpu->samples[cpu->sample_ptr].end_time = now;
+		cpu->samples[cpu->sample_ptr].duration_us =
+			ktime_us_delta(now, cpu->prev_sample);
+		cpu->samples[cpu->sample_ptr].idletime_us =
+			idle_time_us - cpu->prev_idle_time_us;
+
+		cpu->samples[cpu->sample_ptr].aperf = aperf;
+		cpu->samples[cpu->sample_ptr].mperf = mperf;
+		cpu->samples[cpu->sample_ptr].aperf -= cpu->prev_aperf;
+		cpu->samples[cpu->sample_ptr].mperf -= cpu->prev_mperf;
+
+		intel_pstate_calc_busy(cpu, &cpu->samples[cpu->sample_ptr]);
+	}
+
+	cpu->prev_sample = now;
+	cpu->prev_idle_time_us = idle_time_us;
+	cpu->prev_aperf = aperf;
+	cpu->prev_mperf = mperf;
+}
+
+static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
+{
+	int sample_time, delay;
+
+	sample_time = cpu->pstate_policy->sample_rate_ms;
+	delay = msecs_to_jiffies(sample_time);
+	delay -= jiffies % delay;
+	mod_timer_pinned(&cpu->timer, jiffies + delay);
+}
+
+static inline void intel_pstate_idle_mode(struct cpudata *cpu)
+{
+	cpu->idle_mode = 1;
+}
+
+static inline void intel_pstate_normal_mode(struct cpudata *cpu)
+{
+	cpu->idle_mode = 0;
+}
+
+static inline int intel_pstate_get_scaled_busy(struct cpudata *cpu)
+{
+	int32_t busy_scaled;
+	int32_t core_busy, turbo_pstate, current_pstate;
+
+	core_busy = int_tofp(cpu->samples[cpu->sample_ptr].core_pct_busy);
+	turbo_pstate = int_tofp(cpu->pstate.turbo_pstate);
+	current_pstate = int_tofp(cpu->pstate.current_pstate);
+	busy_scaled = mul_fp(core_busy, div_fp(turbo_pstate, current_pstate));
+
+	return fp_toint(busy_scaled);
+}
+
+static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
+{
+	int busy_scaled;
+	struct _pid *pid;
+	signed int ctl = 0;
+	int steps;
+
+	pid = &cpu->pid;
+	busy_scaled = intel_pstate_get_scaled_busy(cpu);
+
+	ctl = pid_calc(pid, busy_scaled);
+
+	steps = abs(ctl);
+	if (ctl < 0)
+		intel_pstate_pstate_increase(cpu, steps);
+	else
+		intel_pstate_pstate_decrease(cpu, steps);
+}
+
+static inline void intel_pstate_adjust_idle_pstate(struct cpudata *cpu)
+{
+	int busy_scaled;
+	struct _pid *pid;
+	int ctl = 0;
+	int steps;
+
+	pid = &cpu->idle_pid;
+
+	busy_scaled = intel_pstate_get_scaled_busy(cpu);
+
+	ctl = pid_calc(pid, 100 - busy_scaled);
+
+	steps = abs(ctl);
+	if (ctl < 0)
+		intel_pstate_pstate_decrease(cpu, steps);
+	else
+		intel_pstate_pstate_increase(cpu, steps);
+
+	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate)
+		intel_pstate_normal_mode(cpu);
+}
+
+static void intel_pstate_timer_func(unsigned long __data)
+{
+	struct cpudata *cpu = (struct cpudata *) __data;
+
+	intel_pstate_sample(cpu);
+
+	if (!cpu->idle_mode)
+		intel_pstate_adjust_busy_pstate(cpu);
+	else
+		intel_pstate_adjust_idle_pstate(cpu);
+
+#if defined(XPERF_FIX)
+	if (cpu->pstate.current_pstate == cpu->pstate.min_pstate) {
+		cpu->min_pstate_count++;
+		if (!(cpu->min_pstate_count % 5)) {
+			intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
+			intel_pstate_idle_mode(cpu);
+		}
+	} else
+		cpu->min_pstate_count = 0;
+#endif
+	intel_pstate_set_sample_time(cpu);
+}
+
+#define ICPU(model, policy) \
+	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&policy }
+
+static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
+	ICPU(0x2a, default_policy),
+	ICPU(0x2d, default_policy),
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, intel_pstate_cpu_ids);
+
+static int intel_pstate_init_cpu(unsigned int cpunum)
+{
+
+	const struct x86_cpu_id *id;
+	struct cpudata *cpu;
+
+	id = x86_match_cpu(intel_pstate_cpu_ids);
+	if (!id)
+		return -ENODEV;
+
+	all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
+	if (!all_cpu_data[cpunum])
+		return -ENOMEM;
+
+	cpu = all_cpu_data[cpunum];
+
+	intel_pstate_get_cpu_pstates(cpu);
+
+	cpu->cpu = cpunum;
+	cpu->pstate_policy =
+		(struct pstate_adjust_policy *)id->driver_data;
