These changes are the raw update to linux-4.4.6-rt14. Kernel sources

are taken from kernel.org, and rt patch from the rt wiki download page.

During the rebasing, the following patch collided:

Force tick interrupt and get rid of softirq magic(I70131fb85).

Collisions have been removed because its logic was found on the
source already.

Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>

46 files changed, 2727 insertions, 2164 deletions

diff --git a/kernel/drivers/cpufreq/Kconfig.arm b/kernel/drivers/cpufreq/Kconfig.arm
index 4f3dbc8cf..b1f8a73e5 100644
--- a/kernel/drivers/cpufreq/Kconfig.arm
+++ b/kernel/drivers/cpufreq/Kconfig.arm
@@ -5,7 +5,7 @@
 # big LITTLE core layer and glue drivers
 config ARM_BIG_LITTLE_CPUFREQ
 	tristate "Generic ARM big LITTLE CPUfreq driver"
-	depends on ARM && BIG_LITTLE && ARM_CPU_TOPOLOGY && HAVE_CLK
+	depends on (ARM_CPU_TOPOLOGY || ARM64) && HAVE_CLK
 	select PM_OPP
 	help
 	  This enables the Generic CPUfreq driver for ARM big.LITTLE platforms.
@@ -24,66 +24,6 @@ config ARM_VEXPRESS_SPC_CPUFREQ
           This add the CPUfreq driver support for Versatile Express
 	  big.LITTLE platforms using SPC for power management.
 
-
-config ARM_EXYNOS_CPUFREQ
-	tristate "SAMSUNG EXYNOS CPUfreq Driver"
-	depends on CPU_EXYNOS4210 || SOC_EXYNOS4212 || SOC_EXYNOS4412 || SOC_EXYNOS5250
-	depends on THERMAL
-	help
-	  This adds the CPUFreq driver for Samsung EXYNOS platforms.
-	  Supported SoC versions are:
-	     Exynos4210, Exynos4212, Exynos4412, and Exynos5250.
-
-	  If in doubt, say N.
-
-config ARM_EXYNOS4210_CPUFREQ
-	bool "SAMSUNG EXYNOS4210"
-	depends on CPU_EXYNOS4210
-	depends on ARM_EXYNOS_CPUFREQ
-	default y
-	help
-	  This adds the CPUFreq driver for Samsung EXYNOS4210
-	  SoC (S5PV310 or S5PC210).
-
-	  If in doubt, say N.
-
-config ARM_EXYNOS4X12_CPUFREQ
-	bool "SAMSUNG EXYNOS4x12"
-	depends on SOC_EXYNOS4212 || SOC_EXYNOS4412
-	depends on ARM_EXYNOS_CPUFREQ
-	default y
-	help
-	  This adds the CPUFreq driver for Samsung EXYNOS4X12
-	  SoC (EXYNOS4212 or EXYNOS4412).
-
-	  If in doubt, say N.
-
-config ARM_EXYNOS5250_CPUFREQ
-	bool "SAMSUNG EXYNOS5250"
-	depends on SOC_EXYNOS5250
-	depends on ARM_EXYNOS_CPUFREQ
-	default y
-	help
-	  This adds the CPUFreq driver for Samsung EXYNOS5250
-	  SoC.
-
-	  If in doubt, say N.
-
-config ARM_EXYNOS_CPU_FREQ_BOOST_SW
-	bool "EXYNOS Frequency Overclocking - Software"
-	depends on ARM_EXYNOS_CPUFREQ && THERMAL
-	select CPU_FREQ_BOOST_SW
-	select EXYNOS_THERMAL
-	help
-	  This driver supports software managed overclocking (BOOST).
-	  It allows usage of special frequencies for Samsung Exynos
-	  processors if thermal conditions are appropriate.
-
-	  It requires, for safe operation, thermal framework with properly
-	  defined trip points.
-
-	  If in doubt, say N.
-
 config ARM_EXYNOS5440_CPUFREQ
 	tristate "SAMSUNG EXYNOS5440"
 	depends on SOC_EXYNOS5440
@@ -141,6 +81,15 @@ config ARM_KIRKWOOD_CPUFREQ
 	  This adds the CPUFreq driver for Marvell Kirkwood
 	  SoCs.
 
+config ARM_MT8173_CPUFREQ
+	bool "Mediatek MT8173 CPUFreq support"
+	depends on ARCH_MEDIATEK && REGULATOR
+	depends on ARM64 || (ARM_CPU_TOPOLOGY && COMPILE_TEST)
+	depends on !CPU_THERMAL || THERMAL=y
+	select PM_OPP
+	help
+	  This adds the CPUFreq driver support for Mediatek MT8173 SoC.
+
 config ARM_OMAP2PLUS_CPUFREQ
 	bool "TI OMAP2+"
 	depends on ARCH_OMAP2PLUS
@@ -251,6 +200,16 @@ config ARM_SA1100_CPUFREQ
 config ARM_SA1110_CPUFREQ
 	bool
 
+config ARM_SCPI_CPUFREQ
+        tristate "SCPI based CPUfreq driver"
+	depends on ARM_BIG_LITTLE_CPUFREQ && ARM_SCPI_PROTOCOL && COMMON_CLK_SCPI
+        help
+	  This adds the CPUfreq driver support for ARM big.LITTLE platforms
+	  using SCPI protocol for CPU power management.
+
+	  This driver uses SCPI Message Protocol driver to interact with the
+	  firmware providing the CPU DVFS functionality.
+
 config ARM_SPEAR_CPUFREQ
 	bool "SPEAr CPUFreq support"
 	depends on PLAT_SPEAR
@@ -258,12 +217,19 @@ config ARM_SPEAR_CPUFREQ
 	help
 	  This adds the CPUFreq driver support for SPEAr SOCs.
 
-config ARM_TEGRA_CPUFREQ
-	bool "TEGRA CPUFreq support"
+config ARM_TEGRA20_CPUFREQ
+	bool "Tegra20 CPUFreq support"
 	depends on ARCH_TEGRA
 	default y
 	help
-	  This adds the CPUFreq driver support for TEGRA SOCs.
+	  This adds the CPUFreq driver support for Tegra20 SOCs.
+
+config ARM_TEGRA124_CPUFREQ
+	tristate "Tegra124 CPUFreq support"
+	depends on ARCH_TEGRA && CPUFREQ_DT && REGULATOR
+	default y
+	help
+	  This adds the CPUFreq driver support for Tegra124 SOCs.
 
 config ARM_PXA2xx_CPUFREQ
 	tristate "Intel PXA2xx CPUfreq driver"
@@ -272,3 +238,20 @@ config ARM_PXA2xx_CPUFREQ
 	  This add the CPUFreq driver support for Intel PXA2xx SOCs.
 
 	  If in doubt, say N.
+
+config ACPI_CPPC_CPUFREQ
+	tristate "CPUFreq driver based on the ACPI CPPC spec"
+	depends on ACPI
+	select ACPI_CPPC_LIB
+	default n
+	help
+	  This adds a CPUFreq driver which uses CPPC methods
+	  as described in the ACPIv5.1 spec. CPPC stands for
+	  Collaborative Processor Performance Controls. It
+	  is based on an abstract continuous scale of CPU
+	  performance values which allows the remote power
+	  processor to flexibly optimize for power and
+	  performance. CPPC relies on power management firmware
+	  support for its operation.
+
+	  If in doubt, say N.
diff --git a/kernel/drivers/cpufreq/Makefile b/kernel/drivers/cpufreq/Makefile
index cdce92ae2..c0af1a128 100644
--- a/kernel/drivers/cpufreq/Makefile
+++ b/kernel/drivers/cpufreq/Makefile
@@ -1,6 +1,5 @@
 # CPUfreq core
 obj-$(CONFIG_CPU_FREQ)			+= cpufreq.o freq_table.o
-obj-$(CONFIG_PM_OPP)			+= cpufreq_opp.o
 
 # CPUfreq stats
 obj-$(CONFIG_CPU_FREQ_STAT)             += cpufreq_stats.o
@@ -52,17 +51,13 @@ obj-$(CONFIG_ARM_DT_BL_CPUFREQ)		+= arm_big_little_dt.o
 
 obj-$(CONFIG_ARCH_DAVINCI)		+= davinci-cpufreq.o
 obj-$(CONFIG_UX500_SOC_DB8500)		+= dbx500-cpufreq.o
-obj-$(CONFIG_ARM_EXYNOS_CPUFREQ)	+= arm-exynos-cpufreq.o
-arm-exynos-cpufreq-y					:= exynos-cpufreq.o
-arm-exynos-cpufreq-$(CONFIG_ARM_EXYNOS4210_CPUFREQ)	+= exynos4210-cpufreq.o
-arm-exynos-cpufreq-$(CONFIG_ARM_EXYNOS4X12_CPUFREQ)	+= exynos4x12-cpufreq.o
-arm-exynos-cpufreq-$(CONFIG_ARM_EXYNOS5250_CPUFREQ)	+= exynos5250-cpufreq.o
 obj-$(CONFIG_ARM_EXYNOS5440_CPUFREQ)	+= exynos5440-cpufreq.o
 obj-$(CONFIG_ARM_HIGHBANK_CPUFREQ)	+= highbank-cpufreq.o
 obj-$(CONFIG_ARM_HISI_ACPU_CPUFREQ)	+= hisi-acpu-cpufreq.o
 obj-$(CONFIG_ARM_IMX6Q_CPUFREQ)		+= imx6q-cpufreq.o
 obj-$(CONFIG_ARM_INTEGRATOR)		+= integrator-cpufreq.o
 obj-$(CONFIG_ARM_KIRKWOOD_CPUFREQ)	+= kirkwood-cpufreq.o
+obj-$(CONFIG_ARM_MT8173_CPUFREQ)	+= mt8173-cpufreq.o
 obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o
 obj-$(CONFIG_PXA3xx)			+= pxa3xx-cpufreq.o
@@ -76,9 +71,13 @@ obj-$(CONFIG_ARM_S3C64XX_CPUFREQ)	+= s3c64xx-cpufreq.o
 obj-$(CONFIG_ARM_S5PV210_CPUFREQ)	+= s5pv210-cpufreq.o
 obj-$(CONFIG_ARM_SA1100_CPUFREQ)	+= sa1100-cpufreq.o
 obj-$(CONFIG_ARM_SA1110_CPUFREQ)	+= sa1110-cpufreq.o
+obj-$(CONFIG_ARM_SCPI_CPUFREQ)		+= scpi-cpufreq.o
 obj-$(CONFIG_ARM_SPEAR_CPUFREQ)		+= spear-cpufreq.o
-obj-$(CONFIG_ARM_TEGRA_CPUFREQ)		+= tegra-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA20_CPUFREQ)	+= tegra20-cpufreq.o
+obj-$(CONFIG_ARM_TEGRA124_CPUFREQ)	+= tegra124-cpufreq.o
 obj-$(CONFIG_ARM_VEXPRESS_SPC_CPUFREQ)	+= vexpress-spc-cpufreq.o
+obj-$(CONFIG_ACPI_CPPC_CPUFREQ) += cppc_cpufreq.o
+
 
 ##################################################################################
 # PowerPC platform drivers
diff --git a/kernel/drivers/cpufreq/acpi-cpufreq.c b/kernel/drivers/cpufreq/acpi-cpufreq.c
index b0c18ed8d..cec1ee2d2 100644
--- a/kernel/drivers/cpufreq/acpi-cpufreq.c
+++ b/kernel/drivers/cpufreq/acpi-cpufreq.c
@@ -65,18 +65,21 @@ enum {
 #define MSR_K7_HWCR_CPB_DIS	(1ULL << 25)
 
 struct acpi_cpufreq_data {
-	struct acpi_processor_performance *acpi_data;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int resume;
 	unsigned int cpu_feature;
+	unsigned int acpi_perf_cpu;
 	cpumask_var_t freqdomain_cpus;
 };
 
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
-
 /* acpi_perf_data is a pointer to percpu data. */
 static struct acpi_processor_performance __percpu *acpi_perf_data;
 
+static inline struct acpi_processor_performance *to_perf_data(struct acpi_cpufreq_data *data)
+{
+	return per_cpu_ptr(acpi_perf_data, data->acpi_perf_cpu);
+}
+
 static struct cpufreq_driver acpi_cpufreq_driver;
 
 static unsigned int acpi_pstate_strict;
@@ -144,7 +147,10 @@ static int _store_boost(int val)
 
 static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
+
+	if (unlikely(!data))
+		return -ENODEV;
 
 	return cpufreq_show_cpus(data->freqdomain_cpus, buf);
 }
@@ -202,7 +208,7 @@ static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
 	struct acpi_processor_performance *perf;
 	int i;
 
-	perf = data->acpi_data;
+	perf = to_perf_data(data);
 
 	for (i = 0; i < perf->state_count; i++) {
 		if (value == perf->states[i].status)
@@ -221,7 +227,7 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
 	else
 		msr &= INTEL_MSR_RANGE;
 
-	perf = data->acpi_data;
+	perf = to_perf_data(data);
 
 	cpufreq_for_each_entry(pos, data->freq_table)
 		if (msr == perf->states[pos->driver_data].status)
@@ -327,7 +333,8 @@ static void drv_write(struct drv_cmd *cmd)
 	put_cpu();
 }
 
-static u32 get_cur_val(const struct cpumask *mask)
+static u32
+get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
 {
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
@@ -335,7 +342,7 @@ static u32 get_cur_val(const struct cpumask *mask)
 	if (unlikely(cpumask_empty(mask)))
 		return 0;
 
-	switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
+	switch (data->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
@@ -346,7 +353,7 @@ static u32 get_cur_val(const struct cpumask *mask)
 		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
-		perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
+		perf = to_perf_data(data);
 		cmd.addr.io.port = perf->control_register.address;
 		cmd.addr.io.bit_width = perf->control_register.bit_width;
 		break;
@@ -364,19 +371,23 @@ static u32 get_cur_val(const struct cpumask *mask)
 
 static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
+	struct acpi_cpufreq_data *data;
+	struct cpufreq_policy *policy;
 	unsigned int freq;
 	unsigned int cached_freq;
 
 	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
 
-	if (unlikely(data == NULL ||
-		     data->acpi_data == NULL || data->freq_table == NULL)) {
+	policy = cpufreq_cpu_get_raw(cpu);
+	if (unlikely(!policy))
+		return 0;
+
+	data = policy->driver_data;
+	if (unlikely(!data || !data->freq_table))
 		return 0;
-	}
 
-	cached_freq = data->freq_table[data->acpi_data->state].frequency;
-	freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
+	cached_freq = data->freq_table[to_perf_data(data)->state].frequency;
+	freq = extract_freq(get_cur_val(cpumask_of(cpu), data), data);
 	if (freq != cached_freq) {
 		/*
 		 * The dreaded BIOS frequency change behind our back.
@@ -397,7 +408,7 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 	unsigned int i;
 
 	for (i = 0; i < 100; i++) {
-		cur_freq = extract_freq(get_cur_val(mask), data);
+		cur_freq = extract_freq(get_cur_val(mask, data), data);
 		if (cur_freq == freq)
 			return 1;
 		udelay(10);
@@ -408,18 +419,17 @@ static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
 static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 			       unsigned int index)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 	struct acpi_processor_performance *perf;
 	struct drv_cmd cmd;
 	unsigned int next_perf_state = 0; /* Index into perf table */
 	int result = 0;
 
-	if (unlikely(data == NULL ||
-	     data->acpi_data == NULL || data->freq_table == NULL)) {
+	if (unlikely(data == NULL || data->freq_table == NULL)) {
 		return -ENODEV;
 	}
 
-	perf = data->acpi_data;
+	perf = to_perf_data(data);
 	next_perf_state = data->freq_table[index].driver_data;
 	if (perf->state == next_perf_state) {
 		if (unlikely(data->resume)) {
@@ -482,8 +492,9 @@ out:
 static unsigned long
 acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
 {
-	struct acpi_processor_performance *perf = data->acpi_data;
+	struct acpi_processor_performance *perf;
 
+	perf = to_perf_data(data);
 	if (cpu_khz) {
 		/* search the closest match to cpu_khz */
 		unsigned int i;
@@ -672,17 +683,17 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_free;
 	}
 
-	data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
-	per_cpu(acfreq_data, cpu) = data;
+	perf = per_cpu_ptr(acpi_perf_data, cpu);
+	data->acpi_perf_cpu = cpu;
+	policy->driver_data = data;
 
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
 		acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
 
-	result = acpi_processor_register_performance(data->acpi_data, cpu);
+	result = acpi_processor_register_performance(perf, cpu);
 	if (result)
 		goto err_free_mask;
 
-	perf = data->acpi_data;
 	policy->shared_type = perf->shared_type;
 
 	/*
@@ -699,13 +710,14 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	dmi_check_system(sw_any_bug_dmi_table);
 	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));
+		cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
 	}
 
 	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
 		cpumask_clear(policy->cpus);
 		cpumask_set_cpu(cpu, policy->cpus);
-		cpumask_copy(data->freqdomain_cpus, cpu_sibling_mask(cpu));
+		cpumask_copy(data->freqdomain_cpus,
+			     topology_sibling_cpumask(cpu));
 		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
 		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
 	}
@@ -837,26 +849,25 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 err_freqfree:
 	kfree(data->freq_table);
 err_unreg:
-	acpi_processor_unregister_performance(perf, cpu);
+	acpi_processor_unregister_performance(cpu);
 err_free_mask:
 	free_cpumask_var(data->freqdomain_cpus);
 err_free:
 	kfree(data);
-	per_cpu(acfreq_data, cpu) = NULL;
+	policy->driver_data = NULL;
 
 	return result;
 }
 
 static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 
 	pr_debug("acpi_cpufreq_cpu_exit\n");
 
 	if (data) {
-		per_cpu(acfreq_data, policy->cpu) = NULL;
-		acpi_processor_unregister_performance(data->acpi_data,
-						      policy->cpu);
+		policy->driver_data = NULL;
+		acpi_processor_unregister_performance(data->acpi_perf_cpu);
 		free_cpumask_var(data->freqdomain_cpus);
 		kfree(data->freq_table);
 		kfree(data);
@@ -867,7 +878,7 @@ static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 
 static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 {
-	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_cpufreq_data *data = policy->driver_data;
 
 	pr_debug("acpi_cpufreq_resume\n");
 
@@ -879,7 +890,9 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
 static struct freq_attr *acpi_cpufreq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
 	&freqdomain_cpus,
-	NULL,	/* this is a placeholder for cpb, do not remove */
+#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
+	&cpb,
+#endif
 	NULL,
 };
 
@@ -952,17 +965,16 @@ static int __init acpi_cpufreq_init(void)
 	 * only if configured. This is considered legacy code, which
 	 * will probably be removed at some point in the future.
 	 */
-	if (check_amd_hwpstate_cpu(0)) {
-		struct freq_attr **iter;
+	if (!check_amd_hwpstate_cpu(0)) {
+		struct freq_attr **attr;
 
-		pr_debug("adding sysfs entry for cpb\n");
+		pr_debug("CPB unsupported, do not expose it\n");
 
-		for (iter = acpi_cpufreq_attr; *iter != NULL; iter++)
-			;
-
-		/* make sure there is a terminator behind it */
-		if (iter[1] == NULL)
-			*iter = &cpb;
+		for (attr = acpi_cpufreq_attr; *attr; attr++)
+			if (*attr == &cpb) {
+				*attr = NULL;
+				break;
+			}
 	}
 #endif
 	acpi_cpufreq_boost_init();
diff --git a/kernel/drivers/cpufreq/arm_big_little.c b/kernel/drivers/cpufreq/arm_big_little.c
index e1a6ba66a..c5d256caa 100644
--- a/kernel/drivers/cpufreq/arm_big_little.c
+++ b/kernel/drivers/cpufreq/arm_big_little.c
@@ -31,7 +31,6 @@
 #include <linux/slab.h>
 #include <linux/topology.h>
 #include <linux/types.h>
-#include <asm/bL_switcher.h>
 
 #include "arm_big_little.h"
 
@@ -41,12 +40,16 @@
 #define MAX_CLUSTERS	2
 
 #ifdef CONFIG_BL_SWITCHER
+#include <asm/bL_switcher.h>
 static bool bL_switching_enabled;
 #define is_bL_switching_enabled()	bL_switching_enabled
 #define set_switching_enabled(x)	(bL_switching_enabled = (x))
 #else
 #define is_bL_switching_enabled()	false
 #define set_switching_enabled(x)	do { } while (0)
+#define bL_switch_request(...)		do { } while (0)
+#define bL_switcher_put_enabled()	do { } while (0)
+#define bL_switcher_get_enabled()	do { } while (0)
 #endif
 
 #define ACTUAL_FREQ(cluster, freq)  ((cluster == A7_CLUSTER) ? freq << 1 : freq)
@@ -146,6 +149,19 @@ bL_cpufreq_set_rate(u32 cpu, u32 old_cluster, u32 new_cluster, u32 rate)
 			__func__, cpu, old_cluster, new_cluster, new_rate);
 
 	ret = clk_set_rate(clk[new_cluster], new_rate * 1000);
+	if (!ret) {
+		/*
+		 * FIXME: clk_set_rate hasn't returned an error here however it
+		 * may be that clk_change_rate failed due to hardware or
+		 * firmware issues and wasn't able to report that due to the
+		 * current design of the clk core layer. To work around this
+		 * problem we will read back the clock rate and check it is
+		 * correct. This needs to be removed once clk core is fixed.
+		 */
+		if (clk_get_rate(clk[new_cluster]) != new_rate * 1000)
+			ret = -EIO;
+	}
+
 	if (WARN_ON(ret)) {
 		pr_err("clk_set_rate failed: %d, new cluster: %d\n", ret,
 				new_cluster);
@@ -322,7 +338,6 @@ static void put_cluster_clk_and_freq_table(struct device *cpu_dev)
 static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 {
 	u32 cluster = raw_cpu_to_cluster(cpu_dev->id);
-	char name[14] = "cpu-cluster.";
 	int ret;
 
 	if (freq_table[cluster])
@@ -342,8 +357,7 @@ static int _get_cluster_clk_and_freq_table(struct device *cpu_dev)
 		goto free_opp_table;
 	}
 
-	name[12] = cluster + '0';
-	clk[cluster] = clk_get(cpu_dev, name);
+	clk[cluster] = clk_get(cpu_dev, NULL);
 	if (!IS_ERR(clk[cluster])) {
 		dev_dbg(cpu_dev, "%s: clk: %p & freq table: %p, cluster: %d\n",
 				__func__, clk[cluster], freq_table[cluster],
@@ -506,6 +520,7 @@ static struct cpufreq_driver bL_cpufreq_driver = {
 	.attr			= cpufreq_generic_attr,
 };
 
+#ifdef CONFIG_BL_SWITCHER
 static int bL_cpufreq_switcher_notifier(struct notifier_block *nfb,
 					unsigned long action, void *_arg)
 {
@@ -538,6 +553,20 @@ static struct notifier_block bL_switcher_notifier = {
 	.notifier_call = bL_cpufreq_switcher_notifier,
 };
 
+static int __bLs_register_notifier(void)
+{
+	return bL_switcher_register_notifier(&bL_switcher_notifier);
+}
+
+static int __bLs_unregister_notifier(void)
+{
+	return bL_switcher_unregister_notifier(&bL_switcher_notifier);
+}
+#else
+static int __bLs_register_notifier(void) { return 0; }
+static int __bLs_unregister_notifier(void) { return 0; }
+#endif
+
 int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 {
 	int ret, i;
@@ -555,8 +584,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 
 	arm_bL_ops = ops;
 
-	ret = bL_switcher_get_enabled();
-	set_switching_enabled(ret);
+	set_switching_enabled(bL_switcher_get_enabled());
 
 	for (i = 0; i < MAX_CLUSTERS; i++)
 		mutex_init(&cluster_lock[i]);
@@ -567,7 +595,7 @@ int bL_cpufreq_register(struct cpufreq_arm_bL_ops *ops)
 				__func__, ops->name, ret);
 		arm_bL_ops = NULL;
 	} else {
-		ret = bL_switcher_register_notifier(&bL_switcher_notifier);
+		ret = __bLs_register_notifier();
 		if (ret) {
 			cpufreq_unregister_driver(&bL_cpufreq_driver);
 			arm_bL_ops = NULL;
@@ -591,7 +619,7 @@ void bL_cpufreq_unregister(struct cpufreq_arm_bL_ops *ops)
 	}
 
 	bL_switcher_get_enabled();
-	bL_switcher_unregister_notifier(&bL_switcher_notifier);
+	__bLs_unregister_notifier();
 	cpufreq_unregister_driver(&bL_cpufreq_driver);
 	bL_switcher_put_enabled();
 	pr_info("%s: Un-registered platform driver: %s\n", __func__,
diff --git a/kernel/drivers/cpufreq/arm_big_little.h b/kernel/drivers/cpufreq/arm_big_little.h
index a211f7db9..b88889d93 100644
--- a/kernel/drivers/cpufreq/arm_big_little.h
+++ b/kernel/drivers/cpufreq/arm_big_little.h
@@ -28,7 +28,7 @@ struct cpufreq_arm_bL_ops {
 
 	/*
 	 * This must set opp table for cpu_dev in a similar way as done by
-	 * of_init_opp_table().
+	 * dev_pm_opp_of_add_table().
 	 */
 	int (*init_opp_table)(struct device *cpu_dev);
 
diff --git a/kernel/drivers/cpufreq/arm_big_little_dt.c b/kernel/drivers/cpufreq/arm_big_little_dt.c
index 36d91dba2..16ddeefe9 100644
--- a/kernel/drivers/cpufreq/arm_big_little_dt.c
+++ b/kernel/drivers/cpufreq/arm_big_little_dt.c
@@ -54,7 +54,7 @@ static int dt_init_opp_table(struct device *cpu_dev)
 		return -ENOENT;
 	}
 