+	init_timer_deferrable(&cpu->timer);
+	cpu->timer.function = intel_pstate_timer_func;
+	cpu->timer.data =
+		(unsigned long)cpu;
+	cpu->timer.expires = jiffies + HZ/100;
+	intel_pstate_busy_pid_reset(cpu);
+	intel_pstate_idle_pid_reset(cpu);
+	intel_pstate_sample(cpu);
+	intel_pstate_set_pstate(cpu, cpu->pstate.max_pstate);
+
+	add_timer_on(&cpu->timer, cpunum);
+
+	pr_info("Intel pstate controlling: cpu %d\n", cpunum);
+
+	return 0;
+}
+
+static unsigned int intel_pstate_get(unsigned int cpu_num)
+{
+	struct sample *sample;
+	struct cpudata *cpu;
+
+	cpu = all_cpu_data[cpu_num];
+	if (!cpu)
+		return 0;
+	sample = &cpu->samples[cpu->sample_ptr];
+	return sample->freq;
+}
+
+static int intel_pstate_set_policy(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu;
+	int min, max;
+
+	cpu = all_cpu_data[policy->cpu];
+
+	if (!policy->cpuinfo.max_freq)
+		return -ENODEV;
+
+	intel_pstate_get_min_max(cpu, &min, &max);
+
+	limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
+	limits.min_perf_pct = clamp_t(int, limits.min_perf_pct, 0 , 100);
+	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
+
+	limits.max_perf_pct = policy->max * 100 / policy->cpuinfo.max_freq;
+	limits.max_perf_pct = clamp_t(int, limits.max_perf_pct, 0 , 100);
+	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
+
+	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
+		limits.min_perf_pct = 100;
+		limits.min_perf = int_tofp(1);
+		limits.max_perf_pct = 100;
+		limits.max_perf = int_tofp(1);
+		limits.no_turbo = 0;
+	}
+
+	return 0;
+}
+
+static int intel_pstate_verify_policy(struct cpufreq_policy *policy)
+{
+	cpufreq_verify_within_limits(policy,
+				policy->cpuinfo.min_freq,
+				policy->cpuinfo.max_freq);
+
+	if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
+		(policy->policy != CPUFREQ_POLICY_PERFORMANCE))
+		return -EINVAL;
+
+	return 0;
+}
+
+static int __cpuinit intel_pstate_cpu_exit(struct cpufreq_policy *policy)
+{
+	int cpu = policy->cpu;
+
+	del_timer(&all_cpu_data[cpu]->timer);
+	kfree(all_cpu_data[cpu]);
+	all_cpu_data[cpu] = NULL;
+	return 0;
+}
+
+static int __cpuinit intel_pstate_cpu_init(struct cpufreq_policy *policy)
+{
+	int rc, min_pstate, max_pstate;
+	struct cpudata *cpu;
+
+	rc = intel_pstate_init_cpu(policy->cpu);
+	if (rc)
+		return rc;
+
+	cpu = all_cpu_data[policy->cpu];
+
+	if (!limits.no_turbo &&
+		limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
+		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
+	else
+		policy->policy = CPUFREQ_POLICY_POWERSAVE;
+
+	intel_pstate_get_min_max(cpu, &min_pstate, &max_pstate);
+	policy->min = min_pstate * 100000;
+	policy->max = max_pstate * 100000;
+
+	/* cpuinfo and default policy values */
+	policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
+	policy->cpuinfo.max_freq = cpu->pstate.turbo_pstate * 100000;
+	policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
+	cpumask_set_cpu(policy->cpu, policy->cpus);
+
+	return 0;
+}
+
+static struct cpufreq_driver intel_pstate_driver = {
+	.flags		= CPUFREQ_CONST_LOOPS,
+	.verify		= intel_pstate_verify_policy,
+	.setpolicy	= intel_pstate_set_policy,
+	.get		= intel_pstate_get,
+	.init		= intel_pstate_cpu_init,
+	.exit		= intel_pstate_cpu_exit,
+	.name		= "intel_pstate",
+	.owner		= THIS_MODULE,
+};
+
+static int __initdata no_load;
+
+static int __init intel_pstate_init(void)
+{
+	int cpu, rc = 0;
+	const struct x86_cpu_id *id;
+
+	if (no_load)
+		return -ENODEV;
+
+	id = x86_match_cpu(intel_pstate_cpu_ids);
+	if (!id)
+		return -ENODEV;
+
+	pr_info("Intel P-state driver initializing.\n");
+
+	all_cpu_data = vmalloc(sizeof(void *) * num_possible_cpus());
+	if (!all_cpu_data)
+		return -ENOMEM;
+	memset(all_cpu_data, 0, sizeof(void *) * num_possible_cpus());
+
+	rc = cpufreq_register_driver(&intel_pstate_driver);