-	ret = of_init_opp_table(cpu_dev);
+	ret = dev_pm_opp_of_add_table(cpu_dev);
 	of_node_put(np);
 
 	return ret;
@@ -82,7 +82,7 @@ static struct cpufreq_arm_bL_ops dt_bL_ops = {
 	.name	= "dt-bl",
 	.get_transition_latency = dt_get_transition_latency,
 	.init_opp_table = dt_init_opp_table,
-	.free_opp_table = of_free_opp_table,
+	.free_opp_table = dev_pm_opp_of_remove_table,
 };
 
 static int generic_bL_probe(struct platform_device *pdev)
diff --git a/kernel/drivers/cpufreq/cppc_cpufreq.c b/kernel/drivers/cpufreq/cppc_cpufreq.c
new file mode 100644
index 000000000..7c0bdfb1a
--- /dev/null
+++ b/kernel/drivers/cpufreq/cppc_cpufreq.c
@@ -0,0 +1,176 @@
+/*
+ * CPPC (Collaborative Processor Performance Control) driver for
+ * interfacing with the CPUfreq layer and governors. See
+ * cppc_acpi.c for CPPC specific methods.
+ *
+ * (C) Copyright 2014, 2015 Linaro Ltd.
+ * Author: Ashwin Chaugule <ashwin.chaugule@linaro.org>
+ *
+ * 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.
+ */
+
+#define pr_fmt(fmt)	"CPPC Cpufreq:"	fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/vmalloc.h>
+
+#include <acpi/cppc_acpi.h>
+
+/*
+ * These structs contain information parsed from per CPU
+ * ACPI _CPC structures.
+ * e.g. For each CPU the highest, lowest supported
+ * performance capabilities, desired performance level
+ * requested etc.
+ */
+static struct cpudata **all_cpu_data;
+
+static int cppc_cpufreq_set_target(struct cpufreq_policy *policy,
+		unsigned int target_freq,
+		unsigned int relation)
+{
+	struct cpudata *cpu;
+	struct cpufreq_freqs freqs;
+	int ret = 0;
+
+	cpu = all_cpu_data[policy->cpu];
+
+	cpu->perf_ctrls.desired_perf = target_freq;
+	freqs.old = policy->cur;
+	freqs.new = target_freq;
+
+	cpufreq_freq_transition_begin(policy, &freqs);
+	ret = cppc_set_perf(cpu->cpu, &cpu->perf_ctrls);
+	cpufreq_freq_transition_end(policy, &freqs, ret != 0);
+
+	if (ret)
+		pr_debug("Failed to set target on CPU:%d. ret:%d\n",
+				cpu->cpu, ret);
+
+	return ret;
+}
+
+static int cppc_verify_policy(struct cpufreq_policy *policy)
+{
+	cpufreq_verify_within_cpu_limits(policy);
+	return 0;
+}
+
+static void cppc_cpufreq_stop_cpu(struct cpufreq_policy *policy)
+{
+	int cpu_num = policy->cpu;
+	struct cpudata *cpu = all_cpu_data[cpu_num];
+	int ret;
+
+	cpu->perf_ctrls.desired_perf = cpu->perf_caps.lowest_perf;
+
+	ret = cppc_set_perf(cpu_num, &cpu->perf_ctrls);
+	if (ret)
+		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
+				cpu->perf_caps.lowest_perf, cpu_num, ret);
+}
+
+static int cppc_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	struct cpudata *cpu;
+	unsigned int cpu_num = policy->cpu;
+	int ret = 0;
+
+	cpu = all_cpu_data[policy->cpu];
+
+	cpu->cpu = cpu_num;
+	ret = cppc_get_perf_caps(policy->cpu, &cpu->perf_caps);
+
+	if (ret) {
+		pr_debug("Err reading CPU%d perf capabilities. ret:%d\n",
+				cpu_num, ret);
+		return ret;
+	}
+
+	policy->min = cpu->perf_caps.lowest_perf;
+	policy->max = cpu->perf_caps.highest_perf;
+	policy->cpuinfo.min_freq = policy->min;
+	policy->cpuinfo.max_freq = policy->max;
+	policy->shared_type = cpu->shared_type;
+
+	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ANY)
+		cpumask_copy(policy->cpus, cpu->shared_cpu_map);
+	else if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL) {
+		/* Support only SW_ANY for now. */
+		pr_debug("Unsupported CPU co-ord type\n");
+		return -EFAULT;
+	}
+
+	cpumask_set_cpu(policy->cpu, policy->cpus);
+	cpu->cur_policy = policy;
+
+	/* Set policy->cur to max now. The governors will adjust later. */
+	policy->cur = cpu->perf_ctrls.desired_perf = cpu->perf_caps.highest_perf;
+
+	ret = cppc_set_perf(cpu_num, &cpu->perf_ctrls);
+	if (ret)
+		pr_debug("Err setting perf value:%d on CPU:%d. ret:%d\n",
+				cpu->perf_caps.highest_perf, cpu_num, ret);
+
+	return ret;
+}
+
+static struct cpufreq_driver cppc_cpufreq_driver = {
+	.flags = CPUFREQ_CONST_LOOPS,
+	.verify = cppc_verify_policy,
+	.target = cppc_cpufreq_set_target,
+	.init = cppc_cpufreq_cpu_init,
+	.stop_cpu = cppc_cpufreq_stop_cpu,
+	.name = "cppc_cpufreq",
+};
+
+static int __init cppc_cpufreq_init(void)
+{
+	int i, ret = 0;
+	struct cpudata *cpu;
+
+	if (acpi_disabled)
+		return -ENODEV;
+
+	all_cpu_data = kzalloc(sizeof(void *) * num_possible_cpus(), GFP_KERNEL);
+	if (!all_cpu_data)
+		return -ENOMEM;
+
+	for_each_possible_cpu(i) {
+		all_cpu_data[i] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
+		if (!all_cpu_data[i])
+			goto out;
+
+		cpu = all_cpu_data[i];
+		if (!zalloc_cpumask_var(&cpu->shared_cpu_map, GFP_KERNEL))
+			goto out;
+	}
+
+	ret = acpi_get_psd_map(all_cpu_data);
+	if (ret) {
+		pr_debug("Error parsing PSD data. Aborting cpufreq registration.\n");
+		goto out;
+	}
+
+	ret = cpufreq_register_driver(&cppc_cpufreq_driver);
+	if (ret)
+		goto out;
+
+	return ret;
+
+out:
+	for_each_possible_cpu(i)
+		kfree(all_cpu_data[i]);
+
+	kfree(all_cpu_data);
+	return -ENODEV;
+}
+
+late_initcall(cppc_cpufreq_init);
diff --git a/kernel/drivers/cpufreq/cpufreq-dt.c b/kernel/drivers/cpufreq/cpufreq-dt.c
index bab67db54..90d64081d 100644
--- a/kernel/drivers/cpufreq/cpufreq-dt.c
+++ b/kernel/drivers/cpufreq/cpufreq-dt.c
@@ -36,6 +36,12 @@ struct private_data {
 	unsigned int voltage_tolerance; /* in percentage */
 };
 
+static struct freq_attr *cpufreq_dt_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,   /* Extra space for boost-attr if required */
+	NULL,
+};
+
 static int set_target(struct cpufreq_policy *policy, unsigned int index)
 {
 	struct dev_pm_opp *opp;
@@ -184,15 +190,16 @@ try_again:
 
 static int cpufreq_init(struct cpufreq_policy *policy)
 {
-	struct cpufreq_dt_platform_data *pd;
 	struct cpufreq_frequency_table *freq_table;
 	struct device_node *np;
 	struct private_data *priv;
 	struct device *cpu_dev;
 	struct regulator *cpu_reg;
 	struct clk *cpu_clk;
+	struct dev_pm_opp *suspend_opp;
 	unsigned long min_uV = ~0, max_uV = 0;
 	unsigned int transition_latency;
+	bool need_update = false;
 	int ret;
 
 	ret = allocate_resources(policy->cpu, &cpu_dev, &cpu_reg, &cpu_clk);
@@ -208,8 +215,30 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_put_reg_clk;
 	}
 
-	/* OPPs might be populated at runtime, don't check for error here */
-	of_init_opp_table(cpu_dev);
+	/* Get OPP-sharing information from "operating-points-v2" bindings */
+	ret = dev_pm_opp_of_get_sharing_cpus(cpu_dev, policy->cpus);
+	if (ret) {
+		/*
+		 * operating-points-v2 not supported, fallback to old method of
+		 * finding shared-OPPs for backward compatibility.
+		 */
+		if (ret == -ENOENT)
+			need_update = true;
+		else
+			goto out_node_put;
+	}
+
+	/*
+	 * Initialize OPP tables for all policy->cpus. They will be shared by
+	 * all CPUs which have marked their CPUs shared with OPP bindings.
+	 *
+	 * For platforms not using operating-points-v2 bindings, we do this
+	 * before updating policy->cpus. Otherwise, we will end up creating
+	 * duplicate OPPs for policy->cpus.
+	 *
+	 * OPPs might be populated at runtime, don't check for error here
+	 */
+	dev_pm_opp_of_cpumask_add_table(policy->cpus);
 
 	/*
 	 * But we need OPP table to function so if it is not there let's
@@ -222,6 +251,26 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_opp;
 	}
 
+	if (need_update) {
+		struct cpufreq_dt_platform_data *pd = cpufreq_get_driver_data();
+
+		if (!pd || !pd->independent_clocks)
+			cpumask_setall(policy->cpus);
+
+		/*
+		 * OPP tables are initialized only for policy->cpu, do it for
+		 * others as well.
+		 */
+		ret = dev_pm_opp_set_sharing_cpus(cpu_dev, policy->cpus);
+		if (ret)
+			dev_err(cpu_dev, "%s: failed to mark OPPs as shared: %d\n",
+				__func__, ret);
+
+		of_property_read_u32(np, "clock-latency", &transition_latency);
+	} else {
+		transition_latency = dev_pm_opp_get_max_clock_latency(cpu_dev);
+	}
+
 	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
 	if (!priv) {
 		ret = -ENOMEM;
@@ -230,7 +279,7 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 
 	of_property_read_u32(np, "voltage-tolerance", &priv->voltage_tolerance);
 
-	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+	if (!transition_latency)
 		transition_latency = CPUFREQ_ETERNAL;
 
 	if (!IS_ERR(cpu_reg)) {
@@ -255,7 +304,8 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 			rcu_read_unlock();
 
 			tol_uV = opp_uV * priv->voltage_tolerance / 100;
-			if (regulator_is_supported_voltage(cpu_reg, opp_uV,
+			if (regulator_is_supported_voltage(cpu_reg,
+							   opp_uV - tol_uV,
 							   opp_uV + tol_uV)) {
 				if (opp_uV < min_uV)
 					min_uV = opp_uV;
@@ -284,6 +334,13 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 	policy->driver_data = priv;
 
 	policy->clk = cpu_clk;
+
+	rcu_read_lock();
+	suspend_opp = dev_pm_opp_get_suspend_opp(cpu_dev);
+	if (suspend_opp)
+		policy->suspend_freq = dev_pm_opp_get_freq(suspend_opp) / 1000;
+	rcu_read_unlock();
+
 	ret = cpufreq_table_validate_and_show(policy, freq_table);
 	if (ret) {
 		dev_err(cpu_dev, "%s: invalid frequency table: %d\n", __func__,
@@ -291,11 +348,16 @@ static int cpufreq_init(struct cpufreq_policy *policy)
 		goto out_free_cpufreq_table;
 	}
 
-	policy->cpuinfo.transition_latency = transition_latency;
+	/* Support turbo/boost mode */
+	if (policy_has_boost_freq(policy)) {
+		/* This gets disabled by core on driver unregister */
+		ret = cpufreq_enable_boost_support();
+		if (ret)
+			goto out_free_cpufreq_table;
+		cpufreq_dt_attr[1] = &cpufreq_freq_attr_scaling_boost_freqs;
+	}
 
-	pd = cpufreq_get_driver_data();
-	if (!pd || !pd->independent_clocks)
-		cpumask_setall(policy->cpus);
+	policy->cpuinfo.transition_latency = transition_latency;
 
 	of_node_put(np);
 
@@ -306,7 +368,8 @@ out_free_cpufreq_table:
 out_free_priv:
 	kfree(priv);
 out_free_opp:
-	of_free_opp_table(cpu_dev);
+	dev_pm_opp_of_cpumask_remove_table(policy->cpus);
+out_node_put:
 	of_node_put(np);
 out_put_reg_clk:
 	clk_put(cpu_clk);
@@ -322,7 +385,7 @@ static int cpufreq_exit(struct cpufreq_policy *policy)
 
 	cpufreq_cooling_unregister(priv->cdev);
 	dev_pm_opp_free_cpufreq_table(priv->cpu_dev, &policy->freq_table);
-	of_free_opp_table(priv->cpu_dev);
+	dev_pm_opp_of_cpumask_remove_table(policy->related_cpus);
 	clk_put(policy->clk);
 	if (!IS_ERR(priv->cpu_reg))
 		regulator_put(priv->cpu_reg);
@@ -367,7 +430,8 @@ static struct cpufreq_driver dt_cpufreq_driver = {
 	.exit = cpufreq_exit,
 	.ready = cpufreq_ready,
 	.name = "cpufreq-dt",
-	.attr = cpufreq_generic_attr,
+	.attr = cpufreq_dt_attr,
+	.suspend = cpufreq_generic_suspend,
 };
 
 static int dt_cpufreq_probe(struct platform_device *pdev)
@@ -416,6 +480,7 @@ static struct platform_driver dt_cpufreq_platdrv = {
 };
 module_platform_driver(dt_cpufreq_platdrv);
 
+MODULE_ALIAS("platform:cpufreq-dt");
 MODULE_AUTHOR("Viresh Kumar <viresh.kumar@linaro.org>");
 MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
 MODULE_DESCRIPTION("Generic cpufreq driver");
diff --git a/kernel/drivers/cpufreq/cpufreq-nforce2.c b/kernel/drivers/cpufreq/cpufreq-nforce2.c
index a2258090b..db69eeb50 100644
--- a/kernel/drivers/cpufreq/cpufreq-nforce2.c
+++ b/kernel/drivers/cpufreq/cpufreq-nforce2.c
@@ -414,7 +414,7 @@ static int nforce2_detect_chipset(void)
  * nforce2_init - initializes the nForce2 CPUFreq driver
  *
  * Initializes the nForce2 FSB support. Returns -ENODEV on unsupported
- * devices, -EINVAL on problems during initiatization, and zero on
+ * devices, -EINVAL on problems during initialization, and zero on
  * success.
  */
 static int __init nforce2_init(void)
diff --git a/kernel/drivers/cpufreq/cpufreq.c b/kernel/drivers/cpufreq/cpufreq.c
index ce1d93e93..8412ce5f9 100644
--- a/kernel/drivers/cpufreq/cpufreq.c
+++ b/kernel/drivers/cpufreq/cpufreq.c
@@ -31,10 +31,62 @@
 #include <linux/tick.h>
 #include <trace/events/power.h>
 
-/* Macros to iterate over lists */
-/* Iterate over online CPUs policies */
 static LIST_HEAD(cpufreq_policy_list);
-#define for_each_policy(__policy)				\
+
+static inline bool policy_is_inactive(struct cpufreq_policy *policy)
+{
+	return cpumask_empty(policy->cpus);
+}
+
+static bool suitable_policy(struct cpufreq_policy *policy, bool active)
+{
+	return active == !policy_is_inactive(policy);
+}
+
+/* Finds Next Acive/Inactive policy */
+static struct cpufreq_policy *next_policy(struct cpufreq_policy *policy,
+					  bool active)
+{
+	do {
+		policy = list_next_entry(policy, policy_list);
+
+		/* No more policies in the list */
+		if (&policy->policy_list == &cpufreq_policy_list)
+			return NULL;
+	} while (!suitable_policy(policy, active));
+
+	return policy;
+}
+
+static struct cpufreq_policy *first_policy(bool active)
+{
+	struct cpufreq_policy *policy;
+
+	/* No policies in the list */
+	if (list_empty(&cpufreq_policy_list))
+		return NULL;
+
+	policy = list_first_entry(&cpufreq_policy_list, typeof(*policy),
+				  policy_list);
+
+	if (!suitable_policy(policy, active))
+		policy = next_policy(policy, active);
+
+	return policy;
+}
+
+/* Macros to iterate over CPU policies */
+#define for_each_suitable_policy(__policy, __active)	\
+	for (__policy = first_policy(__active);		\
+	     __policy;					\
+	     __policy = next_policy(__policy, __active))
+
+#define for_each_active_policy(__policy)		\
+	for_each_suitable_policy(__policy, true)
+#define for_each_inactive_policy(__policy)		\
+	for_each_suitable_policy(__policy, false)
+
+#define for_each_policy(__policy)			\
 	list_for_each_entry(__policy, &cpufreq_policy_list, policy_list)
 
 /* Iterate over governors */
@@ -49,13 +101,9 @@ static LIST_HEAD(cpufreq_governor_list);
  */
 static struct cpufreq_driver *cpufreq_driver;
 static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data);
-static DEFINE_PER_CPU(struct cpufreq_policy *, cpufreq_cpu_data_fallback);
 static DEFINE_RWLOCK(cpufreq_driver_lock);
 DEFINE_MUTEX(cpufreq_governor_lock);
 
-/* This one keeps track of the previously set governor of a removed CPU */
-static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
-
 /* Flag to suspend/resume CPUFreq governors */
 static bool cpufreq_suspended;
 
@@ -115,6 +163,15 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy)
 }
 EXPORT_SYMBOL_GPL(get_governor_parent_kobj);
 
+struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
+
+	return policy && !policy_is_inactive(policy) ?
+		policy->freq_table : NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
+
 static inline u64 get_cpu_idle_time_jiffy(unsigned int cpu, u64 *wall)
 {
 	u64 idle_time;
@@ -172,7 +229,7 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 	policy->cpuinfo.transition_latency = transition_latency;
 
 	/*
-	 * The driver only supports the SMP configuartion where all processors
+	 * The driver only supports the SMP configuration where all processors
 	 * share the clock and voltage and clock.
 	 */
 	cpumask_setall(policy->cpus);
@@ -181,10 +238,18 @@ int cpufreq_generic_init(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_init);
 
-unsigned int cpufreq_generic_get(unsigned int cpu)
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
+	return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL;
+}
+EXPORT_SYMBOL_GPL(cpufreq_cpu_get_raw);
+
+unsigned int cpufreq_generic_get(unsigned int cpu)
+{
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
+
 	if (!policy || IS_ERR(policy->clk)) {
 		pr_err("%s: No %s associated to cpu: %d\n",
 		       __func__, policy ? "clk" : "policy", cpu);
@@ -195,18 +260,25 @@ unsigned int cpufreq_generic_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_get);
 
-/* Only for cpufreq core internal use */
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
-{
-	return per_cpu(cpufreq_cpu_data, cpu);
-}
-
+/**
+ * cpufreq_cpu_get: returns policy for a cpu and marks it busy.
+ *
+ * @cpu: cpu to find policy for.
+ *
+ * This returns policy for 'cpu', returns NULL if it doesn't exist.
+ * It also increments the kobject reference count to mark it busy and so would
+ * require a corresponding call to cpufreq_cpu_put() to decrement it back.
+ * If corresponding call cpufreq_cpu_put() isn't made, the policy wouldn't be
+ * freed as that depends on the kobj count.
+ *
+ * Return: A valid policy on success, otherwise NULL on failure.
+ */
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = NULL;
 	unsigned long flags;
 
-	if (cpu >= nr_cpu_ids)
+	if (WARN_ON(cpu >= nr_cpu_ids))
 		return NULL;
 
 	/* get the cpufreq driver */
@@ -214,7 +286,7 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 
 	if (cpufreq_driver) {
 		/* get the CPU */
-		policy = per_cpu(cpufreq_cpu_data, cpu);
+		policy = cpufreq_cpu_get_raw(cpu);
 		if (policy)
 			kobject_get(&policy->kobj);
 	}
@@ -225,6 +297,14 @@ struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(cpufreq_cpu_get);
 
+/**
+ * cpufreq_cpu_put: Decrements the usage count of a policy
+ *
+ * @policy: policy earlier returned by cpufreq_cpu_get().
+ *
+ * This decrements the kobject reference count incremented earlier by calling
+ * cpufreq_cpu_get().
+ */
 void cpufreq_cpu_put(struct cpufreq_policy *policy)
 {
 	kobject_put(&policy->kobj);
@@ -440,9 +520,6 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 {
 	int err = -EINVAL;
 
-	if (!cpufreq_driver)
-		goto out;
-
 	if (cpufreq_driver->setpolicy) {
 		if (!strncasecmp(str_governor, "performance", CPUFREQ_NAME_LEN)) {
 			*policy = CPUFREQ_POLICY_PERFORMANCE;
@@ -477,7 +554,6 @@ static int cpufreq_parse_governor(char *str_governor, unsigned int *policy,
 
 		mutex_unlock(&cpufreq_governor_mutex);
 	}
-out:
 	return err;
 }
 
@@ -526,9 +602,7 @@ static ssize_t store_##file_name					\
 	int ret, temp;							\
 	struct cpufreq_policy new_policy;				\
 									\
-	ret = cpufreq_get_policy(&new_policy, policy->cpu);		\
-	if (ret)							\
-		return -EINVAL;						\
+	memcpy(&new_policy, policy, sizeof(*policy));			\
 									\
 	ret = sscanf(buf, "%u", &new_policy.object);			\
 	if (ret != 1)							\
@@ -582,9 +656,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 	char	str_governor[16];
 	struct cpufreq_policy new_policy;
 
-	ret = cpufreq_get_policy(&new_policy, policy->cpu);
-	if (ret)
-		return ret;
+	memcpy(&new_policy, policy, sizeof(*policy));
 
 	ret = sscanf(buf, "%15s", str_governor);
 	if (ret != 1)
@@ -595,14 +667,7 @@ static ssize_t store_scaling_governor(struct cpufreq_policy *policy,
 		return -EINVAL;
 
 	ret = cpufreq_set_policy(policy, &new_policy);
-
-	policy->user_policy.policy = policy->policy;
-	policy->user_policy.governor = policy->governor;
-
-	if (ret)
-		return ret;
-	else
-		return count;
+	return ret ? ret : count;
 }
 
 /**
@@ -808,73 +873,61 @@ static struct kobj_type ktype_cpufreq = {
 	.release	= cpufreq_sysfs_release,
 };
 
-struct kobject *cpufreq_global_kobject;
-EXPORT_SYMBOL(cpufreq_global_kobject);
+static int add_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
+{
+	struct device *cpu_dev;
 
-static int cpufreq_global_kobject_usage;
+	pr_debug("%s: Adding symlink for CPU: %u\n", __func__, cpu);
 
-int cpufreq_get_global_kobject(void)
-{
-	if (!cpufreq_global_kobject_usage++)
-		return kobject_add(cpufreq_global_kobject,
-				&cpu_subsys.dev_root->kobj, "%s", "cpufreq");
+	if (!policy)
+		return 0;
 
-	return 0;
-}
-EXPORT_SYMBOL(cpufreq_get_global_kobject);
+	cpu_dev = get_cpu_device(cpu);
+	if (WARN_ON(!cpu_dev))
+		return 0;
 
-void cpufreq_put_global_kobject(void)
-{
-	if (!--cpufreq_global_kobject_usage)
-		kobject_del(cpufreq_global_kobject);
+	return sysfs_create_link(&cpu_dev->kobj, &policy->kobj, "cpufreq");
 }
-EXPORT_SYMBOL(cpufreq_put_global_kobject);
 
-int cpufreq_sysfs_create_file(const struct attribute *attr)
+static void remove_cpu_dev_symlink(struct cpufreq_policy *policy, int cpu)
 {
-	int ret = cpufreq_get_global_kobject();
+	struct device *cpu_dev;
 
-	if (!ret) {
-		ret = sysfs_create_file(cpufreq_global_kobject, attr);
-		if (ret)
-			cpufreq_put_global_kobject();
-	}
+	pr_debug("%s: Removing symlink for CPU: %u\n", __func__, cpu);
 
-	return ret;
-}
-EXPORT_SYMBOL(cpufreq_sysfs_create_file);
+	cpu_dev = get_cpu_device(cpu);
+	if (WARN_ON(!cpu_dev))
+		return;
 
-void cpufreq_sysfs_remove_file(const struct attribute *attr)
-{
-	sysfs_remove_file(cpufreq_global_kobject, attr);
-	cpufreq_put_global_kobject();
+	sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
 }
-EXPORT_SYMBOL(cpufreq_sysfs_remove_file);
 
-/* symlink affected CPUs */
+/* Add/remove symlinks for all related CPUs */
 static int cpufreq_add_dev_symlink(struct cpufreq_policy *policy)
 {
 	unsigned int j;
 	int ret = 0;
 
-	for_each_cpu(j, policy->cpus) {
-		struct device *cpu_dev;
-
-		if (j == policy->cpu)
-			continue;
-
-		pr_debug("Adding link for CPU: %u\n", j);
-		cpu_dev = get_cpu_device(j);
-		ret = sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
-					"cpufreq");
+	/* Some related CPUs might not be present (physically hotplugged) */
+	for_each_cpu(j, policy->real_cpus) {
+		ret = add_cpu_dev_symlink(policy, j);
 		if (ret)
 			break;
 	}
+
 	return ret;
 }
 
-static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
-				     struct device *dev)
+static void cpufreq_remove_dev_symlink(struct cpufreq_policy *policy)
+{
+	unsigned int j;
+
+	/* Some related CPUs might not be present (physically hotplugged) */
+	for_each_cpu(j, policy->real_cpus)
+		remove_cpu_dev_symlink(policy, j);
+}
+
+static int cpufreq_add_dev_interface(struct cpufreq_policy *policy)
 {
 	struct freq_attr **drv_attr;
 	int ret = 0;
@@ -906,16 +959,15 @@ static int cpufreq_add_dev_interface(struct cpufreq_policy *policy,
 	return cpufreq_add_dev_symlink(policy);
 }
 
-static void cpufreq_init_policy(struct cpufreq_policy *policy)
+static int cpufreq_init_policy(struct cpufreq_policy *policy)
 {
 	struct cpufreq_governor *gov = NULL;
 	struct cpufreq_policy new_policy;
-	int ret = 0;
 
 	memcpy(&new_policy, policy, sizeof(*policy));
 
 	/* Update governor of new_policy to the governor used before hotplug */
-	gov = find_governor(per_cpu(cpufreq_cpu_governor, policy->cpu));
+	gov = find_governor(policy->last_governor);
 	if (gov)
 		pr_debug("Restoring governor %s for cpu %d\n",
 				policy->governor->name, policy->cpu);
@@ -924,24 +976,25 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy)
 
 	new_policy.governor = gov;
 
-	/* Use the default policy if its valid. */
-	if (cpufreq_driver->setpolicy)
-		cpufreq_parse_governor(gov->name, &new_policy.policy, NULL);
-
-	/* set default policy */
-	ret = cpufreq_set_policy(policy, &new_policy);
-	if (ret) {
-		pr_debug("setting policy failed\n");
-		if (cpufreq_driver->exit)
-			cpufreq_driver->exit(policy);
+	/* Use the default policy if there is no last_policy. */
+	if (cpufreq_driver->setpolicy) {
+		if (policy->last_policy)
+			new_policy.policy = policy->last_policy;
+		else
+			cpufreq_parse_governor(gov->name, &new_policy.policy,
+					       NULL);
 	}
+	/* set default policy */
+	return cpufreq_set_policy(policy, &new_policy);
 }
 
-static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
-				  unsigned int cpu, struct device *dev)
+static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu)
 {
 	int ret = 0;
-	unsigned long flags;
+
+	/* Has this CPU been taken care of already? */
+	if (cpumask_test_cpu(cpu, policy->cpus))
+		return 0;
 
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
@@ -952,13 +1005,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 	}
 
 	down_write(&policy->rwsem);
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-
 	cpumask_set_cpu(cpu, policy->cpus);
-	per_cpu(cpufreq_cpu_data, cpu) = policy;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
 	up_write(&policy->rwsem);
 
 	if (has_target()) {
@@ -972,29 +1019,16 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy,
 		}
 	}
 
-	return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq");
+	return 0;
 }
 
-static struct cpufreq_policy *cpufreq_policy_restore(unsigned int cpu)
+static struct cpufreq_policy *cpufreq_policy_alloc(unsigned int cpu)
 {
+	struct device *dev = get_cpu_device(cpu);
 	struct cpufreq_policy *policy;
-	unsigned long flags;
-
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
 
-	policy = per_cpu(cpufreq_cpu_data_fallback, cpu);
-
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	if (policy)
-		policy->governor = NULL;
-
-	return policy;
-}
-
-static struct cpufreq_policy *cpufreq_policy_alloc(void)
-{
-	struct cpufreq_policy *policy;
+	if (WARN_ON(!dev))
+		return NULL;
 
 	policy = kzalloc(sizeof(*policy), GFP_KERNEL);
 	if (!policy)
@@ -1006,6 +1040,10 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
 		goto err_free_cpumask;
 
+	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
+		goto err_free_rcpumask;
+
+	kobject_init(&policy->kobj, &ktype_cpufreq);
 	INIT_LIST_HEAD(&policy->policy_list);
 	init_rwsem(&policy->rwsem);
 	spin_lock_init(&policy->transition_lock);
@@ -1013,8 +1051,11 @@ static struct cpufreq_policy *cpufreq_policy_alloc(void)
 	init_completion(&policy->kobj_unregister);
 	INIT_WORK(&policy->update, handle_update);
 
+	policy->cpu = cpu;
 	return policy;
 
+err_free_rcpumask:
+	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
 	free_cpumask_var(policy->cpus);
 err_free_policy:
@@ -1023,18 +1064,20 @@ err_free_policy:
 	return NULL;
 }
 
-static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
+static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy, bool notify)
 {
 	struct kobject *kobj;
 	struct completion *cmp;
 
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_REMOVE_POLICY, policy);
+	if (notify)
+		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
+					     CPUFREQ_REMOVE_POLICY, policy);
 
-	down_read(&policy->rwsem);
+	down_write(&policy->rwsem);
+	cpufreq_remove_dev_symlink(policy);
 	kobj = &policy->kobj;
 	cmp = &policy->kobj_unregister;
-	up_read(&policy->rwsem);
+	up_write(&policy->rwsem);
 	kobject_put(kobj);
 
 	/*
@@ -1047,88 +1090,56 @@ static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy)
 	pr_debug("wait complete\n");
 }
 
-static void cpufreq_policy_free(struct cpufreq_policy *policy)
-{
-	free_cpumask_var(policy->related_cpus);
-	free_cpumask_var(policy->cpus);
-	kfree(policy);
-}
-
-static int update_policy_cpu(struct cpufreq_policy *policy, unsigned int cpu,
-			     struct device *cpu_dev)
+static void cpufreq_policy_free(struct cpufreq_policy *policy, bool notify)
 {
-	int ret;
-
-	if (WARN_ON(cpu == policy->cpu))
-		return 0;
+	unsigned long flags;
+	int cpu;
 
-	/* Move kobject to the new policy->cpu */
-	ret = kobject_move(&policy->kobj, &cpu_dev->kobj);
-	if (ret) {
-		pr_err("%s: Failed to move kobj: %d\n", __func__, ret);
-		return ret;
-	}
+	/* Remove policy from list */
+	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	list_del(&policy->policy_list);
 
-	down_write(&policy->rwsem);
-	policy->cpu = cpu;
-	up_write(&policy->rwsem);
+	for_each_cpu(cpu, policy->related_cpus)
+		per_cpu(cpufreq_cpu_data, cpu) = NULL;
+	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	return 0;
+	cpufreq_policy_put_kobj(policy, notify);
+	free_cpumask_var(policy->real_cpus);
+	free_cpumask_var(policy->related_cpus);
+	free_cpumask_var(policy->cpus);
+	kfree(policy);
 }
 
-static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
+static int cpufreq_online(unsigned int cpu)
 {
-	unsigned int j, cpu = dev->id;
-	int ret = -ENOMEM;
 	struct cpufreq_policy *policy;
+	bool new_policy;
 	unsigned long flags;
-	bool recover_policy = cpufreq_suspended;
-
-	if (cpu_is_offline(cpu))
-		return 0;
-
-	pr_debug("adding CPU %u\n", cpu);
+	unsigned int j;
+	int ret;
 
-	/* check whether a different CPU already registered this
-	 * CPU because it is in the same boat. */
-	policy = cpufreq_cpu_get_raw(cpu);
-	if (unlikely(policy))
-		return 0;
+	pr_debug("%s: bringing CPU%u online\n", __func__, cpu);
 
-	/* Check if this cpu was hot-unplugged earlier and has siblings */
-	read_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_policy(policy) {
-		if (cpumask_test_cpu(cpu, policy->related_cpus)) {
-			read_unlock_irqrestore(&cpufreq_driver_lock, flags);
-			ret = cpufreq_add_policy_cpu(policy, cpu, dev);
-			return ret;
-		}
-	}
-	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	/* Check if this CPU already has a policy to manage it */
+	policy = per_cpu(cpufreq_cpu_data, cpu);
+	if (policy) {
+		WARN_ON(!cpumask_test_cpu(cpu, policy->related_cpus));
+		if (!policy_is_inactive(policy))
+			return cpufreq_add_policy_cpu(policy, cpu);
 
-	/*
-	 * Restore the saved policy when doing light-weight init and fall back
-	 * to the full init if that fails.
-	 */
-	policy = recover_policy ? cpufreq_policy_restore(cpu) : NULL;
-	if (!policy) {
-		recover_policy = false;
-		policy = cpufreq_policy_alloc();
+		/* This is the only online CPU for the policy.  Start over. */
+		new_policy = false;
+		down_write(&policy->rwsem);
+		policy->cpu = cpu;
+		policy->governor = NULL;
+		up_write(&policy->rwsem);
+	} else {
+		new_policy = true;
+		policy = cpufreq_policy_alloc(cpu);
 		if (!policy)
-			goto nomem_out;
+			return -ENOMEM;
 	}
 
-	/*
-	 * In the resume path, since we restore a saved policy, the assignment
-	 * to policy->cpu is like an update of the existing policy, rather than
-	 * the creation of a brand new one. So we need to perform this update
-	 * by invoking update_policy_cpu().
-	 */
-	if (recover_policy && cpu != policy->cpu)
-		WARN_ON(update_policy_cpu(policy, cpu, dev));
-	else
-		policy->cpu = cpu;
-
 	cpumask_copy(policy->cpus, cpumask_of(cpu));
 
 	/* call driver. From then on the cpufreq must be able
@@ -1137,13 +1148,27 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	ret = cpufreq_driver->init(policy);
 	if (ret) {
 		pr_debug("initialization failed\n");
-		goto err_set_policy_cpu;
+		goto out_free_policy;
 	}
 
 	down_write(&policy->rwsem);
 
-	/* related cpus should atleast have policy->cpus */
-	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
+	if (new_policy) {
+		/* related_cpus should at least include policy->cpus. */
+		cpumask_copy(policy->related_cpus, policy->cpus);
+		/* Remember CPUs present at the policy creation time. */
+		cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
+
+		/* Name and add the kobject */
+		ret = kobject_add(&policy->kobj, cpufreq_global_kobject,
+				  "policy%u",
+				  cpumask_first(policy->related_cpus));
+		if (ret) {
+			pr_err("%s: failed to add policy->kobj: %d\n", __func__,
+			       ret);
+			goto out_exit_policy;
+		}
+	}
 
 	/*
 	 * affected cpus must always be the one, which are online. We aren't
@@ -1151,30 +1176,21 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	 */
 	cpumask_and(policy->cpus, policy->cpus, cpu_online_mask);
 
-	if (!recover_policy) {
+	if (new_policy) {
 		policy->user_policy.min = policy->min;
 		policy->user_policy.max = policy->max;
 
-		/* prepare interface data */
-		ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq,
-					   &dev->kobj, "cpufreq");
-		if (ret) {
-			pr_err("%s: failed to init policy->kobj: %d\n",
-			       __func__, ret);
-			goto err_init_policy_kobj;
-		}
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		for_each_cpu(j, policy->related_cpus)
+			per_cpu(cpufreq_cpu_data, j) = policy;
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 	}
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_cpu_data, j) = policy;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
 	if (cpufreq_driver->get && !cpufreq_driver->setpolicy) {
 		policy->cur = cpufreq_driver->get(policy->cpu);
 		if (!policy->cur) {
 			pr_err("%s: ->get() failed\n", __func__);
-			goto err_get_freq;
+			goto out_exit_policy;
 		}
 	}
 
@@ -1221,24 +1237,27 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				     CPUFREQ_START, policy);
 
-	if (!recover_policy) {
-		ret = cpufreq_add_dev_interface(policy, dev);
+	if (new_policy) {
+		ret = cpufreq_add_dev_interface(policy);
 		if (ret)
-			goto err_out_unregister;
+			goto out_exit_policy;
 		blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 				CPUFREQ_CREATE_POLICY, policy);
-	}
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	list_add(&policy->policy_list, &cpufreq_policy_list);
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
-	cpufreq_init_policy(policy);
+		write_lock_irqsave(&cpufreq_driver_lock, flags);
+		list_add(&policy->policy_list, &cpufreq_policy_list);
+		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	}
 
-	if (!recover_policy) {
-		policy->user_policy.policy = policy->policy;
-		policy->user_policy.governor = policy->governor;
+	ret = cpufreq_init_policy(policy);
+	if (ret) {
+		pr_err("%s: Failed to initialize policy for cpu: %d (%d)\n",
+		       __func__, cpu, ret);
+		/* cpufreq_policy_free() will notify based on this */
+		new_policy = false;
+		goto out_exit_policy;
 	}
+
 	up_write(&policy->rwsem);
 
 	kobject_uevent(&policy->kobj, KOBJ_ADD);
@@ -1251,182 +1270,122 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 
 	return 0;
 
-err_out_unregister:
-err_get_freq:
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	for_each_cpu(j, policy->cpus)
-		per_cpu(cpufreq_cpu_data, j) = NULL;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-	if (!recover_policy) {
-		kobject_put(&policy->kobj);
-		wait_for_completion(&policy->kobj_unregister);
-	}
-err_init_policy_kobj:
+out_exit_policy:
 	up_write(&policy->rwsem);
 
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
-err_set_policy_cpu:
-	if (recover_policy) {
-		/* Do not leave stale fallback data behind. */
-		per_cpu(cpufreq_cpu_data_fallback, cpu) = NULL;
-		cpufreq_policy_put_kobj(policy);
-	}
-	cpufreq_policy_free(policy);
-
-nomem_out:
+out_free_policy:
+	cpufreq_policy_free(policy, !new_policy);
 	return ret;
 }
 
 /**
- * cpufreq_add_dev - add a CPU device
- *
- * Adds the cpufreq interface for a CPU device.
- *
- * The Oracle says: try running cpufreq registration/unregistration concurrently
- * with with cpu hotplugging and all hell will break loose. Tried to clean this
- * mess up, but more thorough testing is needed. - Mathieu
+ * cpufreq_add_dev - the cpufreq interface for a CPU device.
+ * @dev: CPU device.
+ * @sif: Subsystem interface structure pointer (not used)
  */
 static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 {
-	return __cpufreq_add_dev(dev, sif);
-}
-
-static int __cpufreq_remove_dev_prepare(struct device *dev,
-					struct subsys_interface *sif)
-{
-	unsigned int cpu = dev->id, cpus;
+	unsigned cpu = dev->id;
 	int ret;
-	unsigned long flags;
-	struct cpufreq_policy *policy;
 
-	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
+	dev_dbg(dev, "%s: adding CPU%u\n", __func__, cpu);
 
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
+	if (cpu_online(cpu)) {
+		ret = cpufreq_online(cpu);
+	} else {
+		/*
+		 * A hotplug notifier will follow and we will handle it as CPU
+		 * online then.  For now, just create the sysfs link, unless
+		 * there is no policy or the link is already present.
+		 */
+		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
-	policy = per_cpu(cpufreq_cpu_data, cpu);
+		ret = policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus)
+			? add_cpu_dev_symlink(policy, cpu) : 0;
+	}
 
-	/* Save the policy somewhere when doing a light-weight tear-down */
-	if (cpufreq_suspended)
-		per_cpu(cpufreq_cpu_data_fallback, cpu) = policy;
+	return ret;
+}
 
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+static void cpufreq_offline_prepare(unsigned int cpu)
+{
+	struct cpufreq_policy *policy;
+
+	pr_debug("%s: unregistering CPU %u\n", __func__, cpu);
 
+	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
-		return -EINVAL;
+		return;
 	}
 
 	if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-		if (ret) {
+		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret)
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
-		}
-
-		strncpy(per_cpu(cpufreq_cpu_governor, cpu),
-			policy->governor->name, CPUFREQ_NAME_LEN);
 	}
 
-	down_read(&policy->rwsem);
-	cpus = cpumask_weight(policy->cpus);
-	up_read(&policy->rwsem);
-
-	if (cpu != policy->cpu) {
-		sysfs_remove_link(&dev->kobj, "cpufreq");
-	} else if (cpus > 1) {
+	down_write(&policy->rwsem);
+	cpumask_clear_cpu(cpu, policy->cpus);
+
+	if (policy_is_inactive(policy)) {
+		if (has_target())
+			strncpy(policy->last_governor, policy->governor->name,
+				CPUFREQ_NAME_LEN);
+		else
+			policy->last_policy = policy->policy;
+	} else if (cpu == policy->cpu) {
 		/* Nominate new CPU */
-		int new_cpu = cpumask_any_but(policy->cpus, cpu);
-		struct device *cpu_dev = get_cpu_device(new_cpu);
+		policy->cpu = cpumask_any(policy->cpus);
+	}
+	up_write(&policy->rwsem);
 
-		sysfs_remove_link(&cpu_dev->kobj, "cpufreq");
-		ret = update_policy_cpu(policy, new_cpu, cpu_dev);
-		if (ret) {
-			if (sysfs_create_link(&cpu_dev->kobj, &policy->kobj,
-					      "cpufreq"))
-				pr_err("%s: Failed to restore kobj link to cpu:%d\n",
-				       __func__, cpu_dev->id);
-			return ret;
-		}
+	/* Start governor again for active policy */
+	if (!policy_is_inactive(policy)) {
+		if (has_target()) {
+			int ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+			if (!ret)
+				ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
 
-		if (!cpufreq_suspended)
-			pr_debug("%s: policy Kobject moved to cpu: %d from: %d\n",
-				 __func__, new_cpu, cpu);
+			if (ret)
+				pr_err("%s: Failed to start governor\n", __func__);
+		}
 	} else if (cpufreq_driver->stop_cpu) {
 		cpufreq_driver->stop_cpu(policy);
 	}
-
-	return 0;
 }
 
-static int __cpufreq_remove_dev_finish(struct device *dev,
-				       struct subsys_interface *sif)
+static void cpufreq_offline_finish(unsigned int cpu)
 {
-	unsigned int cpu = dev->id, cpus;
-	int ret;
-	unsigned long flags;
-	struct cpufreq_policy *policy;
-
-	write_lock_irqsave(&cpufreq_driver_lock, flags);
-	policy = per_cpu(cpufreq_cpu_data, cpu);
-	per_cpu(cpufreq_cpu_data, cpu) = NULL;
-	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
-		return -EINVAL;
+		return;
 	}
 
-	down_write(&policy->rwsem);
-	cpus = cpumask_weight(policy->cpus);
-
-	if (cpus > 1)
-		cpumask_clear_cpu(cpu, policy->cpus);
-	up_write(&policy->rwsem);
+	/* Only proceed for inactive policies */
+	if (!policy_is_inactive(policy))
+		return;
 
 	/* If cpu is last user of policy, free policy */
-	if (cpus == 1) {
-		if (has_target()) {
-			ret = __cpufreq_governor(policy,
-					CPUFREQ_GOV_POLICY_EXIT);
-			if (ret) {
-				pr_err("%s: Failed to exit governor\n",
-				       __func__);
-				return ret;
-			}
-		}
-
-		if (!cpufreq_suspended)
-			cpufreq_policy_put_kobj(policy);
-
-		/*
-		 * Perform the ->exit() even during light-weight tear-down,
-		 * since this is a core component, and is essential for the
-		 * subsequent light-weight ->init() to succeed.
-		 */
-		if (cpufreq_driver->exit)
-			cpufreq_driver->exit(policy);
-
-		/* Remove policy from list of active policies */
-		write_lock_irqsave(&cpufreq_driver_lock, flags);
-		list_del(&policy->policy_list);
-		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-
-		if (!cpufreq_suspended)
-			cpufreq_policy_free(policy);
-	} else if (has_target()) {
-		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
-		if (!ret)
-			ret = __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS);
-
-		if (ret) {
-			pr_err("%s: Failed to start governor\n", __func__);
-			return ret;
-		}
+	if (has_target()) {
+		int ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		if (ret)
+			pr_err("%s: Failed to exit governor\n", __func__);
 	}
 
-	return 0;
+	/*
+	 * Perform the ->exit() even during light-weight tear-down,
+	 * since this is a core component, and is essential for the
+	 * subsequent light-weight ->init() to succeed.
+	 */
+	if (cpufreq_driver->exit) {
+		cpufreq_driver->exit(policy);
+		policy->freq_table = NULL;
+	}
 }
 
 /**
@@ -1434,20 +1393,24 @@ static int __cpufreq_remove_dev_finish(struct device *dev,
  *
  * Removes the cpufreq interface for a CPU device.
  */
-static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
+static void cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id;
-	int ret;
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
-	if (cpu_is_offline(cpu))
-		return 0;
+	if (!policy)
+		return;
 
-	ret = __cpufreq_remove_dev_prepare(dev, sif);
+	if (cpu_online(cpu)) {
+		cpufreq_offline_prepare(cpu);
+		cpufreq_offline_finish(cpu);
+	}
 
-	if (!ret)
-		ret = __cpufreq_remove_dev_finish(dev, sif);
+	cpumask_clear_cpu(cpu, policy->real_cpus);
+	remove_cpu_dev_symlink(policy, cpu);
 
-	return ret;
+	if (cpumask_empty(policy->real_cpus))
+		cpufreq_policy_free(policy, true);
 }
 
 static void handle_update(struct work_struct *work)
@@ -1537,6 +1500,10 @@ static unsigned int __cpufreq_get(struct cpufreq_policy *policy)
 
 	ret_freq = cpufreq_driver->get(policy->cpu);
 
+	/* Updating inactive policies is invalid, so avoid doing that. */
+	if (unlikely(policy_is_inactive(policy)))
+		return ret_freq;
+
 	if (ret_freq && policy->cur &&
 		!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
 		/* verify no discrepancy between actual and
@@ -1589,8 +1556,8 @@ int cpufreq_generic_suspend(struct cpufreq_policy *policy)
 	int ret;
 
 	if (!policy->suspend_freq) {
-		pr_err("%s: suspend_freq can't be zero\n", __func__);
-		return -EINVAL;
+		pr_debug("%s: suspend_freq not defined\n", __func__);
+		return 0;
 	}
 
 	pr_debug("%s: Setting suspend-freq: %u\n", __func__,
@@ -1626,7 +1593,7 @@ void cpufreq_suspend(void)
 
 	pr_debug("%s: Suspending Governors\n", __func__);
 
-	for_each_policy(policy) {
+	for_each_active_policy(policy) {
 		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
 			pr_err("%s: Failed to stop governor for policy: %p\n",
 				__func__, policy);
@@ -1660,7 +1627,7 @@ void cpufreq_resume(void)
 
 	pr_debug("%s: Resuming Governors\n", __func__);
 
-	for_each_policy(policy) {
+	for_each_active_policy(policy) {
 		if (cpufreq_driver->resume && cpufreq_driver->resume(policy))
 			pr_err("%s: Failed to resume driver: %p\n", __func__,
 				policy);
@@ -1861,7 +1828,7 @@ static int __target_index(struct cpufreq_policy *policy,
 		 * Failed after setting to intermediate freq? Driver should have
 		 * reverted back to initial frequency and so should we. Check
 		 * here for intermediate_freq instead of get_intermediate, in
-		 * case we have't switched to intermediate freq at all.
+		 * case we haven't switched to intermediate freq at all.
 		 */
 		if (unlikely(retval && intermediate_freq)) {
 			freqs.old = intermediate_freq;
@@ -1994,8 +1961,7 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 		if (!try_module_get(policy->governor->owner))
 			return -EINVAL;
 
-	pr_debug("__cpufreq_governor for CPU %u, event %u\n",
-		 policy->cpu, event);
+	pr_debug("%s: for CPU %u, event %u\n", __func__, policy->cpu, event);
 
 	mutex_lock(&cpufreq_governor_lock);
 	if ((policy->governor_enabled && event == CPUFREQ_GOV_START)
@@ -2062,7 +2028,8 @@ EXPORT_SYMBOL_GPL(cpufreq_register_governor);
 
 void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 {
-	int cpu;
+	struct cpufreq_policy *policy;
+	unsigned long flags;
 
 	if (!governor)
 		return;
@@ -2070,12 +2037,15 @@ void cpufreq_unregister_governor(struct cpufreq_governor *governor)
 	if (cpufreq_disabled())
 		return;
 
-	for_each_present_cpu(cpu) {
-		if (cpu_online(cpu))
-			continue;
-		if (!strcmp(per_cpu(cpufreq_cpu_governor, cpu), governor->name))
-			strcpy(per_cpu(cpufreq_cpu_governor, cpu), "\0");
+	/* clear last_governor for all inactive policies */
+	read_lock_irqsave(&cpufreq_driver_lock, flags);
+	for_each_inactive_policy(policy) {
+		if (!strcmp(policy->last_governor, governor->name)) {
+			policy->governor = NULL;
+			strcpy(policy->last_governor, "\0");
+		}
 	}
+	read_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	mutex_lock(&cpufreq_governor_mutex);
 	list_del(&governor->governor_list);
@@ -2128,7 +2098,11 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 
 	memcpy(&new_policy->cpuinfo, &policy->cpuinfo, sizeof(policy->cpuinfo));
 
-	if (new_policy->min > policy->max || new_policy->max < policy->min)
+	/*
+	* This check works well when we store new min/max freq attributes,
+	* because new_policy is a copy of policy with one field updated.
+	*/
+	if (new_policy->min > new_policy->max)
 		return -EINVAL;
 
 	/* verify the cpu speed can be set within this limit */
@@ -2140,10 +2114,6 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
 			CPUFREQ_ADJUST, new_policy);
 
-	/* adjust if necessary - hardware incompatibility*/
-	blocking_notifier_call_chain(&cpufreq_policy_notifier_list,
-			CPUFREQ_INCOMPATIBLE, new_policy);
-
 	/*
 	 * verify the cpu speed can be set within this limit, which might be
 	 * different to the first one
@@ -2177,16 +2147,31 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	old_gov = policy->governor;
 	/* end old governor */
 	if (old_gov) {
-		__cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
+		if (ret) {
+			/* This can happen due to race with other operations */
+			pr_debug("%s: Failed to Stop Governor: %s (%d)\n",
+				 __func__, old_gov->name, ret);
+			return ret;
+		}
+
 		up_write(&policy->rwsem);
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
 		down_write(&policy->rwsem);
+
+		if (ret) {
+			pr_err("%s: Failed to Exit Governor: %s (%d)\n",
+			       __func__, old_gov->name, ret);
+			return ret;
+		}
 	}
 
 	/* start new governor */
 	policy->governor = new_policy->governor;
-	if (!__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT)) {
-		if (!__cpufreq_governor(policy, CPUFREQ_GOV_START))
+	ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
+	if (!ret) {
+		ret = __cpufreq_governor(policy, CPUFREQ_GOV_START);
+		if (!ret)
 			goto out;
 
 		up_write(&policy->rwsem);
@@ -2198,11 +2183,13 @@ static int cpufreq_set_policy(struct cpufreq_policy *policy,
 	pr_debug("starting governor %s failed\n", policy->governor->name);
 	if (old_gov) {
 		policy->governor = old_gov;
-		__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT);
-		__cpufreq_governor(policy, CPUFREQ_GOV_START);
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_POLICY_INIT))
+			policy->governor = NULL;
+		else
+			__cpufreq_governor(policy, CPUFREQ_GOV_START);
 	}
 
-	return -EINVAL;
+	return ret;
 
  out:
 	pr_debug("governor: change or update limits\n");
@@ -2231,8 +2218,6 @@ int cpufreq_update_policy(unsigned int cpu)
 	memcpy(&new_policy, policy, sizeof(*policy));
 	new_policy.min = policy->user_policy.min;
 	new_policy.max = policy->user_policy.max;
-	new_policy.policy = policy->user_policy.policy;
-	new_policy.governor = policy->user_policy.governor;
 
 	/*
 	 * BIOS might change freq behind our back
@@ -2268,27 +2253,23 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 					unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
-	struct device *dev;
 
-	dev = get_cpu_device(cpu);
-	if (dev) {
-		switch (action & ~CPU_TASKS_FROZEN) {
-		case CPU_ONLINE:
-			__cpufreq_add_dev(dev, NULL);
-			break;
+	switch (action & ~CPU_TASKS_FROZEN) {
+	case CPU_ONLINE:
+		cpufreq_online(cpu);
+		break;
 
-		case CPU_DOWN_PREPARE:
-			__cpufreq_remove_dev_prepare(dev, NULL);
-			break;
+	case CPU_DOWN_PREPARE:
+		cpufreq_offline_prepare(cpu);
+		break;
 
-		case CPU_POST_DEAD:
-			__cpufreq_remove_dev_finish(dev, NULL);
-			break;
+	case CPU_POST_DEAD:
+		cpufreq_offline_finish(cpu);
+		break;
 
-		case CPU_DOWN_FAILED:
-			__cpufreq_add_dev(dev, NULL);
-			break;
-		}
+	case CPU_DOWN_FAILED:
+		cpufreq_online(cpu);
+		break;
 	}
 	return NOTIFY_OK;
 }
@@ -2306,7 +2287,7 @@ static int cpufreq_boost_set_sw(int state)
 	struct cpufreq_policy *policy;
 	int ret = -EINVAL;
 
-	for_each_policy(policy) {
+	for_each_active_policy(policy) {
 		freq_table = cpufreq_frequency_get_table(policy->cpu);
 		if (freq_table) {
 			ret = cpufreq_frequency_table_cpuinfo(policy,
@@ -2358,6 +2339,49 @@ int cpufreq_boost_supported(void)
 }
 EXPORT_SYMBOL_GPL(cpufreq_boost_supported);
 