+	if (rc)
+		goto out;
+
+	intel_pstate_debug_expose_params();
+	intel_pstate_sysfs_expose_params();
+	return rc;
+out:
+	get_online_cpus();
+	for_each_online_cpu(cpu) {
+		if (all_cpu_data[cpu]) {
+			del_timer_sync(&all_cpu_data[cpu]->timer);
+			kfree(all_cpu_data[cpu]);
+		}
+	}
+
+	put_online_cpus();
+	vfree(all_cpu_data);
+	return -ENODEV;
+}
+device_initcall(intel_pstate_init);
+
+static int __init intel_pstate_setup(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "disable"))
+		no_load = 1;
+	return 0;
+}
+early_param("intel_pstate", intel_pstate_setup);
+
+MODULE_AUTHOR("Dirk Brandewie <dirk.j.brandewie@intel.com>");
+MODULE_DESCRIPTION("'intel_pstate' - P state driver Intel Core processors");
+MODULE_LICENSE("GPL");
diff --git a/drivers/cpufreq/kirkwood-cpufreq.c b/drivers/cpufreq/kirkwood-cpufreq.c
new file mode 100644
index 000000000000..0e83e3c24f5b
--- /dev/null
+++ b/drivers/cpufreq/kirkwood-cpufreq.c
@@ -0,0 +1,259 @@
+/*
+ *	kirkwood_freq.c: cpufreq driver for the Marvell kirkwood
+ *
+ *	Copyright (C) 2013 Andrew Lunn <andrew@lunn.ch>
+ *
+ *	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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/clk.h>
+#include <linux/clk-provider.h>
+#include <linux/cpufreq.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <asm/proc-fns.h>
+
+#define CPU_SW_INT_BLK BIT(28)
+
+static struct priv
+{
+	struct clk *cpu_clk;
+	struct clk *ddr_clk;
+	struct clk *powersave_clk;
+	struct device *dev;
+	void __iomem *base;
+} priv;
+
+#define STATE_CPU_FREQ 0x01
+#define STATE_DDR_FREQ 0x02
+
+/*
+ * Kirkwood can swap the clock to the CPU between two clocks:
+ *
+ * - cpu clk
+ * - ddr clk
+ *
+ * The frequencies are set at runtime before registering this *
+ * table.
+ */
+static struct cpufreq_frequency_table kirkwood_freq_table[] = {
+	{STATE_CPU_FREQ,	0}, /* CPU uses cpuclk */
+	{STATE_DDR_FREQ,	0}, /* CPU uses ddrclk */
+	{0,			CPUFREQ_TABLE_END},
+};
+
+static unsigned int kirkwood_cpufreq_get_cpu_frequency(unsigned int cpu)
+{
+	if (__clk_is_enabled(priv.powersave_clk))
+		return kirkwood_freq_table[1].frequency;
+	return kirkwood_freq_table[0].frequency;
+}
+
+static void kirkwood_cpufreq_set_cpu_state(unsigned int index)
+{
+	struct cpufreq_freqs freqs;
+	unsigned int state = kirkwood_freq_table[index].index;
+	unsigned long reg;
+
+	freqs.old = kirkwood_cpufreq_get_cpu_frequency(0);
+	freqs.new = kirkwood_freq_table[index].frequency;
+	freqs.cpu = 0; /* Kirkwood is UP */
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	dev_dbg(priv.dev, "Attempting to set frequency to %i KHz\n",
+		kirkwood_freq_table[index].frequency);
+	dev_dbg(priv.dev, "old frequency was %i KHz\n",
+		kirkwood_cpufreq_get_cpu_frequency(0));
+
+	if (freqs.old != freqs.new) {
+		local_irq_disable();
+
+		/* Disable interrupts to the CPU */
+		reg = readl_relaxed(priv.base);
+		reg |= CPU_SW_INT_BLK;
+		writel_relaxed(reg, priv.base);
+
+		switch (state) {
+		case STATE_CPU_FREQ:
+			clk_disable(priv.powersave_clk);
+			break;
+		case STATE_DDR_FREQ:
+			clk_enable(priv.powersave_clk);
+			break;
+		}
+
+		/* Wait-for-Interrupt, while the hardware changes frequency */
+		cpu_do_idle();
+
+		/* Enable interrupts to the CPU */
+		reg = readl_relaxed(priv.base);
+		reg &= ~CPU_SW_INT_BLK;
+		writel_relaxed(reg, priv.base);
+
+		local_irq_enable();
+	}
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+};
+
+static int kirkwood_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, kirkwood_freq_table);
+}
+
+static int kirkwood_cpufreq_target(struct cpufreq_policy *policy,
+			    unsigned int target_freq,
+			    unsigned int relation)
+{
+	unsigned int index = 0;
+
+	if (cpufreq_frequency_table_target(policy, kirkwood_freq_table,
+				target_freq, relation, &index))
+		return -EINVAL;
+