+static int create_boost_sysfs_file(void)
+{
+	int ret;
+
+	if (!cpufreq_boost_supported())
+		return 0;
+
+	/*
+	 * Check if driver provides function to enable boost -
+	 * if not, use cpufreq_boost_set_sw as default
+	 */
+	if (!cpufreq_driver->set_boost)
+		cpufreq_driver->set_boost = cpufreq_boost_set_sw;
+
+	ret = sysfs_create_file(cpufreq_global_kobject, &boost.attr);
+	if (ret)
+		pr_err("%s: cannot register global BOOST sysfs file\n",
+		       __func__);
+
+	return ret;
+}
+
+static void remove_boost_sysfs_file(void)
+{
+	if (cpufreq_boost_supported())
+		sysfs_remove_file(cpufreq_global_kobject, &boost.attr);
+}
+
+int cpufreq_enable_boost_support(void)
+{
+	if (!cpufreq_driver)
+		return -EINVAL;
+
+	if (cpufreq_boost_supported())
+		return 0;
+
+	cpufreq_driver->boost_supported = true;
+
+	/* This will get removed on driver unregister */
+	return create_boost_sysfs_file();
+}
+EXPORT_SYMBOL_GPL(cpufreq_enable_boost_support);
+
 int cpufreq_boost_enabled(void)
 {
 	return cpufreq_driver->boost_enabled;
@@ -2396,10 +2420,14 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 
 	pr_debug("trying to register driver %s\n", driver_data->name);
 
+	/* Protect against concurrent CPU online/offline. */
+	get_online_cpus();
+
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	if (cpufreq_driver) {
 		write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-		return -EEXIST;
+		ret = -EEXIST;
+		goto out;
 	}
 	cpufreq_driver = driver_data;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
@@ -2407,21 +2435,9 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	if (driver_data->setpolicy)
 		driver_data->flags |= CPUFREQ_CONST_LOOPS;
 
-	if (cpufreq_boost_supported()) {
-		/*
-		 * Check if driver provides function to enable boost -
-		 * if not, use cpufreq_boost_set_sw as default
-		 */
-		if (!cpufreq_driver->set_boost)
-			cpufreq_driver->set_boost = cpufreq_boost_set_sw;
-
-		ret = cpufreq_sysfs_create_file(&boost.attr);
-		if (ret) {
-			pr_err("%s: cannot register global BOOST sysfs file\n",
-			       __func__);
-			goto err_null_driver;
-		}
-	}
+	ret = create_boost_sysfs_file();
+	if (ret)
+		goto err_null_driver;
 
 	ret = subsys_interface_register(&cpufreq_interface);
 	if (ret)
@@ -2438,17 +2454,19 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	register_hotcpu_notifier(&cpufreq_cpu_notifier);
 	pr_debug("driver %s up and running\n", driver_data->name);
 
-	return 0;
+out:
+	put_online_cpus();
+	return ret;
+
 err_if_unreg:
 	subsys_interface_unregister(&cpufreq_interface);
 err_boost_unreg:
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
+	remove_boost_sysfs_file();
 err_null_driver:
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	cpufreq_driver = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	return ret;
+	goto out;
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_driver);
 
@@ -2472,9 +2490,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	/* Protect against concurrent cpu hotplug */
 	get_online_cpus();
 	subsys_interface_unregister(&cpufreq_interface);
-	if (cpufreq_boost_supported())
-		cpufreq_sysfs_remove_file(&boost.attr);
-
+	remove_boost_sysfs_file();
 	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
@@ -2496,12 +2512,15 @@ static struct syscore_ops cpufreq_syscore_ops = {
 	.shutdown = cpufreq_suspend,
 };
 
+struct kobject *cpufreq_global_kobject;
+EXPORT_SYMBOL(cpufreq_global_kobject);
+
 static int __init cpufreq_core_init(void)
 {
 	if (cpufreq_disabled())
 		return -ENODEV;
 
-	cpufreq_global_kobject = kobject_create();
+	cpufreq_global_kobject = kobject_create_and_add("cpufreq", &cpu_subsys.dev_root->kobj);
 	BUG_ON(!cpufreq_global_kobject);
 
 	register_syscore_ops(&cpufreq_syscore_ops);
diff --git a/kernel/drivers/cpufreq/cpufreq_conservative.c b/kernel/drivers/cpufreq/cpufreq_conservative.c
index 25a70d06c..1fa1deb6e 100644
--- a/kernel/drivers/cpufreq/cpufreq_conservative.c
+++ b/kernel/drivers/cpufreq/cpufreq_conservative.c
@@ -23,6 +23,19 @@
 
 static DEFINE_PER_CPU(struct cs_cpu_dbs_info_s, cs_cpu_dbs_info);
 
+static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
+				   unsigned int event);
+
+#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
+static
+#endif
+struct cpufreq_governor cpufreq_gov_conservative = {
+	.name			= "conservative",
+	.governor		= cs_cpufreq_governor_dbs,
+	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
+	.owner			= THIS_MODULE,
+};
+
 static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
 					   struct cpufreq_policy *policy)
 {
@@ -47,7 +60,7 @@ static inline unsigned int get_freq_target(struct cs_dbs_tuners *cs_tuners,
 static void cs_check_cpu(int cpu, unsigned int load)
 {
 	struct cs_cpu_dbs_info_s *dbs_info = &per_cpu(cs_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
 	struct dbs_data *dbs_data = policy->governor_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 
@@ -102,26 +115,15 @@ static void cs_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static void cs_dbs_timer(struct work_struct *work)
+static unsigned int cs_dbs_timer(struct cpu_dbs_info *cdbs,
+				 struct dbs_data *dbs_data, bool modify_all)
 {
-	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);
-	struct dbs_data *dbs_data = dbs_info->cdbs.cur_policy->governor_data;
 	struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
-	int delay = delay_for_sampling_rate(cs_tuners->sampling_rate);
-	bool modify_all = true;
 
-	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
-	if (!need_load_eval(&core_dbs_info->cdbs, cs_tuners->sampling_rate))
-		modify_all = false;
-	else
-		dbs_check_cpu(dbs_data, cpu);
+	if (modify_all)
+		dbs_check_cpu(dbs_data, cdbs->shared->policy->cpu);
 
-	gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy, delay, modify_all);
-	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
+	return delay_for_sampling_rate(cs_tuners->sampling_rate);
 }
 
 static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
@@ -130,12 +132,14 @@ static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 	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;
+	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(freq->cpu);
 
-	if (!dbs_info->enable)
+	if (!policy)
 		return 0;
 
-	policy = dbs_info->cdbs.cur_policy;
+	/* policy isn't governed by conservative governor */
+	if (policy->governor != &cpufreq_gov_conservative)
+		return 0;
 
 	/*
 	 * we only care if our internally tracked freq moves outside the 'valid'
@@ -148,6 +152,10 @@ static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 	return 0;
 }
 
+static struct notifier_block cs_cpufreq_notifier_block = {
+	.notifier_call = dbs_cpufreq_notifier,
+};
+
 /************************** sysfs interface ************************/
 static struct common_dbs_data cs_dbs_cdata;
 
@@ -317,7 +325,7 @@ static struct attribute_group cs_attr_group_gov_pol = {
 
 /************************** sysfs end ************************/
 
-static int cs_init(struct dbs_data *dbs_data)
+static int cs_init(struct dbs_data *dbs_data, bool notify)
 {
 	struct cs_dbs_tuners *tuners;
 
@@ -336,25 +344,25 @@ static int cs_init(struct dbs_data *dbs_data)
 	dbs_data->tuners = tuners;
 	dbs_data->min_sampling_rate = MIN_SAMPLING_RATE_RATIO *
 		jiffies_to_usecs(10);
-	mutex_init(&dbs_data->mutex);
+
+	if (notify)
+		cpufreq_register_notifier(&cs_cpufreq_notifier_block,
+					  CPUFREQ_TRANSITION_NOTIFIER);
+
 	return 0;
 }
 
-static void cs_exit(struct dbs_data *dbs_data)
+static void cs_exit(struct dbs_data *dbs_data, bool notify)
 {
+	if (notify)
+		cpufreq_unregister_notifier(&cs_cpufreq_notifier_block,
+					    CPUFREQ_TRANSITION_NOTIFIER);
+
 	kfree(dbs_data->tuners);
 }
 
 define_get_cpu_dbs_routines(cs_cpu_dbs_info);
 
-static struct notifier_block cs_cpufreq_notifier_block = {
-	.notifier_call = dbs_cpufreq_notifier,
-};
-
-static struct cs_ops cs_ops = {
-	.notifier_block = &cs_cpufreq_notifier_block,
-};
-
 static struct common_dbs_data cs_dbs_cdata = {
 	.governor = GOV_CONSERVATIVE,
 	.attr_group_gov_sys = &cs_attr_group_gov_sys,
@@ -363,9 +371,9 @@ static struct common_dbs_data cs_dbs_cdata = {
 	.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,
 	.init = cs_init,
 	.exit = cs_exit,
+	.mutex = __MUTEX_INITIALIZER(cs_dbs_cdata.mutex),
 };
 
 static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
@@ -374,16 +382,6 @@ static int cs_cpufreq_governor_dbs(struct cpufreq_policy *policy,
 	return cpufreq_governor_dbs(policy, &cs_dbs_cdata, event);
 }
 
-#ifndef CONFIG_CPU_FREQ_DEFAULT_GOV_CONSERVATIVE
-static
-#endif
-struct cpufreq_governor cpufreq_gov_conservative = {
-	.name			= "conservative",
-	.governor		= cs_cpufreq_governor_dbs,
-	.max_transition_latency	= TRANSITION_LATENCY_LIMIT,
-	.owner			= THIS_MODULE,
-};
-
 static int __init cpufreq_gov_dbs_init(void)
 {
 	return cpufreq_register_governor(&cpufreq_gov_conservative);
diff --git a/kernel/drivers/cpufreq/cpufreq_governor.c b/kernel/drivers/cpufreq/cpufreq_governor.c
index 1b44496b2..d994b0f65 100644
--- a/kernel/drivers/cpufreq/cpufreq_governor.c
+++ b/kernel/drivers/cpufreq/cpufreq_governor.c
@@ -32,10 +32,10 @@ static struct attribute_group *get_sysfs_attr(struct dbs_data *dbs_data)
 
 void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 {
-	struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = dbs_data->cdata->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;
+	struct cpufreq_policy *policy = cdbs->shared->policy;
 	unsigned int sampling_rate;
 	unsigned int max_load = 0;
 	unsigned int ignore_nice;
@@ -60,11 +60,9 @@ void dbs_check_cpu(struct dbs_data *dbs_data, int cpu)
 		ignore_nice = cs_tuners->ignore_nice_load;
 	}
 
-	policy = cdbs->cur_policy;
-
 	/* Get Absolute Load */
 	for_each_cpu(j, policy->cpus) {
-		struct cpu_dbs_common_info *j_cdbs;
+		struct cpu_dbs_info *j_cdbs;
 		u64 cur_wall_time, cur_idle_time;
 		unsigned int idle_time, wall_time;
 		unsigned int load;
@@ -163,9 +161,9 @@ EXPORT_SYMBOL_GPL(dbs_check_cpu);
 static inline void __gov_queue_work(int cpu, struct dbs_data *dbs_data,
 		unsigned int delay)
 {
-	struct cpu_dbs_common_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
 
-	mod_delayed_work_on(cpu, system_wq, &cdbs->work, delay);
+	mod_delayed_work_on(cpu, system_wq, &cdbs->dwork, delay);
 }
 
 void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
@@ -173,10 +171,6 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
 {
 	int i;
 
-	mutex_lock(&cpufreq_governor_lock);
-	if (!policy->governor_enabled)
-		goto out_unlock;
-
 	if (!all_cpus) {
 		/*
 		 * Use raw_smp_processor_id() to avoid preemptible warnings.
@@ -190,42 +184,81 @@ void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
 		for_each_cpu(i, policy->cpus)
 			__gov_queue_work(i, dbs_data, delay);
 	}
-
-out_unlock:
-	mutex_unlock(&cpufreq_governor_lock);
 }
 EXPORT_SYMBOL_GPL(gov_queue_work);
 
 static inline void gov_cancel_work(struct dbs_data *dbs_data,
 		struct cpufreq_policy *policy)
 {
-	struct cpu_dbs_common_info *cdbs;
+	struct cpu_dbs_info *cdbs;
 	int i;
 
 	for_each_cpu(i, policy->cpus) {
 		cdbs = dbs_data->cdata->get_cpu_cdbs(i);
-		cancel_delayed_work_sync(&cdbs->work);
+		cancel_delayed_work_sync(&cdbs->dwork);
 	}
 }
 
 /* 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)
+static bool need_load_eval(struct cpu_common_dbs_info *shared,
+			   unsigned int sampling_rate)
 {
-	if (policy_is_shared(cdbs->cur_policy)) {
+	if (policy_is_shared(shared->policy)) {
 		ktime_t time_now = ktime_get();
-		s64 delta_us = ktime_us_delta(time_now, cdbs->time_stamp);
+		s64 delta_us = ktime_us_delta(time_now, shared->time_stamp);
 
 		/* Do nothing if we recently have sampled */
 		if (delta_us < (s64)(sampling_rate / 2))
 			return false;
 		else
-			cdbs->time_stamp = time_now;
+			shared->time_stamp = time_now;
 	}
 
 	return true;
 }
-EXPORT_SYMBOL_GPL(need_load_eval);
+
+static void dbs_timer(struct work_struct *work)
+{
+	struct cpu_dbs_info *cdbs = container_of(work, struct cpu_dbs_info,
+						 dwork.work);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+	struct cpufreq_policy *policy;
+	struct dbs_data *dbs_data;
+	unsigned int sampling_rate, delay;
+	bool modify_all = true;
+
+	mutex_lock(&shared->timer_mutex);
+
+	policy = shared->policy;
+
+	/*
+	 * Governor might already be disabled and there is no point continuing
+	 * with the work-handler.
+	 */
+	if (!policy)
+		goto unlock;
+
+	dbs_data = policy->governor_data;
+
+	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
+
+		sampling_rate = cs_tuners->sampling_rate;
+	} else {
+		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+
+		sampling_rate = od_tuners->sampling_rate;
+	}
+
+	if (!need_load_eval(cdbs->shared, sampling_rate))
+		modify_all = false;
+
+	delay = dbs_data->cdata->gov_dbs_timer(cdbs, dbs_data, modify_all);
+	gov_queue_work(dbs_data, policy, delay, modify_all);
+
+unlock:
+	mutex_unlock(&shared->timer_mutex);
+}
 
 static void set_sampling_rate(struct dbs_data *dbs_data,
 		unsigned int sampling_rate)
@@ -239,211 +272,303 @@ static void set_sampling_rate(struct dbs_data *dbs_data,
 	}
 }
 
-int cpufreq_governor_dbs(struct cpufreq_policy *policy,
-		struct common_dbs_data *cdata, unsigned int event)
+static int alloc_common_dbs_info(struct cpufreq_policy *policy,
+				 struct common_dbs_data *cdata)
 {
-	struct dbs_data *dbs_data;
-	struct od_cpu_dbs_info_s *od_dbs_info = NULL;
-	struct cs_cpu_dbs_info_s *cs_dbs_info = NULL;
-	struct od_ops *od_ops = NULL;
-	struct od_dbs_tuners *od_tuners = NULL;
-	struct cs_dbs_tuners *cs_tuners = NULL;
-	struct cpu_dbs_common_info *cpu_cdbs;
-	unsigned int sampling_rate, latency, ignore_nice, j, cpu = policy->cpu;
-	int io_busy = 0;
-	int rc;
+	struct cpu_common_dbs_info *shared;
+	int j;
 
-	if (have_governor_per_policy())
-		dbs_data = policy->governor_data;
-	else
-		dbs_data = cdata->gdbs_data;
+	/* Allocate memory for the common information for policy->cpus */
+	shared = kzalloc(sizeof(*shared), GFP_KERNEL);
+	if (!shared)
+		return -ENOMEM;
 
-	WARN_ON(!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT));
+	/* Set shared for all CPUs, online+offline */
+	for_each_cpu(j, policy->related_cpus)
+		cdata->get_cpu_cdbs(j)->shared = shared;
 
-	switch (event) {
-	case CPUFREQ_GOV_POLICY_INIT:
-		if (have_governor_per_policy()) {
-			WARN_ON(dbs_data);
-		} else if (dbs_data) {
-			dbs_data->usage_count++;
-			policy->governor_data = dbs_data;
-			return 0;
-		}
+	return 0;
+}
 
-		dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
-		if (!dbs_data) {
-			pr_err("%s: POLICY_INIT: kzalloc failed\n", __func__);
-			return -ENOMEM;
-		}
+static void free_common_dbs_info(struct cpufreq_policy *policy,
+				 struct common_dbs_data *cdata)
+{
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+	int j;
 
-		dbs_data->cdata = cdata;
-		dbs_data->usage_count = 1;
-		rc = cdata->init(dbs_data);
-		if (rc) {
-			pr_err("%s: POLICY_INIT: init() failed\n", __func__);
-			kfree(dbs_data);
-			return rc;
-		}
+	for_each_cpu(j, policy->cpus)
+		cdata->get_cpu_cdbs(j)->shared = NULL;
 
-		if (!have_governor_per_policy())
-			WARN_ON(cpufreq_get_global_kobject());
-
-		rc = sysfs_create_group(get_governor_parent_kobj(policy),
-				get_sysfs_attr(dbs_data));
-		if (rc) {
-			cdata->exit(dbs_data);
-			kfree(dbs_data);
-			return rc;
-		}
+	kfree(shared);
+}
+
+static int cpufreq_governor_init(struct cpufreq_policy *policy,
+				 struct dbs_data *dbs_data,
+				 struct common_dbs_data *cdata)
+{
+	unsigned int latency;
+	int ret;
+
+	/* State should be equivalent to EXIT */
+	if (policy->governor_data)
+		return -EBUSY;
+
+	if (dbs_data) {
+		if (WARN_ON(have_governor_per_policy()))
+			return -EINVAL;
+
+		ret = alloc_common_dbs_info(policy, cdata);
+		if (ret)
+			return ret;
 
+		dbs_data->usage_count++;
 		policy->governor_data = dbs_data;
+		return 0;
+	}
+
+	dbs_data = kzalloc(sizeof(*dbs_data), GFP_KERNEL);
+	if (!dbs_data)
+		return -ENOMEM;
+
+	ret = alloc_common_dbs_info(policy, cdata);
+	if (ret)
+		goto free_dbs_data;
+
+	dbs_data->cdata = cdata;
+	dbs_data->usage_count = 1;
+
+	ret = cdata->init(dbs_data, !policy->governor->initialized);
+	if (ret)
+		goto free_common_dbs_info;
 
-		/* policy latency is in ns. Convert it to us first */
-		latency = policy->cpuinfo.transition_latency / 1000;
-		if (latency == 0)
-			latency = 1;
+	/* 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);
-		set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
+	/* Bring kernel and HW constraints together */
+	dbs_data->min_sampling_rate = max(dbs_data->min_sampling_rate,
+					  MIN_LATENCY_MULTIPLIER * latency);
+	set_sampling_rate(dbs_data, max(dbs_data->min_sampling_rate,
 					latency * LATENCY_MULTIPLIER));
 
-		if ((cdata->governor == GOV_CONSERVATIVE) &&
-				(!policy->governor->initialized)) {
-			struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
+	if (!have_governor_per_policy())
+		cdata->gdbs_data = dbs_data;
 
-			cpufreq_register_notifier(cs_ops->notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
-		}
+	policy->governor_data = dbs_data;
 
-		if (!have_governor_per_policy())
-			cdata->gdbs_data = dbs_data;
+	ret = sysfs_create_group(get_governor_parent_kobj(policy),
+				 get_sysfs_attr(dbs_data));
+	if (ret)
+		goto reset_gdbs_data;
 
-		return 0;
-	case CPUFREQ_GOV_POLICY_EXIT:
-		if (!--dbs_data->usage_count) {
-			sysfs_remove_group(get_governor_parent_kobj(policy),
-					get_sysfs_attr(dbs_data));
+	return 0;
+
+reset_gdbs_data:
+	policy->governor_data = NULL;
+
+	if (!have_governor_per_policy())
+		cdata->gdbs_data = NULL;
+	cdata->exit(dbs_data, !policy->governor->initialized);
+free_common_dbs_info:
+	free_common_dbs_info(policy, cdata);
+free_dbs_data:
+	kfree(dbs_data);
+	return ret;
+}
+
+static int cpufreq_governor_exit(struct cpufreq_policy *policy,
+				 struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(policy->cpu);
 
-			if (!have_governor_per_policy())
-				cpufreq_put_global_kobject();
+	/* State should be equivalent to INIT */
+	if (!cdbs->shared || cdbs->shared->policy)
+		return -EBUSY;
 
-			if ((dbs_data->cdata->governor == GOV_CONSERVATIVE) &&
-				(policy->governor->initialized == 1)) {
-				struct cs_ops *cs_ops = dbs_data->cdata->gov_ops;
+	if (!--dbs_data->usage_count) {
+		sysfs_remove_group(get_governor_parent_kobj(policy),
+				   get_sysfs_attr(dbs_data));
 
-				cpufreq_unregister_notifier(cs_ops->notifier_block,
-						CPUFREQ_TRANSITION_NOTIFIER);
-			}
+		policy->governor_data = NULL;
 
-			cdata->exit(dbs_data);
-			kfree(dbs_data);
+		if (!have_governor_per_policy())
 			cdata->gdbs_data = NULL;
-		}
 
+		cdata->exit(dbs_data, policy->governor->initialized == 1);
+		kfree(dbs_data);
+	} else {
 		policy->governor_data = NULL;
-		return 0;
 	}
 
-	cpu_cdbs = dbs_data->cdata->get_cpu_cdbs(cpu);
+	free_common_dbs_info(policy, cdata);
+	return 0;
+}
+
+static int cpufreq_governor_start(struct cpufreq_policy *policy,
+				  struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
+	unsigned int sampling_rate, ignore_nice, j, cpu = policy->cpu;
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
+	int io_busy = 0;
+
+	if (!policy->cur)
+		return -EINVAL;
+
+	/* State should be equivalent to INIT */
+	if (!shared || shared->policy)
+		return -EBUSY;
+
+	if (cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_dbs_tuners *cs_tuners = dbs_data->tuners;
 
-	if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-		cs_tuners = dbs_data->tuners;
-		cs_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
 		sampling_rate = cs_tuners->sampling_rate;
 		ignore_nice = cs_tuners->ignore_nice_load;
 	} else {
-		od_tuners = dbs_data->tuners;
-		od_dbs_info = dbs_data->cdata->get_cpu_dbs_info_s(cpu);
+		struct od_dbs_tuners *od_tuners = dbs_data->tuners;
+
 		sampling_rate = od_tuners->sampling_rate;
 		ignore_nice = od_tuners->ignore_nice_load;
-		od_ops = dbs_data->cdata->gov_ops;
 		io_busy = od_tuners->io_is_busy;
 	}
 
-	switch (event) {
-	case CPUFREQ_GOV_START:
-		if (!policy->cur)
-			return -EINVAL;
+	shared->policy = policy;
+	shared->time_stamp = ktime_get();
+	mutex_init(&shared->timer_mutex);
 
-		mutex_lock(&dbs_data->mutex);
+	for_each_cpu(j, policy->cpus) {
+		struct cpu_dbs_info *j_cdbs = cdata->get_cpu_cdbs(j);
+		unsigned int prev_load;
 
-		for_each_cpu(j, policy->cpus) {
-			struct cpu_dbs_common_info *j_cdbs =
-				dbs_data->cdata->get_cpu_cdbs(j);
-			unsigned int prev_load;
+		j_cdbs->prev_cpu_idle =
+			get_cpu_idle_time(j, &j_cdbs->prev_cpu_wall, io_busy);
 
-			j_cdbs->cpu = j;
-			j_cdbs->cur_policy = policy;
-			j_cdbs->prev_cpu_idle = get_cpu_idle_time(j,
-					       &j_cdbs->prev_cpu_wall, io_busy);
+		prev_load = (unsigned int)(j_cdbs->prev_cpu_wall -
+					    j_cdbs->prev_cpu_idle);
+		j_cdbs->prev_load = 100 * prev_load /
+				    (unsigned int)j_cdbs->prev_cpu_wall;
 
-			prev_load = (unsigned int)
-				(j_cdbs->prev_cpu_wall - j_cdbs->prev_cpu_idle);
-			j_cdbs->prev_load = 100 * prev_load /
-					(unsigned int) j_cdbs->prev_cpu_wall;
+		if (ignore_nice)
+			j_cdbs->prev_cpu_nice = kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 
-			if (ignore_nice)
-				j_cdbs->prev_cpu_nice =
-					kcpustat_cpu(j).cpustat[CPUTIME_NICE];
+		INIT_DEFERRABLE_WORK(&j_cdbs->dwork, dbs_timer);
+	}
 
-			mutex_init(&j_cdbs->timer_mutex);
-			INIT_DEFERRABLE_WORK(&j_cdbs->work,
-					     dbs_data->cdata->gov_dbs_timer);
-		}
+	if (cdata->governor == GOV_CONSERVATIVE) {
+		struct cs_cpu_dbs_info_s *cs_dbs_info =
+			cdata->get_cpu_dbs_info_s(cpu);
 
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE) {
-			cs_dbs_info->down_skip = 0;
-			cs_dbs_info->enable = 1;
-			cs_dbs_info->requested_freq = policy->cur;
-		} else {
-			od_dbs_info->rate_mult = 1;
-			od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
-			od_ops->powersave_bias_init_cpu(cpu);
-		}
+		cs_dbs_info->down_skip = 0;
+		cs_dbs_info->requested_freq = policy->cur;
+	} else {
+		struct od_ops *od_ops = cdata->gov_ops;
+		struct od_cpu_dbs_info_s *od_dbs_info = cdata->get_cpu_dbs_info_s(cpu);
 
-		mutex_unlock(&dbs_data->mutex);
+		od_dbs_info->rate_mult = 1;
+		od_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+		od_ops->powersave_bias_init_cpu(cpu);
+	}
 
-		/* Initiate timer time stamp */
-		cpu_cdbs->time_stamp = ktime_get();
+	gov_queue_work(dbs_data, policy, delay_for_sampling_rate(sampling_rate),
+		       true);
+	return 0;
+}
 
-		gov_queue_work(dbs_data, policy,
-				delay_for_sampling_rate(sampling_rate), true);
-		break;
+static int cpufreq_governor_stop(struct cpufreq_policy *policy,
+				 struct dbs_data *dbs_data)
+{
+	struct cpu_dbs_info *cdbs = dbs_data->cdata->get_cpu_cdbs(policy->cpu);
+	struct cpu_common_dbs_info *shared = cdbs->shared;
 
-	case CPUFREQ_GOV_STOP:
-		if (dbs_data->cdata->governor == GOV_CONSERVATIVE)
-			cs_dbs_info->enable = 0;
+	/* State should be equivalent to START */
+	if (!shared || !shared->policy)
+		return -EBUSY;
 
-		gov_cancel_work(dbs_data, policy);
+	/*
+	 * Work-handler must see this updated, as it should not proceed any
+	 * further after governor is disabled. And so timer_mutex is taken while
+	 * updating this value.
+	 */
+	mutex_lock(&shared->timer_mutex);
+	shared->policy = NULL;
+	mutex_unlock(&shared->timer_mutex);
 
-		mutex_lock(&dbs_data->mutex);
-		mutex_destroy(&cpu_cdbs->timer_mutex);
-		cpu_cdbs->cur_policy = NULL;
+	gov_cancel_work(dbs_data, policy);
 
-		mutex_unlock(&dbs_data->mutex);
+	mutex_destroy(&shared->timer_mutex);
+	return 0;
+}
 
-		break;
+static int cpufreq_governor_limits(struct cpufreq_policy *policy,
+				   struct dbs_data *dbs_data)
+{
+	struct common_dbs_data *cdata = dbs_data->cdata;
+	unsigned int cpu = policy->cpu;
+	struct cpu_dbs_info *cdbs = cdata->get_cpu_cdbs(cpu);
+
+	/* State should be equivalent to START */
+	if (!cdbs->shared || !cdbs->shared->policy)
+		return -EBUSY;
+
+	mutex_lock(&cdbs->shared->timer_mutex);
+	if (policy->max < cdbs->shared->policy->cur)
+		__cpufreq_driver_target(cdbs->shared->policy, policy->max,
+					CPUFREQ_RELATION_H);
+	else if (policy->min > cdbs->shared->policy->cur)
+		__cpufreq_driver_target(cdbs->shared->policy, policy->min,
+					CPUFREQ_RELATION_L);
+	dbs_check_cpu(dbs_data, cpu);
+	mutex_unlock(&cdbs->shared->timer_mutex);
+
+	return 0;
+}
+
+int cpufreq_governor_dbs(struct cpufreq_policy *policy,
+			 struct common_dbs_data *cdata, unsigned int event)
+{
+	struct dbs_data *dbs_data;
+	int ret;
+
+	/* Lock governor to block concurrent initialization of governor */
+	mutex_lock(&cdata->mutex);
+
+	if (have_governor_per_policy())
+		dbs_data = policy->governor_data;
+	else
+		dbs_data = cdata->gdbs_data;
+
+	if (!dbs_data && (event != CPUFREQ_GOV_POLICY_INIT)) {
+		ret = -EINVAL;
+		goto unlock;
+	}
 
+	switch (event) {
+	case CPUFREQ_GOV_POLICY_INIT:
+		ret = cpufreq_governor_init(policy, dbs_data, cdata);
+		break;
+	case CPUFREQ_GOV_POLICY_EXIT:
+		ret = cpufreq_governor_exit(policy, dbs_data);
+		break;
+	case CPUFREQ_GOV_START:
+		ret = cpufreq_governor_start(policy, dbs_data);
+		break;
+	case CPUFREQ_GOV_STOP:
+		ret = cpufreq_governor_stop(policy, dbs_data);
+		break;
 	case CPUFREQ_GOV_LIMITS:
-		mutex_lock(&dbs_data->mutex);
-		if (!cpu_cdbs->cur_policy) {
-			mutex_unlock(&dbs_data->mutex);
-			break;
-		}
-		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);
-		mutex_unlock(&dbs_data->mutex);
+		ret = cpufreq_governor_limits(policy, dbs_data);
 		break;
+	default:
+		ret = -EINVAL;
 	}
-	return 0;
+
+unlock:
+	mutex_unlock(&cdata->mutex);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_governor_dbs);
diff --git a/kernel/drivers/cpufreq/cpufreq_governor.h b/kernel/drivers/cpufreq/cpufreq_governor.h
index cc401d147..5621bb03e 100644
--- a/kernel/drivers/cpufreq/cpufreq_governor.h
+++ b/kernel/drivers/cpufreq/cpufreq_governor.h
@@ -109,7 +109,7 @@ store_one(_gov, file_name)
 
 /* create helper routines */
 #define define_get_cpu_dbs_routines(_dbs_info)				\
-static struct cpu_dbs_common_info *get_cpu_cdbs(int cpu)		\
+static struct cpu_dbs_info *get_cpu_cdbs(int cpu)			\
 {									\
 	return &per_cpu(_dbs_info, cpu).cdbs;				\
 }									\
@@ -128,9 +128,20 @@ static void *get_cpu_dbs_info_s(int cpu)				\
  * cs_*: Conservative governor
  */
 
+/* Common to all CPUs of a policy */
+struct cpu_common_dbs_info {
+	struct cpufreq_policy *policy;
+	/*
+	 * percpu mutex that serializes governor limit change with dbs_timer
+	 * invocation. We do not want dbs_timer to run when user is changing
+	 * the governor or limits.
+	 */
+	struct mutex timer_mutex;
+	ktime_t time_stamp;
+};
+
 /* Per cpu structures */
-struct cpu_dbs_common_info {
-	int cpu;
+struct cpu_dbs_info {
 	u64 prev_cpu_idle;
 	u64 prev_cpu_wall;
 	u64 prev_cpu_nice;
@@ -141,19 +152,12 @@ struct cpu_dbs_common_info {
 	 * wake-up from idle.
 	 */
 	unsigned int prev_load;
-	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 delayed_work dwork;
+	struct cpu_common_dbs_info *shared;
 };
 
 struct od_cpu_dbs_info_s {
-	struct cpu_dbs_common_info cdbs;
+	struct cpu_dbs_info cdbs;
 	struct cpufreq_frequency_table *freq_table;
 	unsigned int freq_lo;
 	unsigned int freq_lo_jiffies;
@@ -163,10 +167,9 @@ struct od_cpu_dbs_info_s {
 };
 
 struct cs_cpu_dbs_info_s {
-	struct cpu_dbs_common_info cdbs;
+	struct cpu_dbs_info cdbs;
 	unsigned int down_skip;
 	unsigned int requested_freq;
-	unsigned int enable:1;
 };
 
 /* Per policy Governors sysfs tunables */
@@ -204,15 +207,22 @@ struct common_dbs_data {
 	 */
 	struct dbs_data *gdbs_data;
 
-	struct cpu_dbs_common_info *(*get_cpu_cdbs)(int cpu);
+	struct cpu_dbs_info *(*get_cpu_cdbs)(int cpu);
 	void *(*get_cpu_dbs_info_s)(int cpu);
-	void (*gov_dbs_timer)(struct work_struct *work);
+	unsigned int (*gov_dbs_timer)(struct cpu_dbs_info *cdbs,
+				      struct dbs_data *dbs_data,
+				      bool modify_all);
 	void (*gov_check_cpu)(int cpu, unsigned int load);
-	int (*init)(struct dbs_data *dbs_data);
-	void (*exit)(struct dbs_data *dbs_data);
+	int (*init)(struct dbs_data *dbs_data, bool notify);
+	void (*exit)(struct dbs_data *dbs_data, bool notify);
 
 	/* Governor specific ops, see below */
 	void *gov_ops;
+
+	/*
+	 * Protects governor's data (struct dbs_data and struct common_dbs_data)
+	 */
+	struct mutex mutex;
 };
 
 /* Governor Per policy data */
@@ -221,9 +231,6 @@ struct dbs_data {
 	unsigned int min_sampling_rate;
 	int usage_count;
 	void *tuners;
-
-	/* dbs_mutex protects dbs_enable in governor start/stop */
-	struct mutex mutex;
 };
 
 /* Governor specific ops, will be passed to dbs_data->gov_ops */
@@ -234,10 +241,6 @@ struct od_ops {
 	void (*freq_increase)(struct cpufreq_policy *policy, 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);
@@ -267,8 +270,6 @@ static ssize_t show_sampling_rate_min_gov_pol				\
 extern struct mutex cpufreq_governor_lock;
 
 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 cpufreq_policy *policy,
 		struct common_dbs_data *cdata, unsigned int event);
 void gov_queue_work(struct dbs_data *dbs_data, struct cpufreq_policy *policy,
diff --git a/kernel/drivers/cpufreq/cpufreq_ondemand.c b/kernel/drivers/cpufreq/cpufreq_ondemand.c
index ad3f38fd3..03ac6ce54 100644
--- a/kernel/drivers/cpufreq/cpufreq_ondemand.c
+++ b/kernel/drivers/cpufreq/cpufreq_ondemand.c
@@ -155,7 +155,7 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
 static void od_check_cpu(int cpu, unsigned int load)
 {
 	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
-	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
+	struct cpufreq_policy *policy = dbs_info->cdbs.shared->policy;
 	struct dbs_data *dbs_data = policy->governor_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
 
@@ -191,46 +191,40 @@ static void od_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static void od_dbs_timer(struct work_struct *work)
+static unsigned int od_dbs_timer(struct cpu_dbs_info *cdbs,
+				 struct dbs_data *dbs_data, bool modify_all)
 {
-	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,
+	struct cpufreq_policy *policy = cdbs->shared->policy;
+	unsigned int cpu = policy->cpu;
+	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info,
 			cpu);
-	struct dbs_data *dbs_data = dbs_info->cdbs.cur_policy->governor_data;
 	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
-	int delay = 0, sample_type = core_dbs_info->sample_type;
-	bool modify_all = true;
+	int delay = 0, sample_type = dbs_info->sample_type;
 
-	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
-	if (!need_load_eval(&core_dbs_info->cdbs, od_tuners->sampling_rate)) {
-		modify_all = false;
+	if (!modify_all)
 		goto max_delay;
-	}
 
 	/* Common NORMAL_SAMPLE setup */
-	core_dbs_info->sample_type = OD_NORMAL_SAMPLE;
+	dbs_info->sample_type = OD_NORMAL_SAMPLE;
 	if (sample_type == OD_SUB_SAMPLE) {
-		delay = core_dbs_info->freq_lo_jiffies;
-		__cpufreq_driver_target(core_dbs_info->cdbs.cur_policy,
-				core_dbs_info->freq_lo, CPUFREQ_RELATION_H);
+		delay = dbs_info->freq_lo_jiffies;
+		__cpufreq_driver_target(policy, dbs_info->freq_lo,
+					CPUFREQ_RELATION_H);
 	} else {
 		dbs_check_cpu(dbs_data, cpu);
-		if (core_dbs_info->freq_lo) {
+		if (dbs_info->freq_lo) {
 			/* Setup timer for SUB_SAMPLE */
-			core_dbs_info->sample_type = OD_SUB_SAMPLE;
-			delay = core_dbs_info->freq_hi_jiffies;
+			dbs_info->sample_type = OD_SUB_SAMPLE;
+			delay = dbs_info->freq_hi_jiffies;
 		}
 	}
 
 max_delay:
 	if (!delay)
 		delay = delay_for_sampling_rate(od_tuners->sampling_rate
-				* core_dbs_info->rate_mult);
+				* dbs_info->rate_mult);
 
-	gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy, delay, modify_all);
-	mutex_unlock(&core_dbs_info->cdbs.timer_mutex);
+	return delay;
 }
 
 /************************** sysfs interface ************************/
@@ -273,27 +267,19 @@ static void update_sampling_rate(struct dbs_data *dbs_data,
 		dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
 		cpufreq_cpu_put(policy);
 
-		mutex_lock(&dbs_info->cdbs.timer_mutex);
-
-		if (!delayed_work_pending(&dbs_info->cdbs.work)) {
-			mutex_unlock(&dbs_info->cdbs.timer_mutex);
+		if (!delayed_work_pending(&dbs_info->cdbs.dwork))
 			continue;
-		}
 
 		next_sampling = jiffies + usecs_to_jiffies(new_rate);
-		appointed_at = dbs_info->cdbs.work.timer.expires;
+		appointed_at = dbs_info->cdbs.dwork.timer.expires;
 
 		if (time_before(next_sampling, appointed_at)) {
+			cancel_delayed_work_sync(&dbs_info->cdbs.dwork);
 
-			mutex_unlock(&dbs_info->cdbs.timer_mutex);
-			cancel_delayed_work_sync(&dbs_info->cdbs.work);
-			mutex_lock(&dbs_info->cdbs.timer_mutex);
-
-			gov_queue_work(dbs_data, dbs_info->cdbs.cur_policy,
-					usecs_to_jiffies(new_rate), true);
+			gov_queue_work(dbs_data, policy,
+				       usecs_to_jiffies(new_rate), true);
 
 		}
-		mutex_unlock(&dbs_info->cdbs.timer_mutex);
 	}
 }
 
@@ -475,7 +461,7 @@ static struct attribute_group od_attr_group_gov_pol = {
 
 /************************** sysfs end ************************/
 
-static int od_init(struct dbs_data *dbs_data)
+static int od_init(struct dbs_data *dbs_data, bool notify)
 {
 	struct od_dbs_tuners *tuners;
 	u64 idle_time;
@@ -513,11 +499,10 @@ static int od_init(struct dbs_data *dbs_data)
 	tuners->io_is_busy = should_io_be_busy();
 
 	dbs_data->tuners = tuners;
-	mutex_init(&dbs_data->mutex);
 	return 0;
 }
 
-static void od_exit(struct dbs_data *dbs_data)
+static void od_exit(struct dbs_data *dbs_data, bool notify)
 {
 	kfree(dbs_data->tuners);
 }
@@ -541,6 +526,7 @@ static struct common_dbs_data od_dbs_cdata = {
 	.gov_ops = &od_ops,
 	.init = od_init,
 	.exit = od_exit,
+	.mutex = __MUTEX_INITIALIZER(od_dbs_cdata.mutex),
 };
 
 static void od_set_powersave_bias(unsigned int powersave_bias)
@@ -556,13 +542,16 @@ static void od_set_powersave_bias(unsigned int powersave_bias)
 
 	get_online_cpus();
 	for_each_online_cpu(cpu) {
+		struct cpu_common_dbs_info *shared;
+
 		if (cpumask_test_cpu(cpu, &done))
 			continue;
 
-		policy = per_cpu(od_cpu_dbs_info, cpu).cdbs.cur_policy;
-		if (!policy)
+		shared = per_cpu(od_cpu_dbs_info, cpu).cdbs.shared;
+		if (!shared)
 			continue;
 
+		policy = shared->policy;
 		cpumask_or(&done, &done, policy->cpus);
 