+	kirkwood_cpufreq_set_cpu_state(index);
+
+	return 0;
+}
+
+/* Module init and exit code */
+static int kirkwood_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	int result;
+
+	/* cpuinfo and default policy values */
+	policy->cpuinfo.transition_latency = 5000; /* 5uS */
+	policy->cur = kirkwood_cpufreq_get_cpu_frequency(0);
+
+	result = cpufreq_frequency_table_cpuinfo(policy, kirkwood_freq_table);
+	if (result)
+		return result;
+
+	cpufreq_frequency_table_get_attr(kirkwood_freq_table, policy->cpu);
+
+	return 0;
+}
+
+static int kirkwood_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
+static struct freq_attr *kirkwood_cpufreq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static struct cpufreq_driver kirkwood_cpufreq_driver = {
+	.get	= kirkwood_cpufreq_get_cpu_frequency,
+	.verify	= kirkwood_cpufreq_verify,
+	.target	= kirkwood_cpufreq_target,
+	.init	= kirkwood_cpufreq_cpu_init,
+	.exit	= kirkwood_cpufreq_cpu_exit,
+	.name	= "kirkwood-cpufreq",
+	.owner	= THIS_MODULE,
+	.attr	= kirkwood_cpufreq_attr,
+};
+
+static int kirkwood_cpufreq_probe(struct platform_device *pdev)
+{
+	struct device_node *np;
+	struct resource *res;
+	int err;
+
+	priv.dev = &pdev->dev;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		dev_err(&pdev->dev, "Cannot get memory resource\n");
+		return -ENODEV;
+	}
+	priv.base = devm_request_and_ioremap(&pdev->dev, res);
+	if (!priv.base) {
+		dev_err(&pdev->dev, "Cannot ioremap\n");
+		return -EADDRNOTAVAIL;
+	}
+
+	np = of_find_node_by_path("/cpus/cpu@0");
+	if (!np)
+		return -ENODEV;
+
+	priv.cpu_clk = of_clk_get_by_name(np, "cpu_clk");
+	if (IS_ERR(priv.cpu_clk)) {
+		dev_err(priv.dev, "Unable to get cpuclk");
+		return PTR_ERR(priv.cpu_clk);
+	}
+
+	clk_prepare_enable(priv.cpu_clk);
+	kirkwood_freq_table[0].frequency = clk_get_rate(priv.cpu_clk) / 1000;
+
+	priv.ddr_clk = of_clk_get_by_name(np, "ddrclk");
+	if (IS_ERR(priv.ddr_clk)) {
+		dev_err(priv.dev, "Unable to get ddrclk");
+		err = PTR_ERR(priv.ddr_clk);
+		goto out_cpu;
+	}
+
+	clk_prepare_enable(priv.ddr_clk);
+	kirkwood_freq_table[1].frequency = clk_get_rate(priv.ddr_clk) / 1000;
+
+	priv.powersave_clk = of_clk_get_by_name(np, "powersave");
+	if (IS_ERR(priv.powersave_clk)) {
+		dev_err(priv.dev, "Unable to get powersave");
+		err = PTR_ERR(priv.powersave_clk);
+		goto out_ddr;
+	}
+	clk_prepare(priv.powersave_clk);
+
+	of_node_put(np);
+	np = NULL;
+
+	err = cpufreq_register_driver(&kirkwood_cpufreq_driver);
+	if (!err)
+		return 0;
+
+	dev_err(priv.dev, "Failed to register cpufreq driver");
+
+	clk_disable_unprepare(priv.powersave_clk);
+out_ddr:
+	clk_disable_unprepare(priv.ddr_clk);
+out_cpu:
+	clk_disable_unprepare(priv.cpu_clk);
+	of_node_put(np);
+
+	return err;
+}
+
+static int kirkwood_cpufreq_remove(struct platform_device *pdev)
+{
+	cpufreq_unregister_driver(&kirkwood_cpufreq_driver);
+
+	clk_disable_unprepare(priv.powersave_clk);
+	clk_disable_unprepare(priv.ddr_clk);
+	clk_disable_unprepare(priv.cpu_clk);
+
+	return 0;
+}
+
+static struct platform_driver kirkwood_cpufreq_platform_driver = {
+	.probe = kirkwood_cpufreq_probe,
+	.remove = kirkwood_cpufreq_remove,
+	.driver = {
+		.name = "kirkwood-cpufreq",
+		.owner = THIS_MODULE,
+	},
+};
+
+module_platform_driver(kirkwood_cpufreq_platform_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Andrew Lunn <andrew@lunn.ch");
+MODULE_DESCRIPTION("cpufreq driver for Marvell's kirkwood CPU");
+MODULE_ALIAS("platform:kirkwood-cpufreq");
diff --git a/drivers/cpufreq/longhaul.c b/drivers/cpufreq/longhaul.c
index 53ddbc760af7..1180d536d1eb 100644
--- a/drivers/cpufreq/longhaul.c
+++ b/drivers/cpufreq/longhaul.c
@@ -77,7 +77,7 @@ static unsigned int longhaul_index;
 static int scale_voltage;
 static int disable_acpi_c3;
 static int revid_errata;
-
+static int enable;
 
 /* Clock ratios multiplied by 10 */
 static int mults[32];
@@ -930,7 +930,7 @@ static int __cpuinit longhaul_cpu_init(struct cpufreq_policy *policy)
 	return 0;
 }
 
-static int __devexit longhaul_cpu_exit(struct cpufreq_policy *policy)
+static int longhaul_cpu_exit(struct cpufreq_policy *policy)
 {
 	cpufreq_frequency_table_put_attr(policy->cpu);
 	return 0;
@@ -946,7 +946,7 @@ static struct cpufreq_driver longhaul_driver = {
 	.target	= longhaul_target,
 	.get	= longhaul_get,
 	.init	= longhaul_cpu_init,
-	.exit	= __devexit_p(longhaul_cpu_exit),
+	.exit	= longhaul_cpu_exit,
 	.name	= "longhaul",
 	.owner	= THIS_MODULE,
 	.attr	= longhaul_attr,
@@ -965,6 +965,10 @@ static int __init longhaul_init(void)
 	if (!x86_match_cpu(longhaul_id))
 		return -ENODEV;
 
+	if (!enable) {
+		printk(KERN_ERR PFX "Option \"enable\" not set. Aborting.\n");
+		return -ENODEV;
+	}
 #ifdef CONFIG_SMP
 	if (num_online_cpus() > 1) {
 		printk(KERN_ERR PFX "More than 1 CPU detected, "
@@ -1021,6 +1025,10 @@ MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor");
  * such. */
 module_param(revid_errata, int, 0644);
 MODULE_PARM_DESC(revid_errata, "Ignore CPU Revision ID");
+/* By default driver is disabled to prevent incompatible
+ * system freeze. */
+module_param(enable, int, 0644);
+MODULE_PARM_DESC(enable, "Enable driver");
 