 		if (policy->governor != &cpufreq_gov_ondemand)
diff --git a/kernel/drivers/cpufreq/cpufreq_opp.c b/kernel/drivers/cpufreq/cpufreq_opp.c
deleted file mode 100644
index 773bcde89..000000000
--- a/kernel/drivers/cpufreq/cpufreq_opp.c
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * Generic OPP helper interface for CPUFreq drivers
- *
- * Copyright (C) 2009-2014 Texas Instruments Incorporated.
- *	Nishanth Menon
- *	Romit Dasgupta
- *	Kevin Hilman
- *
- * 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/cpufreq.h>
-#include <linux/device.h>
-#include <linux/err.h>
-#include <linux/errno.h>
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <linux/pm_opp.h>
-#include <linux/rcupdate.h>
-#include <linux/slab.h>
-
-/**
- * dev_pm_opp_init_cpufreq_table() - create a cpufreq table for a device
- * @dev:	device for which we do this operation
- * @table:	Cpufreq table returned back to caller
- *
- * Generate a cpufreq table for a provided device- this assumes that the
- * opp list is already initialized and ready for usage.
- *
- * This function allocates required memory for the cpufreq table. It is
- * expected that the caller does the required maintenance such as freeing
- * the table as required.
- *
- * Returns -EINVAL for bad pointers, -ENODEV if the device is not found, -ENOMEM
- * if no memory available for the operation (table is not populated), returns 0
- * if successful and table is populated.
- *
- * WARNING: It is  important for the callers to ensure refreshing their copy of
- * the table if any of the mentioned functions have been invoked in the interim.
- *
- * Locking: The internal device_opp and opp structures are RCU protected.
- * Since we just use the regular accessor functions to access the internal data
- * structures, we use RCU read lock inside this function. As a result, users of
- * this function DONOT need to use explicit locks for invoking.
- */
-int dev_pm_opp_init_cpufreq_table(struct device *dev,
-				  struct cpufreq_frequency_table **table)
-{
-	struct dev_pm_opp *opp;
-	struct cpufreq_frequency_table *freq_table = NULL;
-	int i, max_opps, ret = 0;
-	unsigned long rate;
-
-	rcu_read_lock();
-
-	max_opps = dev_pm_opp_get_opp_count(dev);
-	if (max_opps <= 0) {
-		ret = max_opps ? max_opps : -ENODATA;
-		goto out;
-	}
-
-	freq_table = kcalloc((max_opps + 1), sizeof(*freq_table), GFP_ATOMIC);
-	if (!freq_table) {
-		ret = -ENOMEM;
-		goto out;
-	}
-
-	for (i = 0, rate = 0; i < max_opps; i++, rate++) {
-		/* find next rate */
-		opp = dev_pm_opp_find_freq_ceil(dev, &rate);
-		if (IS_ERR(opp)) {
-			ret = PTR_ERR(opp);
-			goto out;
-		}
-		freq_table[i].driver_data = i;
-		freq_table[i].frequency = rate / 1000;
-	}
-
-	freq_table[i].driver_data = i;
-	freq_table[i].frequency = CPUFREQ_TABLE_END;
-
-	*table = &freq_table[0];
-
-out:
-	rcu_read_unlock();
-	if (ret)
-		kfree(freq_table);
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_init_cpufreq_table);
-
-/**
- * dev_pm_opp_free_cpufreq_table() - free the cpufreq table
- * @dev:	device for which we do this operation
- * @table:	table to free
- *
- * Free up the table allocated by dev_pm_opp_init_cpufreq_table
- */
-void dev_pm_opp_free_cpufreq_table(struct device *dev,
-				   struct cpufreq_frequency_table **table)
-{
-	if (!table)
-		return;
-
-	kfree(*table);
-	*table = NULL;
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_free_cpufreq_table);
diff --git a/kernel/drivers/cpufreq/e_powersaver.c b/kernel/drivers/cpufreq/e_powersaver.c
index a0d2a423c..4085244c8 100644
--- a/kernel/drivers/cpufreq/e_powersaver.c
+++ b/kernel/drivers/cpufreq/e_powersaver.c
@@ -78,7 +78,7 @@ static int eps_acpi_init(void)
 static int eps_acpi_exit(struct cpufreq_policy *policy)
 {
 	if (eps_acpi_cpu_perf) {
-		acpi_processor_unregister_performance(eps_acpi_cpu_perf, 0);
+		acpi_processor_unregister_performance(0);
 		free_cpumask_var(eps_acpi_cpu_perf->shared_cpu_map);
 		kfree(eps_acpi_cpu_perf);
 		eps_acpi_cpu_perf = NULL;
diff --git a/kernel/drivers/cpufreq/exynos-cpufreq.c b/kernel/drivers/cpufreq/exynos-cpufreq.c
deleted file mode 100644
index 82d2fbb20..000000000
--- a/kernel/drivers/cpufreq/exynos-cpufreq.c
+++ /dev/null
@@ -1,239 +0,0 @@
-/*
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS - CPU frequency scaling support for EXYNOS series
- *
- * 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/kernel.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/regulator/consumer.h>
-#include <linux/cpufreq.h>
-#include <linux/platform_device.h>
-#include <linux/of.h>
-#include <linux/cpu_cooling.h>
-#include <linux/cpu.h>
-
-#include "exynos-cpufreq.h"
-
-static struct exynos_dvfs_info *exynos_info;
-static struct thermal_cooling_device *cdev;
-static struct regulator *arm_regulator;
-static unsigned int locking_frequency;
-
-static int exynos_cpufreq_get_index(unsigned int freq)
-{
-	struct cpufreq_frequency_table *freq_table = exynos_info->freq_table;
-	struct cpufreq_frequency_table *pos;
-
-	cpufreq_for_each_entry(pos, freq_table)
-		if (pos->frequency == freq)
-			break;
-
-	if (pos->frequency == CPUFREQ_TABLE_END)
-		return -EINVAL;
-
-	return pos - freq_table;
-}
-
-static int exynos_cpufreq_scale(unsigned int target_freq)
-{
-	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;
-	struct device *dev = exynos_info->dev;
-	unsigned int old_freq;
-	int index, old_index;
-	int ret = 0;
-
-	old_freq = policy->cur;
-
-	/*
-	 * 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 frequency table.
-	 */
-	old_index = exynos_cpufreq_get_index(old_freq);
-	if (old_index < 0) {
-		ret = old_index;
-		goto out;
-	}
-
-	index = exynos_cpufreq_get_index(target_freq);
-	if (index < 0) {
-		ret = index;
-		goto out;
-	}
-
-	/*
-	 * ARM clock source will be changed APLL to MPLL temporary
-	 * To support this level, need to control regulator for
-	 * required voltage level
-	 */
-	if (exynos_info->need_apll_change != NULL) {
-		if (exynos_info->need_apll_change(old_index, index) &&
-		   (freq_table[index].frequency < mpll_freq_khz) &&
-		   (freq_table[old_index].frequency < mpll_freq_khz))
-			safe_arm_volt = volt_table[exynos_info->pll_safe_idx];
-	}
-	arm_volt = volt_table[index];
-
-	/* When the new frequency is higher than current frequency */
-	if ((target_freq > old_freq) && !safe_arm_volt) {
-		/* Firstly, voltage up to increase frequency */
-		ret = regulator_set_voltage(arm_regulator, arm_volt, arm_volt);
-		if (ret) {
-			dev_err(dev, "failed to set cpu voltage to %d\n",
-				arm_volt);
-			return ret;
-		}
-	}
-
-	if (safe_arm_volt) {
-		ret = regulator_set_voltage(arm_regulator, safe_arm_volt,
-				      safe_arm_volt);
-		if (ret) {
-			dev_err(dev, "failed to set cpu voltage to %d\n",
-				safe_arm_volt);
-			return ret;
-		}
-	}
-
-	exynos_info->set_freq(old_index, index);
-
-	/* When the new frequency is lower than current frequency */
-	if ((target_freq < old_freq) ||
-	   ((target_freq > old_freq) && safe_arm_volt)) {
-		/* down the voltage after frequency change */
-		ret = regulator_set_voltage(arm_regulator, arm_volt,
-				arm_volt);
-		if (ret) {
-			dev_err(dev, "failed to set cpu voltage to %d\n",
-				arm_volt);
-			goto out;
-		}
-	}
-
-out:
-	cpufreq_cpu_put(policy);
-
-	return ret;
-}
-
-static int exynos_target(struct cpufreq_policy *policy, unsigned int index)
-{
-	return exynos_cpufreq_scale(exynos_info->freq_table[index].frequency);
-}
-
-static int exynos_cpufreq_cpu_init(struct cpufreq_policy *policy)
-{
-	policy->clk = exynos_info->cpu_clk;
-	policy->suspend_freq = locking_frequency;
-	return cpufreq_generic_init(policy, exynos_info->freq_table, 100000);
-}
-
-static struct cpufreq_driver exynos_driver = {
-	.flags		= CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify		= cpufreq_generic_frequency_table_verify,
-	.target_index	= exynos_target,
-	.get		= cpufreq_generic_get,
-	.init		= exynos_cpufreq_cpu_init,
-	.name		= "exynos_cpufreq",
-	.attr		= cpufreq_generic_attr,
-#ifdef CONFIG_ARM_EXYNOS_CPU_FREQ_BOOST_SW
-	.boost_supported = true,
-#endif
-#ifdef CONFIG_PM
-	.suspend	= cpufreq_generic_suspend,
-#endif
-};
-
-static int exynos_cpufreq_probe(struct platform_device *pdev)
-{
-	struct device_node *cpu0;
-	int ret = -EINVAL;
-
-	exynos_info = kzalloc(sizeof(*exynos_info), GFP_KERNEL);
-	if (!exynos_info)
-		return -ENOMEM;
-
-	exynos_info->dev = &pdev->dev;
-
-	if (of_machine_is_compatible("samsung,exynos4210")) {
-		exynos_info->type = EXYNOS_SOC_4210;
-		ret = exynos4210_cpufreq_init(exynos_info);
-	} else if (of_machine_is_compatible("samsung,exynos4212")) {
-		exynos_info->type = EXYNOS_SOC_4212;
-		ret = exynos4x12_cpufreq_init(exynos_info);
-	} else if (of_machine_is_compatible("samsung,exynos4412")) {
-		exynos_info->type = EXYNOS_SOC_4412;
-		ret = exynos4x12_cpufreq_init(exynos_info);
-	} else if (of_machine_is_compatible("samsung,exynos5250")) {
-		exynos_info->type = EXYNOS_SOC_5250;
-		ret = exynos5250_cpufreq_init(exynos_info);
-	} else {
-		pr_err("%s: Unknown SoC type\n", __func__);
-		return -ENODEV;
-	}
-
-	if (ret)
-		goto err_vdd_arm;
-
-	if (exynos_info->set_freq == NULL) {
-		dev_err(&pdev->dev, "No set_freq function (ERR)\n");
-		goto err_vdd_arm;
-	}
-
-	arm_regulator = regulator_get(NULL, "vdd_arm");
-	if (IS_ERR(arm_regulator)) {
-		dev_err(&pdev->dev, "failed to get resource vdd_arm\n");
-		goto err_vdd_arm;
-	}
-
-	/* Done here as we want to capture boot frequency */
-	locking_frequency = clk_get_rate(exynos_info->cpu_clk) / 1000;
-
-	ret = cpufreq_register_driver(&exynos_driver);
-	if (ret)
-		goto err_cpufreq_reg;
-
-	cpu0 = of_get_cpu_node(0, NULL);
-	if (!cpu0) {
-		pr_err("failed to find cpu0 node\n");
-		return 0;
-	}
-
-	if (of_find_property(cpu0, "#cooling-cells", NULL)) {
-		cdev = of_cpufreq_cooling_register(cpu0,
-						   cpu_present_mask);
-		if (IS_ERR(cdev))
-			pr_err("running cpufreq without cooling device: %ld\n",
-			       PTR_ERR(cdev));
-	}
-
-	return 0;
-
-err_cpufreq_reg:
-	dev_err(&pdev->dev, "failed to register cpufreq driver\n");
-	regulator_put(arm_regulator);
-err_vdd_arm:
-	kfree(exynos_info);
-	return -EINVAL;
-}
-
-static struct platform_driver exynos_cpufreq_platdrv = {
-	.driver = {
-		.name	= "exynos-cpufreq",
-	},
-	.probe = exynos_cpufreq_probe,
-};
-module_platform_driver(exynos_cpufreq_platdrv);
diff --git a/kernel/drivers/cpufreq/exynos-cpufreq.h b/kernel/drivers/cpufreq/exynos-cpufreq.h
deleted file mode 100644
index 9f2062a7c..000000000
--- a/kernel/drivers/cpufreq/exynos-cpufreq.h
+++ /dev/null
@@ -1,98 +0,0 @@
-/*
- * 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,
-};
-
-enum exynos_soc_type {
-	EXYNOS_SOC_4210,
-	EXYNOS_SOC_4212,
-	EXYNOS_SOC_4412,
-	EXYNOS_SOC_5250,
-};
-
-#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 {
-	enum exynos_soc_type type;
-	struct device	*dev;
-	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);
-	void __iomem	*cmu_regs;
-};
-
-#ifdef CONFIG_ARM_EXYNOS4210_CPUFREQ
-extern int exynos4210_cpufreq_init(struct exynos_dvfs_info *);
-#else
-static inline int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	return -EOPNOTSUPP;
-}
-#endif
-#ifdef CONFIG_ARM_EXYNOS4X12_CPUFREQ
-extern int exynos4x12_cpufreq_init(struct exynos_dvfs_info *);
-#else
-static inline int exynos4x12_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	return -EOPNOTSUPP;
-}
-#endif
-#ifdef CONFIG_ARM_EXYNOS5250_CPUFREQ
-extern int exynos5250_cpufreq_init(struct exynos_dvfs_info *);
-#else
-static inline int exynos5250_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	return -EOPNOTSUPP;
-}
-#endif
-
-#define EXYNOS4_CLKSRC_CPU			0x14200
-#define EXYNOS4_CLKMUX_STATCPU			0x14400
-
-#define EXYNOS4_CLKDIV_CPU			0x14500
-#define EXYNOS4_CLKDIV_CPU1			0x14504
-#define EXYNOS4_CLKDIV_STATCPU			0x14600
-#define EXYNOS4_CLKDIV_STATCPU1			0x14604
-
-#define EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT	(16)
-#define EXYNOS4_CLKMUX_STATCPU_MUXCORE_MASK	(0x7 << EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT)
-
-#define EXYNOS5_APLL_LOCK			0x00000
-#define EXYNOS5_APLL_CON0			0x00100
-#define EXYNOS5_CLKMUX_STATCPU			0x00400
-#define EXYNOS5_CLKDIV_CPU0			0x00500
-#define EXYNOS5_CLKDIV_CPU1			0x00504
-#define EXYNOS5_CLKDIV_STATCPU0			0x00600
-#define EXYNOS5_CLKDIV_STATCPU1			0x00604
diff --git a/kernel/drivers/cpufreq/exynos4210-cpufreq.c b/kernel/drivers/cpufreq/exynos4210-cpufreq.c
deleted file mode 100644
index 843ec824f..000000000
--- a/kernel/drivers/cpufreq/exynos4210-cpufreq.c
+++ /dev/null
@@ -1,184 +0,0 @@
-/*
- * Copyright (c) 2010-2011 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS4210 - CPU frequency scaling 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.
-*/
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/cpufreq.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include "exynos-cpufreq.h"
-
-static struct clk *cpu_clk;
-static struct clk *moutcore;
-static struct clk *mout_mpll;
-static struct clk *mout_apll;
-static struct exynos_dvfs_info *cpufreq;
-
-static unsigned int exynos4210_volt_table[] = {
-	1250000, 1150000, 1050000, 975000, 950000,
-};
-
-static struct cpufreq_frequency_table exynos4210_freq_table[] = {
-	{0, L0, 1200 * 1000},
-	{0, L1, 1000 * 1000},
-	{0, L2,  800 * 1000},
-	{0, L3,  500 * 1000},
-	{0, L4,  200 * 1000},
-	{0, 0, CPUFREQ_TABLE_END},
-};
-
-static struct apll_freq apll_freq_4210[] = {
-	/*
-	 * values:
-	 * freq
-	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, RESERVED
-	 * clock divider for COPY, HPM, RESERVED
-	 * PLL M, P, S
-	 */
-	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)
-{
-	unsigned int tmp;
-
-	/* Change Divider - CPU0 */
-
-	tmp = apll_freq_4210[div_index].clk_div_cpu0;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS4_CLKDIV_CPU);
-
-	do {
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKDIV_STATCPU);
-	} while (tmp & 0x1111111);
-
-	/* Change Divider - CPU1 */
-
-	tmp = apll_freq_4210[div_index].clk_div_cpu1;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS4_CLKDIV_CPU1);
-
-	do {
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKDIV_STATCPU1);
-	} while (tmp & 0x11);
-}
-
-static void exynos4210_set_apll(unsigned int index)
-{
-	unsigned int tmp, freq = apll_freq_4210[index].freq;
-
-	/* MUX_CORE_SEL = MPLL, ARMCLK uses MPLL for lock time */
-	clk_set_parent(moutcore, mout_mpll);
-
-	do {
-		tmp = (__raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKMUX_STATCPU)
-			>> EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT);
-		tmp &= 0x7;
-	} while (tmp != 0x2);
-
-	clk_set_rate(mout_apll, freq * 1000);
-
-	/* MUX_CORE_SEL = APLL */
-	clk_set_parent(moutcore, mout_apll);
-
-	do {
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKMUX_STATCPU);
-		tmp &= EXYNOS4_CLKMUX_STATCPU_MUXCORE_MASK;
-	} while (tmp != (0x1 << EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT));
-}
-
-static void exynos4210_set_frequency(unsigned int old_index,
-				     unsigned int new_index)
-{
-	if (old_index > new_index) {
-		exynos4210_set_clkdiv(new_index);
-		exynos4210_set_apll(new_index);
-	} else if (old_index < new_index) {
-		exynos4210_set_apll(new_index);
-		exynos4210_set_clkdiv(new_index);
-	}
-}
-
-int exynos4210_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	struct device_node *np;
-	unsigned long rate;
-
-	/*
-	 * HACK: This is a temporary workaround to get access to clock
-	 * controller registers directly and remove static mappings and
-	 * dependencies on platform headers. It is necessary to enable
-	 * Exynos multi-platform support and will be removed together with
-	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-dt driver.
-	 */
-	np = of_find_compatible_node(NULL, NULL, "samsung,exynos4210-clock");
-	if (!np) {
-		pr_err("%s: failed to find clock controller DT node\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	info->cmu_regs = of_iomap(np, 0);
-	if (!info->cmu_regs) {
-		pr_err("%s: failed to map CMU registers\n", __func__);
-		return -EFAULT;
-	}
-
-	cpu_clk = clk_get(NULL, "armclk");
-	if (IS_ERR(cpu_clk))
-		return PTR_ERR(cpu_clk);
-
-	moutcore = clk_get(NULL, "moutcore");
-	if (IS_ERR(moutcore))
-		goto err_moutcore;
-
-	mout_mpll = clk_get(NULL, "mout_mpll");
-	if (IS_ERR(mout_mpll))
-		goto err_mout_mpll;
-
-	rate = clk_get_rate(mout_mpll) / 1000;
-
-	mout_apll = clk_get(NULL, "mout_apll");
-	if (IS_ERR(mout_apll))
-		goto err_mout_apll;
-
-	info->mpll_freq_khz = rate;
-	/* 800Mhz */
-	info->pll_safe_idx = L2;
-	info->cpu_clk = cpu_clk;
-	info->volt_table = exynos4210_volt_table;
-	info->freq_table = exynos4210_freq_table;
-	info->set_freq = exynos4210_set_frequency;
-
-	cpufreq = info;
-
-	return 0;
-
-err_mout_apll:
-	clk_put(mout_mpll);
-err_mout_mpll:
-	clk_put(moutcore);
-err_moutcore:
-	clk_put(cpu_clk);
-
-	pr_debug("%s: failed initialization\n", __func__);
-	return -EINVAL;
-}
diff --git a/kernel/drivers/cpufreq/exynos4x12-cpufreq.c b/kernel/drivers/cpufreq/exynos4x12-cpufreq.c
deleted file mode 100644
index 9e78a850e..000000000
--- a/kernel/drivers/cpufreq/exynos4x12-cpufreq.c
+++ /dev/null
@@ -1,236 +0,0 @@
-/*
- * Copyright (c) 2010-2012 Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS4X12 - CPU frequency scaling 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.
-*/
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/cpufreq.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include "exynos-cpufreq.h"
-
-static struct clk *cpu_clk;
-static struct clk *moutcore;
-static struct clk *mout_mpll;
-static struct clk *mout_apll;
-static struct exynos_dvfs_info *cpufreq;
-
-static unsigned int exynos4x12_volt_table[] = {
-	1350000, 1287500, 1250000, 1187500, 1137500, 1087500, 1037500,
-	1000000,  987500,  975000,  950000,  925000,  900000,  900000
-};
-
-static struct cpufreq_frequency_table exynos4x12_freq_table[] = {
-	{CPUFREQ_BOOST_FREQ, L0, 1500 * 1000},
-	{0, L1, 1400 * 1000},
-	{0, L2, 1300 * 1000},
-	{0, L3, 1200 * 1000},
-	{0, L4, 1100 * 1000},
-	{0, L5, 1000 * 1000},
-	{0, L6,  900 * 1000},
-	{0, L7,  800 * 1000},
-	{0, L8,  700 * 1000},
-	{0, L9,  600 * 1000},
-	{0, L10, 500 * 1000},
-	{0, L11, 400 * 1000},
-	{0, L12, 300 * 1000},
-	{0, L13, 200 * 1000},
-	{0, 0, CPUFREQ_TABLE_END},
-};
-
-static struct apll_freq *apll_freq_4x12;
-
-static struct apll_freq apll_freq_4212[] = {
-	/*
-	 * values:
-	 * freq
-	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, CORE2
-	 * clock divider for COPY, HPM, RESERVED
-	 * PLL M, P, S
-	 */
-	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 struct apll_freq apll_freq_4412[] = {
-	/*
-	 * values:
-	 * freq
-	 * clock divider for CORE, COREM0, COREM1, PERIPH, ATB, PCLK_DBG, APLL, CORE2
-	 * clock divider for COPY, HPM, CORES
-	 * PLL M, P, S
-	 */
-	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)
-{
-	unsigned int tmp;
-
-	/* Change Divider - CPU0 */
-
-	tmp = apll_freq_4x12[div_index].clk_div_cpu0;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS4_CLKDIV_CPU);
-
-	while (__raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKDIV_STATCPU)
-	       & 0x11111111)
-		cpu_relax();
-
-	/* Change Divider - CPU1 */
-	tmp = apll_freq_4x12[div_index].clk_div_cpu1;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS4_CLKDIV_CPU1);
-
-	do {
-		cpu_relax();
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKDIV_STATCPU1);
-	} while (tmp != 0x0);
-}
-
-static void exynos4x12_set_apll(unsigned int index)
-{
-	unsigned int tmp, freq = apll_freq_4x12[index].freq;
-
-	/* MUX_CORE_SEL = MPLL, ARMCLK uses MPLL for lock time */
-	clk_set_parent(moutcore, mout_mpll);
-
-	do {
-		cpu_relax();
-		tmp = (__raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKMUX_STATCPU)
-			>> EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT);
-		tmp &= 0x7;
-	} while (tmp != 0x2);
-
-	clk_set_rate(mout_apll, freq * 1000);
-
-	/* MUX_CORE_SEL = APLL */
-	clk_set_parent(moutcore, mout_apll);
-
-	do {
-		cpu_relax();
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS4_CLKMUX_STATCPU);
-		tmp &= EXYNOS4_CLKMUX_STATCPU_MUXCORE_MASK;
-	} while (tmp != (0x1 << EXYNOS4_CLKSRC_CPU_MUXCORE_SHIFT));
-}
-
-static void exynos4x12_set_frequency(unsigned int old_index,
-				  unsigned int new_index)
-{
-	if (old_index > new_index) {
-		exynos4x12_set_clkdiv(new_index);
-		exynos4x12_set_apll(new_index);
-	} else if (old_index < new_index) {
-		exynos4x12_set_apll(new_index);
-		exynos4x12_set_clkdiv(new_index);
-	}
-}
-
-int exynos4x12_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	struct device_node *np;
-	unsigned long rate;
-
-	/*
-	 * HACK: This is a temporary workaround to get access to clock
-	 * controller registers directly and remove static mappings and
-	 * dependencies on platform headers. It is necessary to enable
-	 * Exynos multi-platform support and will be removed together with
-	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-dt driver.
-	 */
-	np = of_find_compatible_node(NULL, NULL, "samsung,exynos4412-clock");
-	if (!np) {
-		pr_err("%s: failed to find clock controller DT node\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	info->cmu_regs = of_iomap(np, 0);
-	if (!info->cmu_regs) {
-		pr_err("%s: failed to map CMU registers\n", __func__);
-		return -EFAULT;
-	}
-
-	cpu_clk = clk_get(NULL, "armclk");
-	if (IS_ERR(cpu_clk))
-		return PTR_ERR(cpu_clk);
-
-	moutcore = clk_get(NULL, "moutcore");
-	if (IS_ERR(moutcore))
-		goto err_moutcore;
-
-	mout_mpll = clk_get(NULL, "mout_mpll");
-	if (IS_ERR(mout_mpll))
-		goto err_mout_mpll;
-
-	rate = clk_get_rate(mout_mpll) / 1000;
-
-	mout_apll = clk_get(NULL, "mout_apll");
-	if (IS_ERR(mout_apll))
-		goto err_mout_apll;
-
-	if (info->type == EXYNOS_SOC_4212)
-		apll_freq_4x12 = apll_freq_4212;
-	else
-		apll_freq_4x12 = apll_freq_4412;
-
-	info->mpll_freq_khz = rate;
-	/* 800Mhz */
-	info->pll_safe_idx = L7;
-	info->cpu_clk = cpu_clk;
-	info->volt_table = exynos4x12_volt_table;
-	info->freq_table = exynos4x12_freq_table;
-	info->set_freq = exynos4x12_set_frequency;
-
-	cpufreq = info;
-
-	return 0;
-
-err_mout_apll:
-	clk_put(mout_mpll);
-err_mout_mpll:
-	clk_put(moutcore);
-err_moutcore:
-	clk_put(cpu_clk);
-
-	pr_debug("%s: failed initialization\n", __func__);
-	return -EINVAL;
-}
diff --git a/kernel/drivers/cpufreq/exynos5250-cpufreq.c b/kernel/drivers/cpufreq/exynos5250-cpufreq.c
deleted file mode 100644
index 3eafdc7ba..000000000
--- a/kernel/drivers/cpufreq/exynos5250-cpufreq.c
+++ /dev/null
@@ -1,210 +0,0 @@
-/*
- * Copyright (c) 2010-20122Samsung Electronics Co., Ltd.
- *		http://www.samsung.com
- *
- * EXYNOS5250 - CPU frequency scaling 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.
-*/
-
-#include <linux/module.h>
-#include <linux/kernel.h>
-#include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/cpufreq.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-
-#include "exynos-cpufreq.h"
-
-static struct clk *cpu_clk;
-static struct clk *moutcore;
-static struct clk *mout_mpll;
-static struct clk *mout_apll;
-static struct exynos_dvfs_info *cpufreq;
-
-static unsigned int exynos5250_volt_table[] = {
-	1300000, 1250000, 1225000, 1200000, 1150000,
-	1125000, 1100000, 1075000, 1050000, 1025000,
-	1012500, 1000000,  975000,  950000,  937500,
-	925000
-};
-
-static struct cpufreq_frequency_table exynos5250_freq_table[] = {
-	{0, L0, 1700 * 1000},
-	{0, L1, 1600 * 1000},
-	{0, L2, 1500 * 1000},
-	{0, L3, 1400 * 1000},
-	{0, L4, 1300 * 1000},
-	{0, L5, 1200 * 1000},
-	{0, L6, 1100 * 1000},
-	{0, L7, 1000 * 1000},
-	{0, L8,  900 * 1000},
-	{0, L9,  800 * 1000},
-	{0, L10, 700 * 1000},
-	{0, L11, 600 * 1000},
-	{0, L12, 500 * 1000},
-	{0, L13, 400 * 1000},
-	{0, L14, 300 * 1000},
-	{0, L15, 200 * 1000},
-	{0, 0, CPUFREQ_TABLE_END},
-};
-
-static struct apll_freq apll_freq_5250[] = {
-	/*
-	 * values:
-	 * freq
-	 * clock divider for ARM, CPUD, ACP, PERIPH, ATB, PCLK_DBG, APLL, ARM2
-	 * clock divider for COPY, HPM, RESERVED
-	 * PLL M, P, S
-	 */
-	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)
-{
-	unsigned int tmp;
-
-	/* Change Divider - CPU0 */
-
-	tmp = apll_freq_5250[div_index].clk_div_cpu0;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS5_CLKDIV_CPU0);
-
-	while (__raw_readl(cpufreq->cmu_regs + EXYNOS5_CLKDIV_STATCPU0)
-	       & 0x11111111)
-		cpu_relax();
-
-	/* Change Divider - CPU1 */
-	tmp = apll_freq_5250[div_index].clk_div_cpu1;
-
-	__raw_writel(tmp, cpufreq->cmu_regs + EXYNOS5_CLKDIV_CPU1);
-
-	while (__raw_readl(cpufreq->cmu_regs + EXYNOS5_CLKDIV_STATCPU1) & 0x11)
-		cpu_relax();
-}
-
-static void set_apll(unsigned int index)
-{
-	unsigned int tmp;
-	unsigned int freq = apll_freq_5250[index].freq;
-
-	/* MUX_CORE_SEL = MPLL, ARMCLK uses MPLL for lock time */
-	clk_set_parent(moutcore, mout_mpll);
-
-	do {
-		cpu_relax();
-		tmp = (__raw_readl(cpufreq->cmu_regs + EXYNOS5_CLKMUX_STATCPU)
-			>> 16);
-		tmp &= 0x7;
-	} while (tmp != 0x2);
-
-	clk_set_rate(mout_apll, freq * 1000);
-
-	/* MUX_CORE_SEL = APLL */
-	clk_set_parent(moutcore, mout_apll);
-
-	do {
-		cpu_relax();
-		tmp = __raw_readl(cpufreq->cmu_regs + EXYNOS5_CLKMUX_STATCPU);
-		tmp &= (0x7 << 16);
-	} while (tmp != (0x1 << 16));
-}
-
-static void exynos5250_set_frequency(unsigned int old_index,
-				  unsigned int new_index)
-{
-	if (old_index > new_index) {
-		set_clkdiv(new_index);
-		set_apll(new_index);
-	} else if (old_index < new_index) {
-		set_apll(new_index);
-		set_clkdiv(new_index);
-	}
-}
-
-int exynos5250_cpufreq_init(struct exynos_dvfs_info *info)
-{
-	struct device_node *np;
-	unsigned long rate;
-
-	/*
-	 * HACK: This is a temporary workaround to get access to clock
-	 * controller registers directly and remove static mappings and
-	 * dependencies on platform headers. It is necessary to enable
-	 * Exynos multi-platform support and will be removed together with
-	 * this whole driver as soon as Exynos gets migrated to use
-	 * cpufreq-dt driver.
-	 */
-	np = of_find_compatible_node(NULL, NULL, "samsung,exynos5250-clock");
-	if (!np) {
-		pr_err("%s: failed to find clock controller DT node\n",
-			__func__);
-		return -ENODEV;
-	}
-
-	info->cmu_regs = of_iomap(np, 0);
-	if (!info->cmu_regs) {
-		pr_err("%s: failed to map CMU registers\n", __func__);
-		return -EFAULT;
-	}
-
-	cpu_clk = clk_get(NULL, "armclk");
-	if (IS_ERR(cpu_clk))
-		return PTR_ERR(cpu_clk);
-
-	moutcore = clk_get(NULL, "mout_cpu");
-	if (IS_ERR(moutcore))
-		goto err_moutcore;
-
-	mout_mpll = clk_get(NULL, "mout_mpll");
-	if (IS_ERR(mout_mpll))
-		goto err_mout_mpll;
-
-	rate = clk_get_rate(mout_mpll) / 1000;
-
-	mout_apll = clk_get(NULL, "mout_apll");
-	if (IS_ERR(mout_apll))
-		goto err_mout_apll;
-
-	info->mpll_freq_khz = rate;
-	/* 800Mhz */
-	info->pll_safe_idx = L9;
-	info->cpu_clk = cpu_clk;
-	info->volt_table = exynos5250_volt_table;
-	info->freq_table = exynos5250_freq_table;
-	info->set_freq = exynos5250_set_frequency;
-
-	cpufreq = info;
-
-	return 0;
-
-err_mout_apll:
-	clk_put(mout_mpll);
-err_mout_mpll:
-	clk_put(moutcore);
-err_moutcore:
-	clk_put(cpu_clk);
-
-	pr_err("%s: failed initialization\n", __func__);
-	return -EINVAL;
-}
diff --git a/kernel/drivers/cpufreq/exynos5440-cpufreq.c b/kernel/drivers/cpufreq/exynos5440-cpufreq.c
index 21a90ed7f..c0f337370 100644
--- a/kernel/drivers/cpufreq/exynos5440-cpufreq.c
+++ b/kernel/drivers/cpufreq/exynos5440-cpufreq.c
@@ -360,7 +360,7 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 		goto err_put_node;
 	}
 
-	ret = of_init_opp_table(dvfs_info->dev);
+	ret = dev_pm_opp_of_add_table(dvfs_info->dev);
 	if (ret) {
 		dev_err(dvfs_info->dev, "failed to init OPP table: %d\n", ret);
 		goto err_put_node;
@@ -424,7 +424,7 @@ static int exynos_cpufreq_probe(struct platform_device *pdev)
 err_free_table:
 	dev_pm_opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
 err_free_opp:
-	of_free_opp_table(dvfs_info->dev);
+	dev_pm_opp_of_remove_table(dvfs_info->dev);
 err_put_node:
 	of_node_put(np);
 	dev_err(&pdev->dev, "%s: failed initialization\n", __func__);
@@ -435,7 +435,7 @@ static int exynos_cpufreq_remove(struct platform_device *pdev)
 {
 	cpufreq_unregister_driver(&exynos_driver);
 	dev_pm_opp_free_cpufreq_table(dvfs_info->dev, &dvfs_info->freq_table);
-	of_free_opp_table(dvfs_info->dev);
+	dev_pm_opp_of_remove_table(dvfs_info->dev);
 	return 0;
 }
 
diff --git a/kernel/drivers/cpufreq/freq_table.c b/kernel/drivers/cpufreq/freq_table.c
index df14766a8..a8f1daffc 100644
--- a/kernel/drivers/cpufreq/freq_table.c
+++ b/kernel/drivers/cpufreq/freq_table.c
@@ -18,6 +18,21 @@
  *                     FREQUENCY TABLE HELPERS                       *
  *********************************************************************/
 
+bool policy_has_boost_freq(struct cpufreq_policy *policy)
+{
+	struct cpufreq_frequency_table *pos, *table = policy->freq_table;
+
+	if (!table)
+		return false;
+
+	cpufreq_for_each_valid_entry(pos, table)
+		if (pos->flags & CPUFREQ_BOOST_FREQ)
+			return true;
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(policy_has_boost_freq);
+
 int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
 				    struct cpufreq_frequency_table *table)
 {
@@ -297,15 +312,6 @@ int cpufreq_table_validate_and_show(struct cpufreq_policy *policy,
 }
 EXPORT_SYMBOL_GPL(cpufreq_table_validate_and_show);
 
-struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu);
-
-struct cpufreq_frequency_table *cpufreq_frequency_get_table(unsigned int cpu)
-{
-	struct cpufreq_policy *policy = cpufreq_cpu_get_raw(cpu);
-	return policy ? policy->freq_table : NULL;
-}
-EXPORT_SYMBOL_GPL(cpufreq_frequency_get_table);
-
 MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
 MODULE_DESCRIPTION("CPUfreq frequency table helpers");
 MODULE_LICENSE("GPL");
diff --git a/kernel/drivers/cpufreq/gx-suspmod.c b/kernel/drivers/cpufreq/gx-suspmod.c
index 1d723dc88..3488c9c17 100644
--- a/kernel/drivers/cpufreq/gx-suspmod.c
+++ b/kernel/drivers/cpufreq/gx-suspmod.c
@@ -144,7 +144,7 @@ module_param(max_duration, int, 0444);
 
 
 /**
- * we can detect a core multipiler from dir0_lsb
+ * we can detect a core multiplier from dir0_lsb
  * from GX1 datasheet p.56,
  *	MULT[3:0]:
  *	0000 = SYSCLK multiplied by 4 (test only)
@@ -346,7 +346,7 @@ static int cpufreq_gx_verify(struct cpufreq_policy *policy)
 
 	/* it needs to be assured that at least one supported frequency is
 	 * within policy->min and policy->max. If it is not, policy->max
-	 * needs to be increased until one freuqency is supported.
+	 * needs to be increased until one frequency is supported.
 	 * policy->min may not be decreased, though. This way we guarantee a
 	 * specific processing capacity.
 	 */
diff --git a/kernel/drivers/cpufreq/ia64-acpi-cpufreq.c b/kernel/drivers/cpufreq/ia64-acpi-cpufreq.c
index c30aaa6a5..0202429f1 100644
--- a/kernel/drivers/cpufreq/ia64-acpi-cpufreq.c
+++ b/kernel/drivers/cpufreq/ia64-acpi-cpufreq.c
@@ -29,7 +29,6 @@ MODULE_LICENSE("GPL");
 
 struct cpufreq_acpi_io {
 	struct acpi_processor_performance	acpi_data;
-	struct cpufreq_frequency_table		*freq_table;
 	unsigned int				resume;
 };
 
@@ -221,6 +220,7 @@ acpi_cpufreq_cpu_init (
 	unsigned int		cpu = policy->cpu;
 	struct cpufreq_acpi_io	*data;
 	unsigned int		result = 0;
+	struct cpufreq_frequency_table *freq_table;
 
 	pr_debug("acpi_cpufreq_cpu_init\n");
 
@@ -254,10 +254,10 @@ acpi_cpufreq_cpu_init (
 	}
 
 	/* alloc freq_table */
-	data->freq_table = kzalloc(sizeof(*data->freq_table) *
+	freq_table = kzalloc(sizeof(*freq_table) *
 	                           (data->acpi_data.state_count + 1),
 	                           GFP_KERNEL);
-	if (!data->freq_table) {
+	if (!freq_table) {
 		result = -ENOMEM;
 		goto err_unreg;
 	}
@@ -276,14 +276,14 @@ acpi_cpufreq_cpu_init (
 	for (i = 0; i <= data->acpi_data.state_count; i++)
 	{
 		if (i < data->acpi_data.state_count) {
-			data->freq_table[i].frequency =
+			freq_table[i].frequency =
 			      data->acpi_data.states[i].core_frequency * 1000;
 		} else {
-			data->freq_table[i].frequency = CPUFREQ_TABLE_END;
+			freq_table[i].frequency = CPUFREQ_TABLE_END;
 		}
 	}
 