 MODULE_AUTHOR("Dave Jones <davej@redhat.com>");
 MODULE_DESCRIPTION("Longhaul driver for VIA Cyrix processors.");
diff --git a/drivers/cpufreq/maple-cpufreq.c b/drivers/cpufreq/maple-cpufreq.c
index 89b178a3f849..d4c4989823dc 100644
--- a/drivers/cpufreq/maple-cpufreq.c
+++ b/drivers/cpufreq/maple-cpufreq.c
@@ -181,7 +181,7 @@ static int maple_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	/* secondary CPUs are tied to the primary one by the
 	 * cpufreq core if in the secondary policy we tell it that
 	 * it actually must be one policy together with all others. */
-	cpumask_copy(policy->cpus, cpu_online_mask);
+	cpumask_setall(policy->cpus);
 	cpufreq_frequency_table_get_attr(maple_cpu_freqs, policy->cpu);
 
 	return cpufreq_frequency_table_cpuinfo(policy,
diff --git a/drivers/cpufreq/omap-cpufreq.c b/drivers/cpufreq/omap-cpufreq.c
index 1f3417a8322d..9128c07bafba 100644
--- a/drivers/cpufreq/omap-cpufreq.c
+++ b/drivers/cpufreq/omap-cpufreq.c
@@ -110,13 +110,16 @@ static int omap_target(struct cpufreq_policy *policy,
 	freq = ret;
 
 	if (mpu_reg) {
+		rcu_read_lock();
 		opp = opp_find_freq_ceil(mpu_dev, &freq);
 		if (IS_ERR(opp)) {
+			rcu_read_unlock();
 			dev_err(mpu_dev, "%s: unable to find MPU OPP for %d\n",
 				__func__, freqs.new);
 			return -EINVAL;
 		}
 		volt = opp_get_voltage(opp);
+		rcu_read_unlock();
 		tol = volt * OPP_TOLERANCE / 100;
 		volt_old = regulator_get_voltage(mpu_reg);
 	}
@@ -211,10 +214,8 @@ static int __cpuinit omap_cpu_init(struct cpufreq_policy *policy)
 	 * interface to handle this scenario. Additional is_smp() check
 	 * is to keep SMP_ON_UP build working.
 	 */
-	if (is_smp()) {
-		policy->shared_type = CPUFREQ_SHARED_TYPE_ANY;
+	if (is_smp())
 		cpumask_setall(policy->cpus);
-	}
 
 	/* FIXME: what's the actual transition time? */
 	policy->cpuinfo.transition_latency = 300 * 1000;
diff --git a/drivers/cpufreq/powernow-k8.c b/drivers/cpufreq/powernow-k8.c
index e3ebb4fa2c3e..d13a13678b5f 100644
--- a/drivers/cpufreq/powernow-k8.c
+++ b/drivers/cpufreq/powernow-k8.c
@@ -1186,7 +1186,7 @@ err_out:
 	return -ENODEV;
 }
 
-static int __devexit powernowk8_cpu_exit(struct cpufreq_policy *pol)
+static int powernowk8_cpu_exit(struct cpufreq_policy *pol)
 {
 	struct powernow_k8_data *data = per_cpu(powernow_data, pol->cpu);
 
@@ -1242,46 +1242,66 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
 	.target		= powernowk8_target,
 	.bios_limit	= acpi_processor_get_bios_limit,
 	.init		= powernowk8_cpu_init,
-	.exit		= __devexit_p(powernowk8_cpu_exit),
+	.exit		= powernowk8_cpu_exit,
 	.get		= powernowk8_get,
 	.name		= "powernow-k8",
 	.owner		= THIS_MODULE,
 	.attr		= powernow_k8_attr,
 };
 
+static void __request_acpi_cpufreq(void)
+{
+	const char *cur_drv, *drv = "acpi-cpufreq";
+
+	cur_drv = cpufreq_get_current_driver();
+	if (!cur_drv)
+		goto request;
+
+	if (strncmp(cur_drv, drv, min_t(size_t, strlen(cur_drv), strlen(drv))))
+		pr_warn(PFX "WTF driver: %s\n", cur_drv);
+
+	return;
+
+ request:
+	pr_warn(PFX "This CPU is not supported anymore, using acpi-cpufreq instead.\n");
+	request_module(drv);
+}
+
 /* driver entry point for init */
 static int __cpuinit powernowk8_init(void)
 {
 	unsigned int i, supported_cpus = 0;
-	int rv;
+	int ret;
 
 	if (static_cpu_has(X86_FEATURE_HW_PSTATE)) {
-		pr_warn(PFX "this CPU is not supported anymore, using acpi-cpufreq instead.\n");
-		request_module("acpi-cpufreq");
+		__request_acpi_cpufreq();
 		return -ENODEV;
 	}
 
 	if (!x86_match_cpu(powernow_k8_ids))
 		return -ENODEV;
 
+	get_online_cpus();
 	for_each_online_cpu(i) {
-		int rc;
-		smp_call_function_single(i, check_supported_cpu, &rc, 1);
-		if (rc == 0)
+		smp_call_function_single(i, check_supported_cpu, &ret, 1);
+		if (!ret)
 			supported_cpus++;
 	}
 
-	if (supported_cpus != num_online_cpus())
+	if (supported_cpus != num_online_cpus()) {
+		put_online_cpus();
 		return -ENODEV;
+	}
+	put_online_cpus();
 
-	rv = cpufreq_register_driver(&cpufreq_amd64_driver);
+	ret = cpufreq_register_driver(&cpufreq_amd64_driver);
+	if (ret)
+		return ret;
 
-	if (!rv)
-		pr_info(PFX "Found %d %s (%d cpu cores) (" VERSION ")\n",
-			num_online_nodes(), boot_cpu_data.x86_model_id,
-			supported_cpus);
+	pr_info(PFX "Found %d %s (%d cpu cores) (" VERSION ")\n",
+		num_online_nodes(), boot_cpu_data.x86_model_id, supported_cpus);
 