-	result = cpufreq_table_validate_and_show(policy, data->freq_table);
+	result = cpufreq_table_validate_and_show(policy, freq_table);
 	if (result) {
 		goto err_freqfree;
 	}
@@ -311,9 +311,9 @@ acpi_cpufreq_cpu_init (
 	return (result);
 
  err_freqfree:
-	kfree(data->freq_table);
+	kfree(freq_table);
  err_unreg:
-	acpi_processor_unregister_performance(&data->acpi_data, cpu);
+	acpi_processor_unregister_performance(cpu);
  err_free:
 	kfree(data);
 	acpi_io_data[cpu] = NULL;
@@ -332,8 +332,8 @@ acpi_cpufreq_cpu_exit (
 
 	if (data) {
 		acpi_io_data[policy->cpu] = NULL;
-		acpi_processor_unregister_performance(&data->acpi_data,
-		                                      policy->cpu);
+		acpi_processor_unregister_performance(policy->cpu);
+		kfree(policy->freq_table);
 		kfree(data);
 	}
 
diff --git a/kernel/drivers/cpufreq/imx6q-cpufreq.c b/kernel/drivers/cpufreq/imx6q-cpufreq.c
index 380a90d3c..ef1fa8145 100644
--- a/kernel/drivers/cpufreq/imx6q-cpufreq.c
+++ b/kernel/drivers/cpufreq/imx6q-cpufreq.c
@@ -30,6 +30,10 @@ static struct clk *pll1_sw_clk;
 static struct clk *step_clk;
 static struct clk *pll2_pfd2_396m_clk;
 
+/* clk used by i.MX6UL */
+static struct clk *pll2_bus_clk;
+static struct clk *secondary_sel_clk;
+
 static struct device *cpu_dev;
 static bool free_opp;
 static struct cpufreq_frequency_table *freq_table;
@@ -91,16 +95,36 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index)
 	 * 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.
-	 *
+	 * For i.MX6UL, it has a secondary clk mux, the cpu frequency change
+	 * flow is slightly different from other i.MX6 OSC.
+	 * The cpu frequeny change flow for i.MX6(except i.MX6UL) 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_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, new_freq * 1000);
+	if (of_machine_is_compatible("fsl,imx6ul")) {
+		/*
+		 * When changing pll1_sw_clk's parent to pll1_sys_clk,
+		 * CPU may run at higher than 528MHz, this will lead to
+		 * the system unstable if the voltage is lower than the
+		 * voltage of 528MHz, so lower the CPU frequency to one
+		 * half before changing CPU frequency.
+		 */
+		clk_set_rate(arm_clk, (old_freq >> 1) * 1000);
 		clk_set_parent(pll1_sw_clk, pll1_sys_clk);
+		if (freq_hz > clk_get_rate(pll2_pfd2_396m_clk))
+			clk_set_parent(secondary_sel_clk, pll2_bus_clk);
+		else
+			clk_set_parent(secondary_sel_clk, pll2_pfd2_396m_clk);
+		clk_set_parent(step_clk, secondary_sel_clk);
+		clk_set_parent(pll1_sw_clk, step_clk);
+	} else {
+		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, new_freq * 1000);
+			clk_set_parent(pll1_sw_clk, pll1_sys_clk);
+		}
 	}
 
 	/* Ensure the arm clock divider is what we expect */
@@ -186,6 +210,16 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 		goto put_clk;
 	}
 
+	if (of_machine_is_compatible("fsl,imx6ul")) {
+		pll2_bus_clk = clk_get(cpu_dev, "pll2_bus");
+		secondary_sel_clk = clk_get(cpu_dev, "secondary_sel");
+		if (IS_ERR(pll2_bus_clk) || IS_ERR(secondary_sel_clk)) {
+			dev_err(cpu_dev, "failed to get clocks specific to imx6ul\n");
+			ret = -ENOENT;
+			goto put_clk;
+		}
+	}
+
 	arm_reg = regulator_get(cpu_dev, "arm");
 	pu_reg = regulator_get_optional(cpu_dev, "pu");
 	soc_reg = regulator_get(cpu_dev, "soc");
@@ -202,7 +236,7 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev)
 	 */
 	num = dev_pm_opp_get_opp_count(cpu_dev);
 	if (num < 0) {
-		ret = of_init_opp_table(cpu_dev);
+		ret = dev_pm_opp_of_add_table(cpu_dev);
 		if (ret < 0) {
 			dev_err(cpu_dev, "failed to init OPP table: %d\n", ret);
 			goto put_reg;
@@ -312,7 +346,7 @@ free_freq_table:
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 out_free_opp:
 	if (free_opp)
-		of_free_opp_table(cpu_dev);
+		dev_pm_opp_of_remove_table(cpu_dev);
 put_reg:
 	if (!IS_ERR(arm_reg))
 		regulator_put(arm_reg);
@@ -331,6 +365,10 @@ put_clk:
 		clk_put(step_clk);
 	if (!IS_ERR(pll2_pfd2_396m_clk))
 		clk_put(pll2_pfd2_396m_clk);
+	if (!IS_ERR(pll2_bus_clk))
+		clk_put(pll2_bus_clk);
+	if (!IS_ERR(secondary_sel_clk))
+		clk_put(secondary_sel_clk);
 	of_node_put(np);
 	return ret;
 }
@@ -340,7 +378,7 @@ static int imx6q_cpufreq_remove(struct platform_device *pdev)
 	cpufreq_unregister_driver(&imx6q_cpufreq_driver);
 	dev_pm_opp_free_cpufreq_table(cpu_dev, &freq_table);
 	if (free_opp)
-		of_free_opp_table(cpu_dev);
+		dev_pm_opp_of_remove_table(cpu_dev);
 	regulator_put(arm_reg);
 	if (!IS_ERR(pu_reg))
 		regulator_put(pu_reg);
@@ -350,6 +388,8 @@ static int imx6q_cpufreq_remove(struct platform_device *pdev)
 	clk_put(pll1_sw_clk);
 	clk_put(step_clk);
 	clk_put(pll2_pfd2_396m_clk);
+	clk_put(pll2_bus_clk);
+	clk_put(secondary_sel_clk);
 
 	return 0;
 }
diff --git a/kernel/drivers/cpufreq/integrator-cpufreq.c b/kernel/drivers/cpufreq/integrator-cpufreq.c
index 129e266f7..79e3ff277 100644
--- a/kernel/drivers/cpufreq/integrator-cpufreq.c
+++ b/kernel/drivers/cpufreq/integrator-cpufreq.c
@@ -98,11 +98,10 @@ static int integrator_set_target(struct cpufreq_policy *policy,
 	/* get current setting */
 	cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET);
 
-	if (machine_is_integrator()) {
+	if (machine_is_integrator())
 		vco.s = (cm_osc >> 8) & 7;
-	} else if (machine_is_cintegrator()) {
+	else if (machine_is_cintegrator())
 		vco.s = 1;
-	}
 	vco.v = cm_osc & 255;
 	vco.r = 22;
 	freqs.old = icst_hz(&cclk_params, vco) / 1000;
@@ -163,11 +162,10 @@ static unsigned int integrator_get(unsigned int cpu)
 	/* detect memory etc. */
 	cm_osc = __raw_readl(cm_base + INTEGRATOR_HDR_OSC_OFFSET);
 
-	if (machine_is_integrator()) {
+	if (machine_is_integrator())
 		vco.s = (cm_osc >> 8) & 7;
-	} else {
+	else
 		vco.s = 1;
-	}
 	vco.v = cm_osc & 255;
 	vco.r = 22;
 
@@ -203,7 +201,7 @@ static int __init integrator_cpufreq_probe(struct platform_device *pdev)
 	struct resource *res;
 
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-        if (!res)
+	if (!res)
 		return -ENODEV;
 
 	cm_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
@@ -223,6 +221,8 @@ static const struct of_device_id integrator_cpufreq_match[] = {
 	{ },
 };
 
+MODULE_DEVICE_TABLE(of, integrator_cpufreq_match);
+
 static struct platform_driver integrator_cpufreq_driver = {
 	.driver = {
 		.name = "integrator-cpufreq",
@@ -234,6 +234,6 @@ static struct platform_driver integrator_cpufreq_driver = {
 module_platform_driver_probe(integrator_cpufreq_driver,
 			     integrator_cpufreq_probe);
 
-MODULE_AUTHOR ("Russell M. King");
-MODULE_DESCRIPTION ("cpufreq driver for ARM Integrator CPUs");
-MODULE_LICENSE ("GPL");
+MODULE_AUTHOR("Russell M. King");
+MODULE_DESCRIPTION("cpufreq driver for ARM Integrator CPUs");
+MODULE_LICENSE("GPL");
diff --git a/kernel/drivers/cpufreq/intel_pstate.c b/kernel/drivers/cpufreq/intel_pstate.c
index 6f9d27f90..98fb88213 100644
--- a/kernel/drivers/cpufreq/intel_pstate.c
+++ b/kernel/drivers/cpufreq/intel_pstate.c
@@ -26,6 +26,7 @@
 #include <linux/fs.h>
 #include <linux/debugfs.h>
 #include <linux/acpi.h>
+#include <linux/vmalloc.h>
 #include <trace/events/power.h>
 
 #include <asm/div64.h>
@@ -33,24 +34,23 @@
 #include <asm/cpu_device_id.h>
 #include <asm/cpufeature.h>
 
-#define BYT_RATIOS		0x66a
-#define BYT_VIDS		0x66b
-#define BYT_TURBO_RATIOS	0x66c
-#define BYT_TURBO_VIDS		0x66d
+#define ATOM_RATIOS		0x66a
+#define ATOM_VIDS		0x66b
+#define ATOM_TURBO_RATIOS	0x66c
+#define ATOM_TURBO_VIDS		0x66d
 
 #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)
+static inline int32_t div_fp(s64 x, s64 y)
 {
-	return div_s64((int64_t)x << FRAC_BITS, y);
+	return div64_s64((int64_t)x << FRAC_BITS, y);
 }
 
 static inline int ceiling_fp(int32_t x)
@@ -68,6 +68,7 @@ struct sample {
 	int32_t core_pct_busy;
 	u64 aperf;
 	u64 mperf;
+	u64 tsc;
 	int freq;
 	ktime_t time;
 };
@@ -76,6 +77,7 @@ struct pstate_data {
 	int	current_pstate;
 	int	min_pstate;
 	int	max_pstate;
+	int	max_pstate_physical;
 	int	scaling;
 	int	turbo_pstate;
 };
@@ -109,6 +111,7 @@ struct cpudata {
 	ktime_t last_sample_time;
 	u64	prev_aperf;
 	u64	prev_mperf;
+	u64	prev_tsc;
 	struct sample sample;
 };
 
@@ -124,6 +127,7 @@ struct pstate_adjust_policy {
 
 struct pstate_funcs {
 	int (*get_max)(void);
+	int (*get_max_physical)(void);
 	int (*get_min)(void);
 	int (*get_turbo)(void);
 	int (*get_scaling)(void);
@@ -153,7 +157,20 @@ struct perf_limits {
 	int min_sysfs_pct;
 };
 
-static struct perf_limits limits = {
+static struct perf_limits performance_limits = {
+	.no_turbo = 0,
+	.turbo_disabled = 0,
+	.max_perf_pct = 100,
+	.max_perf = int_tofp(1),
+	.min_perf_pct = 100,
+	.min_perf = int_tofp(1),
+	.max_policy_pct = 100,
+	.max_sysfs_pct = 100,
+	.min_policy_pct = 0,
+	.min_sysfs_pct = 0,
+};
+
+static struct perf_limits powersave_limits = {
 	.no_turbo = 0,
 	.turbo_disabled = 0,
 	.max_perf_pct = 100,
@@ -166,6 +183,12 @@ static struct perf_limits limits = {
 	.min_sysfs_pct = 0,
 };
 
+#ifdef CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE
+static struct perf_limits *limits = &performance_limits;
+#else
+static struct perf_limits *limits = &powersave_limits;
+#endif
+
 static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
 			     int deadband, int integral) {
 	pid->setpoint = setpoint;
@@ -252,29 +275,36 @@ static inline void update_turbo_state(void)
 
 	cpu = all_cpu_data[0];
 	rdmsrl(MSR_IA32_MISC_ENABLE, misc_en);
-	limits.turbo_disabled =
+	limits->turbo_disabled =
 		(misc_en & MSR_IA32_MISC_ENABLE_TURBO_DISABLE ||
 		 cpu->pstate.max_pstate == cpu->pstate.turbo_pstate);
 }
 
-#define PCT_TO_HWP(x) (x * 255 / 100)
 static void intel_pstate_hwp_set(void)
 {
-	int min, max, cpu;
-	u64 value, freq;
+	int min, hw_min, max, hw_max, cpu, range, adj_range;
+	u64 value, cap;
+
+	rdmsrl(MSR_HWP_CAPABILITIES, cap);
+	hw_min = HWP_LOWEST_PERF(cap);
+	hw_max = HWP_HIGHEST_PERF(cap);
+	range = hw_max - hw_min;
 
 	get_online_cpus();
 
 	for_each_online_cpu(cpu) {
 		rdmsrl_on_cpu(cpu, MSR_HWP_REQUEST, &value);
-		min = PCT_TO_HWP(limits.min_perf_pct);
+		adj_range = limits->min_perf_pct * range / 100;
+		min = hw_min + adj_range;
 		value &= ~HWP_MIN_PERF(~0L);
 		value |= HWP_MIN_PERF(min);
 
-		max = PCT_TO_HWP(limits.max_perf_pct);
-		if (limits.no_turbo) {
-			rdmsrl( MSR_HWP_CAPABILITIES, freq);
-			max = HWP_GUARANTEED_PERF(freq);
+		adj_range = limits->max_perf_pct * range / 100;
+		max = hw_min + adj_range;
+		if (limits->no_turbo) {
+			hw_max = HWP_GUARANTEED_PERF(cap);
+			if (hw_max < max)
+				max = hw_max;
 		}
 
 		value &= ~HWP_MAX_PERF(~0L);
@@ -340,7 +370,7 @@ static void __init intel_pstate_debug_expose_params(void)
 	static ssize_t show_##file_name					\
 	(struct kobject *kobj, struct attribute *attr, char *buf)	\
 	{								\
-		return sprintf(buf, "%u\n", limits.object);		\
+		return sprintf(buf, "%u\n", limits->object);		\
 	}
 
 static ssize_t show_turbo_pct(struct kobject *kobj,
@@ -376,10 +406,10 @@ static ssize_t show_no_turbo(struct kobject *kobj,
 	ssize_t ret;
 
 	update_turbo_state();
-	if (limits.turbo_disabled)
-		ret = sprintf(buf, "%u\n", limits.turbo_disabled);
+	if (limits->turbo_disabled)
+		ret = sprintf(buf, "%u\n", limits->turbo_disabled);
 	else
-		ret = sprintf(buf, "%u\n", limits.no_turbo);
+		ret = sprintf(buf, "%u\n", limits->no_turbo);
 
 	return ret;
 }
@@ -395,12 +425,12 @@ static ssize_t store_no_turbo(struct kobject *a, struct attribute *b,
 		return -EINVAL;
 
 	update_turbo_state();
-	if (limits.turbo_disabled) {
-		pr_warn("Turbo disabled by BIOS or unavailable on processor\n");
+	if (limits->turbo_disabled) {
+		pr_warn("intel_pstate: Turbo disabled by BIOS or unavailable on processor\n");
 		return -EPERM;
 	}
 
-	limits.no_turbo = clamp_t(int, input, 0, 1);
+	limits->no_turbo = clamp_t(int, input, 0, 1);
 
 	if (hwp_active)
 		intel_pstate_hwp_set();
@@ -418,9 +448,15 @@ static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
-	limits.max_sysfs_pct = clamp_t(int, input, 0 , 100);
-	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
-	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
+	limits->max_sysfs_pct = clamp_t(int, input, 0 , 100);
+	limits->max_perf_pct = min(limits->max_policy_pct,
+				   limits->max_sysfs_pct);
+	limits->max_perf_pct = max(limits->min_policy_pct,
+				   limits->max_perf_pct);
+	limits->max_perf_pct = max(limits->min_perf_pct,
+				   limits->max_perf_pct);
+	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
+				  int_tofp(100));
 
 	if (hwp_active)
 		intel_pstate_hwp_set();
@@ -437,9 +473,15 @@ static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
 	if (ret != 1)
 		return -EINVAL;
 
-	limits.min_sysfs_pct = clamp_t(int, input, 0 , 100);
-	limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct);
-	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
+	limits->min_sysfs_pct = clamp_t(int, input, 0 , 100);
+	limits->min_perf_pct = max(limits->min_policy_pct,
+				   limits->min_sysfs_pct);
+	limits->min_perf_pct = min(limits->max_policy_pct,
+				   limits->min_perf_pct);
+	limits->min_perf_pct = min(limits->max_perf_pct,
+				   limits->min_perf_pct);
+	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
+				  int_tofp(100));
 
 	if (hwp_active)
 		intel_pstate_hwp_set();
@@ -481,46 +523,43 @@ static void __init intel_pstate_sysfs_expose_params(void)
 }
 /************************** sysfs end ************************/
 
-static void intel_pstate_hwp_enable(void)
+static void intel_pstate_hwp_enable(struct cpudata *cpudata)
 {
-	hwp_active++;
-	pr_info("intel_pstate HWP enabled\n");
-
-	wrmsrl( MSR_PM_ENABLE, 0x1);
+	wrmsrl_on_cpu(cpudata->cpu, MSR_PM_ENABLE, 0x1);
 }
 
-static int byt_get_min_pstate(void)
+static int atom_get_min_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 8) & 0x7F;
 }
 
-static int byt_get_max_pstate(void)
+static int atom_get_max_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_RATIOS, value);
+	rdmsrl(ATOM_RATIOS, value);
 	return (value >> 16) & 0x7F;
 }
 
-static int byt_get_turbo_pstate(void)
+static int atom_get_turbo_pstate(void)
 {
 	u64 value;
 
-	rdmsrl(BYT_TURBO_RATIOS, value);
+	rdmsrl(ATOM_TURBO_RATIOS, value);
 	return value & 0x7F;
 }
 
-static void byt_set_pstate(struct cpudata *cpudata, int pstate)
+static void atom_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 	int32_t vid_fp;
 	u32 vid;
 
-	val = pstate << 8;
-	if (limits.no_turbo && !limits.turbo_disabled)
+	val = (u64)pstate << 8;
+	if (limits->no_turbo && !limits->turbo_disabled)
 		val |= (u64)1 << 32;
 
 	vid_fp = cpudata->vid.min + mul_fp(
@@ -538,27 +577,42 @@ static void byt_set_pstate(struct cpudata *cpudata, int pstate)
 	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
 }
 
-#define BYT_BCLK_FREQS 5
-static int byt_freq_table[BYT_BCLK_FREQS] = { 833, 1000, 1333, 1167, 800};
-
-static int byt_get_scaling(void)
+static int silvermont_get_scaling(void)
 {
 	u64 value;
 	int i;
+	/* Defined in Table 35-6 from SDM (Sept 2015) */
+	static int silvermont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000};
 
 	rdmsrl(MSR_FSB_FREQ, value);
-	i = value & 0x3;
+	i = value & 0x7;
+	WARN_ON(i > 4);
 
-	BUG_ON(i > BYT_BCLK_FREQS);
+	return silvermont_freq_table[i];
+}
 
-	return byt_freq_table[i] * 100;
+static int airmont_get_scaling(void)
+{
+	u64 value;
+	int i;
+	/* Defined in Table 35-10 from SDM (Sept 2015) */
+	static int airmont_freq_table[] = {
+		83300, 100000, 133300, 116700, 80000,
+		93300, 90000, 88900, 87500};
+
+	rdmsrl(MSR_FSB_FREQ, value);
+	i = value & 0xF;
+	WARN_ON(i > 8);
+
+	return airmont_freq_table[i];
 }
 
-static void byt_get_vid(struct cpudata *cpudata)
+static void atom_get_vid(struct cpudata *cpudata)
 {
 	u64 value;
 
-	rdmsrl(BYT_VIDS, value);
+	rdmsrl(ATOM_VIDS, value);
 	cpudata->vid.min = int_tofp((value >> 8) & 0x7f);
 	cpudata->vid.max = int_tofp((value >> 16) & 0x7f);
 	cpudata->vid.ratio = div_fp(
@@ -566,7 +620,7 @@ static void byt_get_vid(struct cpudata *cpudata)
 		int_tofp(cpudata->pstate.max_pstate -
 			cpudata->pstate.min_pstate));
 
-	rdmsrl(BYT_TURBO_VIDS, value);
+	rdmsrl(ATOM_TURBO_VIDS, value);
 	cpudata->vid.turbo = value & 0x7f;
 }
 
@@ -578,7 +632,7 @@ static int core_get_min_pstate(void)
 	return (value >> 40) & 0xFF;
 }
 
-static int core_get_max_pstate(void)
+static int core_get_max_pstate_physical(void)
 {
 	u64 value;
 
@@ -586,6 +640,46 @@ static int core_get_max_pstate(void)
 	return (value >> 8) & 0xFF;
 }
 
+static int core_get_max_pstate(void)
+{
+	u64 tar;
+	u64 plat_info;
+	int max_pstate;
+	int err;
+
+	rdmsrl(MSR_PLATFORM_INFO, plat_info);
+	max_pstate = (plat_info >> 8) & 0xFF;
+
+	err = rdmsrl_safe(MSR_TURBO_ACTIVATION_RATIO, &tar);
+	if (!err) {
+		/* Do some sanity checking for safety */
+		if (plat_info & 0x600000000) {
+			u64 tdp_ctrl;
+			u64 tdp_ratio;
+			int tdp_msr;
+
+			err = rdmsrl_safe(MSR_CONFIG_TDP_CONTROL, &tdp_ctrl);
+			if (err)
+				goto skip_tar;
+
+			tdp_msr = MSR_CONFIG_TDP_NOMINAL + tdp_ctrl;
+			err = rdmsrl_safe(tdp_msr, &tdp_ratio);
+			if (err)
+				goto skip_tar;
+
+			if (tdp_ratio - 1 == tar) {
+				max_pstate = tar;
+				pr_debug("max_pstate=TAC %x\n", max_pstate);
+			} else {
+				goto skip_tar;
+			}
+		}
+	}
+
+skip_tar:
+	return max_pstate;
+}
+
 static int core_get_turbo_pstate(void)
 {
 	u64 value;
@@ -608,8 +702,8 @@ static void core_set_pstate(struct cpudata *cpudata, int pstate)
 {
 	u64 val;
 
-	val = pstate << 8;
-	if (limits.no_turbo && !limits.turbo_disabled)
+	val = (u64)pstate << 8;
+	if (limits->no_turbo && !limits->turbo_disabled)
 		val |= (u64)1 << 32;
 
 	wrmsrl_on_cpu(cpudata->cpu, MSR_IA32_PERF_CTL, val);
@@ -639,6 +733,7 @@ static struct cpu_defaults core_params = {
 	},
 	.funcs = {
 		.get_max = core_get_max_pstate,
+		.get_max_physical = core_get_max_pstate_physical,
 		.get_min = core_get_min_pstate,
 		.get_turbo = core_get_turbo_pstate,
 		.get_scaling = core_get_scaling,
@@ -646,7 +741,27 @@ static struct cpu_defaults core_params = {
 	},
 };
 
-static struct cpu_defaults byt_params = {
+static struct cpu_defaults silvermont_params = {
+	.pid_policy = {
+		.sample_rate_ms = 10,
+		.deadband = 0,
+		.setpoint = 60,
+		.p_gain_pct = 14,
+		.d_gain_pct = 0,
+		.i_gain_pct = 4,
+	},
+	.funcs = {
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = silvermont_get_scaling,
+		.get_vid = atom_get_vid,
+	},
+};
+
+static struct cpu_defaults airmont_params = {
 	.pid_policy = {
 		.sample_rate_ms = 10,
 		.deadband = 0,
@@ -656,12 +771,13 @@ static struct cpu_defaults byt_params = {
 		.i_gain_pct = 4,
 	},
 	.funcs = {
-		.get_max = byt_get_max_pstate,
-		.get_min = byt_get_min_pstate,
-		.get_turbo = byt_get_turbo_pstate,
-		.set = byt_set_pstate,
-		.get_scaling = byt_get_scaling,
-		.get_vid = byt_get_vid,
+		.get_max = atom_get_max_pstate,
+		.get_max_physical = atom_get_max_pstate,
+		.get_min = atom_get_min_pstate,
+		.get_turbo = atom_get_turbo_pstate,
+		.set = atom_set_pstate,
+		.get_scaling = airmont_get_scaling,
+		.get_vid = atom_get_vid,
 	},
 };
 
@@ -676,6 +792,7 @@ static struct cpu_defaults knl_params = {
 	},
 	.funcs = {
 		.get_max = core_get_max_pstate,
+		.get_max_physical = core_get_max_pstate_physical,
 		.get_min = core_get_min_pstate,
 		.get_turbo = knl_get_turbo_pstate,
 		.get_scaling = core_get_scaling,
@@ -689,7 +806,7 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	int max_perf_adj;
 	int min_perf;
 
-	if (limits.no_turbo || limits.turbo_disabled)
+	if (limits->no_turbo || limits->turbo_disabled)
 		max_perf = cpu->pstate.max_pstate;
 
 	/*
@@ -697,27 +814,28 @@ static void intel_pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
 	 * policy, or by cpu specific default values determined through
 	 * experimentation.
 	 */
-	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
+	max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits->max_perf));
 	*max = clamp_t(int, max_perf_adj,
 			cpu->pstate.min_pstate, cpu->pstate.turbo_pstate);
 
-	min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf));
+	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)
+static void intel_pstate_set_pstate(struct cpudata *cpu, int pstate, bool force)
 {
 	int max_perf, min_perf;
 
-	update_turbo_state();
-
-	intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
+	if (force) {
+		update_turbo_state();
 
-	pstate = clamp_t(int, pstate, min_perf, max_perf);
+		intel_pstate_get_min_max(cpu, &min_perf, &max_perf);
 
-	if (pstate == cpu->pstate.current_pstate)
-		return;
+		pstate = clamp_t(int, pstate, min_perf, max_perf);
 
+		if (pstate == cpu->pstate.current_pstate)
+			return;
+	}
 	trace_cpu_frequency(pstate * cpu->pstate.scaling, cpu->cpu);
 
 	cpu->pstate.current_pstate = pstate;
@@ -729,12 +847,13 @@ static void intel_pstate_get_cpu_pstates(struct cpudata *cpu)
 {
 	cpu->pstate.min_pstate = pstate_funcs.get_min();
 	cpu->pstate.max_pstate = pstate_funcs.get_max();
+	cpu->pstate.max_pstate_physical = pstate_funcs.get_max_physical();
 	cpu->pstate.turbo_pstate = pstate_funcs.get_turbo();
 	cpu->pstate.scaling = pstate_funcs.get_scaling();
 
 	if (pstate_funcs.get_vid)
 		pstate_funcs.get_vid(cpu);
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
 }
 
 static inline void intel_pstate_calc_busy(struct cpudata *cpu)
@@ -747,7 +866,8 @@ static inline void intel_pstate_calc_busy(struct cpudata *cpu)
 
 	sample->freq = fp_toint(
 		mul_fp(int_tofp(
-			cpu->pstate.max_pstate * cpu->pstate.scaling / 100),
+			cpu->pstate.max_pstate_physical *
+			cpu->pstate.scaling / 100),
 			core_pct));
 
 	sample->core_pct_busy = (int32_t)core_pct;
@@ -757,23 +877,33 @@ static inline void intel_pstate_sample(struct cpudata *cpu)
 {
 	u64 aperf, mperf;
 	unsigned long flags;
+	u64 tsc;
 
 	local_irq_save(flags);
 	rdmsrl(MSR_IA32_APERF, aperf);
 	rdmsrl(MSR_IA32_MPERF, mperf);
+	if (cpu->prev_mperf == mperf) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	tsc = rdtsc();
 	local_irq_restore(flags);
 
 	cpu->last_sample_time = cpu->sample.time;
 	cpu->sample.time = ktime_get();
 	cpu->sample.aperf = aperf;
 	cpu->sample.mperf = mperf;
+	cpu->sample.tsc =  tsc;
 	cpu->sample.aperf -= cpu->prev_aperf;
 	cpu->sample.mperf -= cpu->prev_mperf;
+	cpu->sample.tsc -= cpu->prev_tsc;
 
 	intel_pstate_calc_busy(cpu);
 
 	cpu->prev_aperf = aperf;
 	cpu->prev_mperf = mperf;
+	cpu->prev_tsc = tsc;
 }
 
 static inline void intel_hwp_set_sample_time(struct cpudata *cpu)
@@ -795,7 +925,7 @@ static inline void intel_pstate_set_sample_time(struct cpudata *cpu)
 static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 {
 	int32_t core_busy, max_pstate, current_pstate, sample_ratio;
-	u32 duration_us;
+	s64 duration_us;
 	u32 sample_time;
 