-	return rv;
+	return ret;
 }
 
 /* driver entry point for term */
diff --git a/drivers/cpufreq/spear-cpufreq.c b/drivers/cpufreq/spear-cpufreq.c
new file mode 100644
index 000000000000..7e4d77327957
--- /dev/null
+++ b/drivers/cpufreq/spear-cpufreq.c
@@ -0,0 +1,293 @@
+/*
+ * drivers/cpufreq/spear-cpufreq.c
+ *
+ * CPU Frequency Scaling for SPEAr platform
+ *
+ * Copyright (C) 2012 ST Microelectronics
+ * Deepak Sikri <deepak.sikri@st.com>
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+/* SPEAr CPUFreq driver data structure */
+static struct {
+	struct clk *clk;
+	unsigned int transition_latency;
+	struct cpufreq_frequency_table *freq_tbl;
+	u32 cnt;
+} spear_cpufreq;
+
+static int spear_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, spear_cpufreq.freq_tbl);
+}
+
+static unsigned int spear_cpufreq_get(unsigned int cpu)
+{
+	return clk_get_rate(spear_cpufreq.clk) / 1000;
+}
+
+static struct clk *spear1340_cpu_get_possible_parent(unsigned long newfreq)
+{
+	struct clk *sys_pclk;
+	int pclk;
+	/*
+	 * In SPEAr1340, cpu clk's parent sys clk can take input from
+	 * following sources
+	 */
+	const char *sys_clk_src[] = {
+		"sys_syn_clk",
+		"pll1_clk",
+		"pll2_clk",
+		"pll3_clk",
+	};
+
+	/*
+	 * As sys clk can have multiple source with their own range
+	 * limitation so we choose possible sources accordingly
+	 */
+	if (newfreq <= 300000000)
+		pclk = 0; /* src is sys_syn_clk */
+	else if (newfreq > 300000000 && newfreq <= 500000000)
+		pclk = 3; /* src is pll3_clk */
+	else if (newfreq == 600000000)
+		pclk = 1; /* src is pll1_clk */
+	else
+		return ERR_PTR(-EINVAL);
+
+	/* Get parent to sys clock */
+	sys_pclk = clk_get(NULL, sys_clk_src[pclk]);
+	if (IS_ERR(sys_pclk))
+		pr_err("Failed to get %s clock\n", sys_clk_src[pclk]);
+
+	return sys_pclk;
+}
+
+/*
+ * In SPEAr1340, we cannot use newfreq directly because we need to actually
+ * access a source clock (clk) which might not be ancestor of cpu at present.
+ * Hence in SPEAr1340 we would operate on source clock directly before switching
+ * cpu clock to it.
+ */
+static int spear1340_set_cpu_rate(struct clk *sys_pclk, unsigned long newfreq)
+{
+	struct clk *sys_clk;
+	int ret = 0;
+
+	sys_clk = clk_get_parent(spear_cpufreq.clk);
+	if (IS_ERR(sys_clk)) {
+		pr_err("failed to get cpu's parent (sys) clock\n");
+		return PTR_ERR(sys_clk);
+	}
+
+	/* Set the rate of the source clock before changing the parent */
+	ret = clk_set_rate(sys_pclk, newfreq);
+	if (ret) {
+		pr_err("Failed to set sys clk rate to %lu\n", newfreq);
+		return ret;
+	}
+
+	ret = clk_set_parent(sys_clk, sys_pclk);
+	if (ret) {
+		pr_err("Failed to set sys clk parent\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int spear_cpufreq_target(struct cpufreq_policy *policy,
+		unsigned int target_freq, unsigned int relation)
+{
+	struct cpufreq_freqs freqs;
+	unsigned long newfreq;
+	struct clk *srcclk;
+	int index, ret, mult = 1;
+
+	if (cpufreq_frequency_table_target(policy, spear_cpufreq.freq_tbl,
+				target_freq, relation, &index))
+		return -EINVAL;
+
+	freqs.cpu = policy->cpu;
+	freqs.old = spear_cpufreq_get(0);
+
+	newfreq = spear_cpufreq.freq_tbl[index].frequency * 1000;
+	if (of_machine_is_compatible("st,spear1340")) {
+		/*
+		 * SPEAr1340 is special in the sense that due to the possibility
+		 * of multiple clock sources for cpu clk's parent we can have
+		 * different clock source for different frequency of cpu clk.
+		 * Hence we need to choose one from amongst these possible clock
+		 * sources.
+		 */
+		srcclk = spear1340_cpu_get_possible_parent(newfreq);
+		if (IS_ERR(srcclk)) {
+			pr_err("Failed to get src clk\n");
+			return PTR_ERR(srcclk);
+		}
+
+		/* SPEAr1340: src clk is always 2 * intended cpu clk */
+		mult = 2;
+	} else {
+		/*
+		 * src clock to be altered is ancestor of cpu clock. Hence we
+		 * can directly work on cpu clk
+		 */
+		srcclk = spear_cpufreq.clk;
+	}
+
+	newfreq = clk_round_rate(srcclk, newfreq * mult);
+	if (newfreq < 0) {
+		pr_err("clk_round_rate failed for cpu src clock\n");
+		return newfreq;
+	}
+
+	freqs.new = newfreq / 1000;
+	freqs.new /= mult;
+
+	for_each_cpu(freqs.cpu, policy->cpus)
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	if (mult == 2)
+		ret = spear1340_set_cpu_rate(srcclk, newfreq);
+	else
+		ret = clk_set_rate(spear_cpufreq.clk, newfreq);
+
+	/* Get current rate after clk_set_rate, in case of failure */
+	if (ret) {
+		pr_err("CPU Freq: cpu clk_set_rate failed: %d\n", ret);
+		freqs.new = clk_get_rate(spear_cpufreq.clk) / 1000;
+	}
+
+	for_each_cpu(freqs.cpu, policy->cpus)
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	return ret;
+}
+
+static int spear_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	ret = cpufreq_frequency_table_cpuinfo(policy, spear_cpufreq.freq_tbl);
+	if (ret) {
+		pr_err("cpufreq_frequency_table_cpuinfo() failed");
+		return ret;
+	}
+
+	cpufreq_frequency_table_get_attr(spear_cpufreq.freq_tbl, policy->cpu);
+	policy->cpuinfo.transition_latency = spear_cpufreq.transition_latency;
+	policy->cur = spear_cpufreq_get(0);
+
+	cpumask_setall(policy->cpus);
+
+	return 0;
+}
+
+static int spear_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	return 0;
+}
+
+static struct freq_attr *spear_cpufreq_attr[] = {
+	 &cpufreq_freq_attr_scaling_available_freqs,
+	 NULL,
+};
+
+static struct cpufreq_driver spear_cpufreq_driver = {
+	.name		= "cpufreq-spear",
+	.flags		= CPUFREQ_STICKY,
+	.verify		= spear_cpufreq_verify,
+	.target		= spear_cpufreq_target,
+	.get		= spear_cpufreq_get,
+	.init		= spear_cpufreq_init,
+	.exit		= spear_cpufreq_exit,
+	.attr		= spear_cpufreq_attr,
+};
+
+static int spear_cpufreq_driver_init(void)
+{
+	struct device_node *np;
+	const struct property *prop;
+	struct cpufreq_frequency_table *freq_tbl;
+	const __be32 *val;
+	int cnt, i, ret;
+
+	np = of_find_node_by_path("/cpus/cpu@0");
+	if (!np) {
+		pr_err("No cpu node found");
+		return -ENODEV;
+	}
+
+	if (of_property_read_u32(np, "clock-latency",
+				&spear_cpufreq.transition_latency))
+		spear_cpufreq.transition_latency = CPUFREQ_ETERNAL;
+
+	prop = of_find_property(np, "cpufreq_tbl", NULL);
+	if (!prop || !prop->value) {
+		pr_err("Invalid cpufreq_tbl");
+		ret = -ENODEV;
+		goto out_put_node;
+	}
+
+	cnt = prop->length / sizeof(u32);
+	val = prop->value;
+
+	freq_tbl = kmalloc(sizeof(*freq_tbl) * (cnt + 1), GFP_KERNEL);
+	if (!freq_tbl) {
+		ret = -ENOMEM;
+		goto out_put_node;
+	}
+
+	for (i = 0; i < cnt; i++) {
+		freq_tbl[i].index = i;
+		freq_tbl[i].frequency = be32_to_cpup(val++);
+	}
+
+	freq_tbl[i].index = i;
+	freq_tbl[i].frequency = CPUFREQ_TABLE_END;
+
+	spear_cpufreq.freq_tbl = freq_tbl;
+
+	of_node_put(np);
+
+	spear_cpufreq.clk = clk_get(NULL, "cpu_clk");
+	if (IS_ERR(spear_cpufreq.clk)) {
+		pr_err("Unable to get CPU clock\n");
+		ret = PTR_ERR(spear_cpufreq.clk);
+		goto out_put_mem;
+	}
+
+	ret = cpufreq_register_driver(&spear_cpufreq_driver);
+	if (!ret)
+		return 0;
+
+	pr_err("failed register driver: %d\n", ret);
+	clk_put(spear_cpufreq.clk);
+
+out_put_mem:
+	kfree(freq_tbl);
+	return ret;
+
+out_put_node:
+	of_node_put(np);
+	return ret;
+}
+late_initcall(spear_cpufreq_driver_init);
+
+MODULE_AUTHOR("Deepak Sikri <deepak.sikri@st.com>");
+MODULE_DESCRIPTION("SPEAr CPUFreq driver");
+MODULE_LICENSE("GPL");