 	/*
@@ -810,7 +940,7 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 	 * specified pstate.
 	 */
 	core_busy = cpu->sample.core_pct_busy;
-	max_pstate = int_tofp(cpu->pstate.max_pstate);
+	max_pstate = int_tofp(cpu->pstate.max_pstate_physical);
 	current_pstate = int_tofp(cpu->pstate.current_pstate);
 	core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
 
@@ -822,8 +952,8 @@ static inline int32_t intel_pstate_get_scaled_busy(struct cpudata *cpu)
 	 * to adjust our busyness.
 	 */
 	sample_time = pid_params.sample_rate_ms  * USEC_PER_MSEC;
-	duration_us = (u32) ktime_us_delta(cpu->sample.time,
-					   cpu->last_sample_time);
+	duration_us = ktime_us_delta(cpu->sample.time,
+				     cpu->last_sample_time);
 	if (duration_us > sample_time * 3) {
 		sample_ratio = div_fp(int_tofp(sample_time),
 				      int_tofp(duration_us));
@@ -838,6 +968,10 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 	int32_t busy_scaled;
 	struct _pid *pid;
 	signed int ctl;
+	int from;
+	struct sample *sample;
+
+	from = cpu->pstate.current_pstate;
 
 	pid = &cpu->pid;
 	busy_scaled = intel_pstate_get_scaled_busy(cpu);
@@ -845,7 +979,17 @@ static inline void intel_pstate_adjust_busy_pstate(struct cpudata *cpu)
 	ctl = pid_calc(pid, busy_scaled);
 
 	/* Negative values of ctl increase the pstate and vice versa */
-	intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl);
+	intel_pstate_set_pstate(cpu, cpu->pstate.current_pstate - ctl, true);
+
+	sample = &cpu->sample;
+	trace_pstate_sample(fp_toint(sample->core_pct_busy),
+		fp_toint(busy_scaled),
+		from,
+		cpu->pstate.current_pstate,
+		sample->mperf,
+		sample->aperf,
+		sample->tsc,
+		sample->freq);
 }
 
 static void intel_hwp_timer_func(unsigned long __data)
@@ -859,21 +1003,11 @@ static void intel_hwp_timer_func(unsigned long __data)
 static void intel_pstate_timer_func(unsigned long __data)
 {
 	struct cpudata *cpu = (struct cpudata *) __data;
-	struct sample *sample;
 
 	intel_pstate_sample(cpu);
 
-	sample = &cpu->sample;
-
 	intel_pstate_adjust_busy_pstate(cpu);
 
-	trace_pstate_sample(fp_toint(sample->core_pct_busy),
-			fp_toint(intel_pstate_get_scaled_busy(cpu)),
-			cpu->pstate.current_pstate,
-			sample->mperf,
-			sample->aperf,
-			sample->freq);
-
 	intel_pstate_set_sample_time(cpu);
 }
 
@@ -884,7 +1018,7 @@ static void intel_pstate_timer_func(unsigned long __data)
 static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x2a, core_params),
 	ICPU(0x2d, core_params),
-	ICPU(0x37, byt_params),
+	ICPU(0x37, silvermont_params),
 	ICPU(0x3a, core_params),
 	ICPU(0x3c, core_params),
 	ICPU(0x3d, core_params),
@@ -893,9 +1027,10 @@ static const struct x86_cpu_id intel_pstate_cpu_ids[] = {
 	ICPU(0x45, core_params),
 	ICPU(0x46, core_params),
 	ICPU(0x47, core_params),
-	ICPU(0x4c, byt_params),
+	ICPU(0x4c, airmont_params),
 	ICPU(0x4e, core_params),
 	ICPU(0x4f, core_params),
+	ICPU(0x5e, core_params),
 	ICPU(0x56, core_params),
 	ICPU(0x57, knl_params),
 	{}
@@ -920,6 +1055,10 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 	cpu = all_cpu_data[cpunum];
 
 	cpu->cpu = cpunum;
+
+	if (hwp_active)
+		intel_pstate_hwp_enable(cpu);
+
 	intel_pstate_get_cpu_pstates(cpu);
 
 	init_timer_deferrable(&cpu->timer);
@@ -936,7 +1075,7 @@ static int intel_pstate_init_cpu(unsigned int cpunum)
 
 	add_timer_on(&cpu->timer, cpunum);
 
-	pr_debug("Intel pstate controlling: cpu %d\n", cpunum);
+	pr_debug("intel_pstate: controlling: cpu %d\n", cpunum);
 
 	return 0;
 }
@@ -960,25 +1099,39 @@ static int intel_pstate_set_policy(struct cpufreq_policy *policy)
 
 	if (policy->policy == CPUFREQ_POLICY_PERFORMANCE &&
 	    policy->max >= policy->cpuinfo.max_freq) {
-		limits.min_policy_pct = 100;
-		limits.min_perf_pct = 100;
-		limits.min_perf = int_tofp(1);
-		limits.max_policy_pct = 100;
-		limits.max_perf_pct = 100;
-		limits.max_perf = int_tofp(1);
-		limits.no_turbo = 0;
+		pr_debug("intel_pstate: set performance\n");
+		limits = &performance_limits;
+		if (hwp_active)
+			intel_pstate_hwp_set();
 		return 0;
 	}
 
-	limits.min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
-	limits.min_policy_pct = clamp_t(int, limits.min_policy_pct, 0 , 100);
-	limits.min_perf_pct = max(limits.min_policy_pct, limits.min_sysfs_pct);
-	limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
-
-	limits.max_policy_pct = (policy->max * 100) / policy->cpuinfo.max_freq;
-	limits.max_policy_pct = clamp_t(int, limits.max_policy_pct, 0 , 100);
-	limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
-	limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
+	pr_debug("intel_pstate: set powersave\n");
+	limits = &powersave_limits;
+	limits->min_policy_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
+	limits->min_policy_pct = clamp_t(int, limits->min_policy_pct, 0 , 100);
+	limits->max_policy_pct = DIV_ROUND_UP(policy->max * 100,
+					      policy->cpuinfo.max_freq);
+	limits->max_policy_pct = clamp_t(int, limits->max_policy_pct, 0 , 100);
+
+	/* Normalize user input to [min_policy_pct, max_policy_pct] */
+	limits->min_perf_pct = max(limits->min_policy_pct,
+				   limits->min_sysfs_pct);
+	limits->min_perf_pct = min(limits->max_policy_pct,
+				   limits->min_perf_pct);
+	limits->max_perf_pct = min(limits->max_policy_pct,
+				   limits->max_sysfs_pct);
+	limits->max_perf_pct = max(limits->min_policy_pct,
+				   limits->max_perf_pct);
+	limits->max_perf = round_up(limits->max_perf, FRAC_BITS);
+
+	/* Make sure min_perf_pct <= max_perf_pct */
+	limits->min_perf_pct = min(limits->max_perf_pct, limits->min_perf_pct);
+
+	limits->min_perf = div_fp(int_tofp(limits->min_perf_pct),
+				  int_tofp(100));
+	limits->max_perf = div_fp(int_tofp(limits->max_perf_pct),
+				  int_tofp(100));
 
 	if (hwp_active)
 		intel_pstate_hwp_set();
@@ -1002,13 +1155,13 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy)
 	int cpu_num = policy->cpu;
 	struct cpudata *cpu = all_cpu_data[cpu_num];
 
-	pr_info("intel_pstate CPU %d exiting\n", cpu_num);
+	pr_debug("intel_pstate: CPU %d exiting\n", cpu_num);
 
 	del_timer_sync(&all_cpu_data[cpu_num]->timer);
 	if (hwp_active)
 		return;
 
-	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate);
+	intel_pstate_set_pstate(cpu, cpu->pstate.min_pstate, false);
 }
 
 static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
@@ -1022,7 +1175,7 @@ static int intel_pstate_cpu_init(struct cpufreq_policy *policy)
 
 	cpu = all_cpu_data[policy->cpu];
 
-	if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
+	if (limits->min_perf_pct == 100 && limits->max_perf_pct == 100)
 		policy->policy = CPUFREQ_POLICY_PERFORMANCE;
 	else
 		policy->policy = CPUFREQ_POLICY_POWERSAVE;
@@ -1078,6 +1231,7 @@ static void copy_pid_params(struct pstate_adjust_policy *policy)
 static void copy_cpu_funcs(struct pstate_funcs *funcs)
 {
 	pstate_funcs.get_max   = funcs->get_max;
+	pstate_funcs.get_max_physical = funcs->get_max_physical;
 	pstate_funcs.get_min   = funcs->get_min;
 	pstate_funcs.get_turbo = funcs->get_turbo;
 	pstate_funcs.get_scaling = funcs->get_scaling;
@@ -1157,6 +1311,10 @@ static struct hw_vendor_info vendor_info[] = {
 	{1, "ORACLE", "X4270M3 ", PPC},
 	{1, "ORACLE", "X4270M2 ", PPC},
 	{1, "ORACLE", "X4170M2 ", PPC},
+	{1, "ORACLE", "X4170 M3", PPC},
+	{1, "ORACLE", "X4275 M3", PPC},
+	{1, "ORACLE", "X6-2    ", PPC},
+	{1, "ORACLE", "Sudbury ", PPC},
 	{0, "", ""},
 };
 
@@ -1232,8 +1390,10 @@ static int __init intel_pstate_init(void)
 	if (!all_cpu_data)
 		return -ENOMEM;
 
-	if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp)
-		intel_pstate_hwp_enable();
+	if (static_cpu_has_safe(X86_FEATURE_HWP) && !no_hwp) {
+		pr_info("intel_pstate: HWP enabled\n");
+		hwp_active++;
+	}
 
 	if (!hwp_active && hwp_only)
 		goto out;
@@ -1268,8 +1428,10 @@ static int __init intel_pstate_setup(char *str)
 
 	if (!strcmp(str, "disable"))
 		no_load = 1;
-	if (!strcmp(str, "no_hwp"))
+	if (!strcmp(str, "no_hwp")) {
+		pr_info("intel_pstate: HWP disabled\n");
 		no_hwp = 1;
+	}
 	if (!strcmp(str, "force"))
 		force_load = 1;
 	if (!strcmp(str, "hwp_only"))
diff --git a/kernel/drivers/cpufreq/loongson2_cpufreq.c b/kernel/drivers/cpufreq/loongson2_cpufreq.c
index fc897baba..cd593c1f6 100644
--- a/kernel/drivers/cpufreq/loongson2_cpufreq.c
+++ b/kernel/drivers/cpufreq/loongson2_cpufreq.c
@@ -3,7 +3,7 @@
  *
  * The 2E revision of loongson processor not support this feature.
  *
- * Copyright (C) 2006 - 2008 Lemote Inc. & Insititute of Computing Technology
+ * Copyright (C) 2006 - 2008 Lemote Inc. & Institute of Computing Technology
  * Author: Yanhua, yanh@lemote.com
  *
  * This file is subject to the terms and conditions of the GNU General Public
@@ -20,7 +20,7 @@
 #include <asm/clock.h>
 #include <asm/idle.h>
 
-#include <asm/mach-loongson/loongson.h>
+#include <asm/mach-loongson64/loongson.h>
 
 static uint nowait;
 
diff --git a/kernel/drivers/cpufreq/ls1x-cpufreq.c b/kernel/drivers/cpufreq/ls1x-cpufreq.c
index f0913eee2..262581b33 100644
--- a/kernel/drivers/cpufreq/ls1x-cpufreq.c
+++ b/kernel/drivers/cpufreq/ls1x-cpufreq.c
@@ -17,8 +17,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 
-#include <asm/mach-loongson1/cpufreq.h>
-#include <asm/mach-loongson1/loongson1.h>
+#include <cpufreq.h>
+#include <loongson1.h>
 
 static struct {
 	struct device *dev;
diff --git a/kernel/drivers/cpufreq/mt8173-cpufreq.c b/kernel/drivers/cpufreq/mt8173-cpufreq.c
new file mode 100644
index 000000000..83001dc5b
--- /dev/null
+++ b/kernel/drivers/cpufreq/mt8173-cpufreq.c
@@ -0,0 +1,527 @@
+/*
+ * Copyright (c) 2015 Linaro Ltd.
+ * Author: Pi-Cheng Chen <pi-cheng.chen@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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/cpu_cooling.h>
+#include <linux/cpufreq.h>
+#include <linux/cpumask.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+#include <linux/thermal.h>
+
+#define MIN_VOLT_SHIFT		(100000)
+#define MAX_VOLT_SHIFT		(200000)
+#define MAX_VOLT_LIMIT		(1150000)
+#define VOLT_TOL		(10000)
+
+/*
+ * The struct mtk_cpu_dvfs_info holds necessary information for doing CPU DVFS
+ * on each CPU power/clock domain of Mediatek SoCs. Each CPU cluster in
+ * Mediatek SoCs has two voltage inputs, Vproc and Vsram. In some cases the two
+ * voltage inputs need to be controlled under a hardware limitation:
+ * 100mV < Vsram - Vproc < 200mV
+ *
+ * When scaling the clock frequency of a CPU clock domain, the clock source
+ * needs to be switched to another stable PLL clock temporarily until
+ * the original PLL becomes stable at target frequency.
+ */
+struct mtk_cpu_dvfs_info {
+	struct device *cpu_dev;
+	struct regulator *proc_reg;
+	struct regulator *sram_reg;
+	struct clk *cpu_clk;
+	struct clk *inter_clk;
+	struct thermal_cooling_device *cdev;
+	int intermediate_voltage;
+	bool need_voltage_tracking;
+};
+
+static int mtk_cpufreq_voltage_tracking(struct mtk_cpu_dvfs_info *info,
+					int new_vproc)
+{
+	struct regulator *proc_reg = info->proc_reg;
+	struct regulator *sram_reg = info->sram_reg;
+	int old_vproc, old_vsram, new_vsram, vsram, vproc, ret;
+
+	old_vproc = regulator_get_voltage(proc_reg);
+	old_vsram = regulator_get_voltage(sram_reg);
+	/* Vsram should not exceed the maximum allowed voltage of SoC. */
+	new_vsram = min(new_vproc + MIN_VOLT_SHIFT, MAX_VOLT_LIMIT);
+
+	if (old_vproc < new_vproc) {
+		/*
+		 * When scaling up voltages, Vsram and Vproc scale up step
+		 * by step. At each step, set Vsram to (Vproc + 200mV) first,
+		 * then set Vproc to (Vsram - 100mV).
+		 * Keep doing it until Vsram and Vproc hit target voltages.
+		 */
+		do {
+			old_vsram = regulator_get_voltage(sram_reg);
+			old_vproc = regulator_get_voltage(proc_reg);
+
+			vsram = min(new_vsram, old_vproc + MAX_VOLT_SHIFT);
+
+			if (vsram + VOLT_TOL >= MAX_VOLT_LIMIT) {
+				vsram = MAX_VOLT_LIMIT;
+
+				/*
+				 * If the target Vsram hits the maximum voltage,
+				 * try to set the exact voltage value first.
+				 */
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram);
+				if (ret)
+					ret = regulator_set_voltage(sram_reg,
+							vsram - VOLT_TOL,
+							vsram);
+
+				vproc = new_vproc;
+			} else {
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram + VOLT_TOL);
+
+				vproc = vsram - MIN_VOLT_SHIFT;
+			}
+			if (ret)
+				return ret;
+
+			ret = regulator_set_voltage(proc_reg, vproc,
+						    vproc + VOLT_TOL);
+			if (ret) {
+				regulator_set_voltage(sram_reg, old_vsram,
+						      old_vsram);
+				return ret;
+			}
+		} while (vproc < new_vproc || vsram < new_vsram);
+	} else if (old_vproc > new_vproc) {
+		/*
+		 * When scaling down voltages, Vsram and Vproc scale down step
+		 * by step. At each step, set Vproc to (Vsram - 200mV) first,
+		 * then set Vproc to (Vproc + 100mV).
+		 * Keep doing it until Vsram and Vproc hit target voltages.
+		 */
+		do {
+			old_vproc = regulator_get_voltage(proc_reg);
+			old_vsram = regulator_get_voltage(sram_reg);
+
+			vproc = max(new_vproc, old_vsram - MAX_VOLT_SHIFT);
+			ret = regulator_set_voltage(proc_reg, vproc,
+						    vproc + VOLT_TOL);
+			if (ret)
+				return ret;
+
+			if (vproc == new_vproc)
+				vsram = new_vsram;
+			else
+				vsram = max(new_vsram, vproc + MIN_VOLT_SHIFT);
+
+			if (vsram + VOLT_TOL >= MAX_VOLT_LIMIT) {
+				vsram = MAX_VOLT_LIMIT;
+
+				/*
+				 * If the target Vsram hits the maximum voltage,
+				 * try to set the exact voltage value first.
+				 */
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram);
+				if (ret)
+					ret = regulator_set_voltage(sram_reg,
+							vsram - VOLT_TOL,
+							vsram);
+			} else {
+				ret = regulator_set_voltage(sram_reg, vsram,
+							    vsram + VOLT_TOL);
+			}
+
+			if (ret) {
+				regulator_set_voltage(proc_reg, old_vproc,
+						      old_vproc);
+				return ret;
+			}
+		} while (vproc > new_vproc + VOLT_TOL ||
+			 vsram > new_vsram + VOLT_TOL);
+	}
+
+	return 0;
+}
+
+static int mtk_cpufreq_set_voltage(struct mtk_cpu_dvfs_info *info, int vproc)
+{
+	if (info->need_voltage_tracking)
+		return mtk_cpufreq_voltage_tracking(info, vproc);
+	else
+		return regulator_set_voltage(info->proc_reg, vproc,
+					     vproc + VOLT_TOL);
+}
+
+static int mtk_cpufreq_set_target(struct cpufreq_policy *policy,
+				  unsigned int index)
+{
+	struct cpufreq_frequency_table *freq_table = policy->freq_table;
+	struct clk *cpu_clk = policy->clk;
+	struct clk *armpll = clk_get_parent(cpu_clk);
+	struct mtk_cpu_dvfs_info *info = policy->driver_data;
+	struct device *cpu_dev = info->cpu_dev;
+	struct dev_pm_opp *opp;
+	long freq_hz, old_freq_hz;
+	int vproc, old_vproc, inter_vproc, target_vproc, ret;
+
+	inter_vproc = info->intermediate_voltage;
+
+	old_freq_hz = clk_get_rate(cpu_clk);
+	old_vproc = regulator_get_voltage(info->proc_reg);
+
+	freq_hz = freq_table[index].frequency * 1000;
+
+	rcu_read_lock();
+	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &freq_hz);
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
+		pr_err("cpu%d: failed to find OPP for %ld\n",
+		       policy->cpu, freq_hz);
+		return PTR_ERR(opp);
+	}
+	vproc = dev_pm_opp_get_voltage(opp);
+	rcu_read_unlock();
+
+	/*
+	 * If the new voltage or the intermediate voltage is higher than the
+	 * current voltage, scale up voltage first.
+	 */
+	target_vproc = (inter_vproc > vproc) ? inter_vproc : vproc;
+	if (old_vproc < target_vproc) {
+		ret = mtk_cpufreq_set_voltage(info, target_vproc);
+		if (ret) {
+			pr_err("cpu%d: failed to scale up voltage!\n",
+			       policy->cpu);
+			mtk_cpufreq_set_voltage(info, old_vproc);
+			return ret;
+		}
+	}
+
+	/* Reparent the CPU clock to intermediate clock. */
+	ret = clk_set_parent(cpu_clk, info->inter_clk);
+	if (ret) {
+		pr_err("cpu%d: failed to re-parent cpu clock!\n",
+		       policy->cpu);
+		mtk_cpufreq_set_voltage(info, old_vproc);
+		WARN_ON(1);
+		return ret;
+	}
+
+	/* Set the original PLL to target rate. */
+	ret = clk_set_rate(armpll, freq_hz);
+	if (ret) {
+		pr_err("cpu%d: failed to scale cpu clock rate!\n",
+		       policy->cpu);
+		clk_set_parent(cpu_clk, armpll);
+		mtk_cpufreq_set_voltage(info, old_vproc);
+		return ret;
+	}
+
+	/* Set parent of CPU clock back to the original PLL. */
+	ret = clk_set_parent(cpu_clk, armpll);
+	if (ret) {
+		pr_err("cpu%d: failed to re-parent cpu clock!\n",
+		       policy->cpu);
+		mtk_cpufreq_set_voltage(info, inter_vproc);
+		WARN_ON(1);
+		return ret;
+	}
+
+	/*
+	 * If the new voltage is lower than the intermediate voltage or the
+	 * original voltage, scale down to the new voltage.
+	 */
+	if (vproc < inter_vproc || vproc < old_vproc) {
+		ret = mtk_cpufreq_set_voltage(info, vproc);
+		if (ret) {
+			pr_err("cpu%d: failed to scale down voltage!\n",
+			       policy->cpu);
+			clk_set_parent(cpu_clk, info->inter_clk);
+			clk_set_rate(armpll, old_freq_hz);
+			clk_set_parent(cpu_clk, armpll);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void mtk_cpufreq_ready(struct cpufreq_policy *policy)
+{
+	struct mtk_cpu_dvfs_info *info = policy->driver_data;
+	struct device_node *np = of_node_get(info->cpu_dev->of_node);
+
+	if (WARN_ON(!np))
+		return;
+
+	if (of_find_property(np, "#cooling-cells", NULL)) {
+		info->cdev = of_cpufreq_cooling_register(np,
+							 policy->related_cpus);
+
+		if (IS_ERR(info->cdev)) {
+			dev_err(info->cpu_dev,
+				"running cpufreq without cooling device: %ld\n",
+				PTR_ERR(info->cdev));
+
+			info->cdev = NULL;
+		}
+	}
+
+	of_node_put(np);
+}
+
+static int mtk_cpu_dvfs_info_init(struct mtk_cpu_dvfs_info *info, int cpu)
+{
+	struct device *cpu_dev;
+	struct regulator *proc_reg = ERR_PTR(-ENODEV);
+	struct regulator *sram_reg = ERR_PTR(-ENODEV);
+	struct clk *cpu_clk = ERR_PTR(-ENODEV);
+	struct clk *inter_clk = ERR_PTR(-ENODEV);
+	struct dev_pm_opp *opp;
+	unsigned long rate;
+	int ret;
+
+	cpu_dev = get_cpu_device(cpu);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu%d device\n", cpu);
+		return -ENODEV;
+	}
+
+	cpu_clk = clk_get(cpu_dev, "cpu");
+	if (IS_ERR(cpu_clk)) {
+		if (PTR_ERR(cpu_clk) == -EPROBE_DEFER)
+			pr_warn("cpu clk for cpu%d not ready, retry.\n", cpu);
+		else
+			pr_err("failed to get cpu clk for cpu%d\n", cpu);
+
+		ret = PTR_ERR(cpu_clk);
+		return ret;
+	}
+
+	inter_clk = clk_get(cpu_dev, "intermediate");
+	if (IS_ERR(inter_clk)) {
+		if (PTR_ERR(inter_clk) == -EPROBE_DEFER)
+			pr_warn("intermediate clk for cpu%d not ready, retry.\n",
+				cpu);
+		else
+			pr_err("failed to get intermediate clk for cpu%d\n",
+			       cpu);
+
+		ret = PTR_ERR(inter_clk);
+		goto out_free_resources;
+	}
+
+	proc_reg = regulator_get_exclusive(cpu_dev, "proc");
+	if (IS_ERR(proc_reg)) {
+		if (PTR_ERR(proc_reg) == -EPROBE_DEFER)
+			pr_warn("proc regulator for cpu%d not ready, retry.\n",
+				cpu);
+		else
+			pr_err("failed to get proc regulator for cpu%d\n",
+			       cpu);
+
+		ret = PTR_ERR(proc_reg);
+		goto out_free_resources;
+	}
+
+	/* Both presence and absence of sram regulator are valid cases. */
+	sram_reg = regulator_get_exclusive(cpu_dev, "sram");
+
+	ret = dev_pm_opp_of_add_table(cpu_dev);
+	if (ret) {
+		pr_warn("no OPP table for cpu%d\n", cpu);
+		goto out_free_resources;
+	}
+
+	/* Search a safe voltage for intermediate frequency. */
+	rate = clk_get_rate(inter_clk);
+	rcu_read_lock();
+	opp = dev_pm_opp_find_freq_ceil(cpu_dev, &rate);
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
+		pr_err("failed to get intermediate opp for cpu%d\n", cpu);
+		ret = PTR_ERR(opp);
+		goto out_free_opp_table;
+	}
+	info->intermediate_voltage = dev_pm_opp_get_voltage(opp);
+	rcu_read_unlock();
+
+	info->cpu_dev = cpu_dev;
+	info->proc_reg = proc_reg;
+	info->sram_reg = IS_ERR(sram_reg) ? NULL : sram_reg;
+	info->cpu_clk = cpu_clk;
+	info->inter_clk = inter_clk;
+
+	/*
+	 * If SRAM regulator is present, software "voltage tracking" is needed
+	 * for this CPU power domain.
+	 */
+	info->need_voltage_tracking = !IS_ERR(sram_reg);
+
+	return 0;
+
+out_free_opp_table:
+	dev_pm_opp_of_remove_table(cpu_dev);
+
+out_free_resources:
+	if (!IS_ERR(proc_reg))
+		regulator_put(proc_reg);
+	if (!IS_ERR(sram_reg))
+		regulator_put(sram_reg);
+	if (!IS_ERR(cpu_clk))
+		clk_put(cpu_clk);
+	if (!IS_ERR(inter_clk))
+		clk_put(inter_clk);
+
+	return ret;
+}
+
+static void mtk_cpu_dvfs_info_release(struct mtk_cpu_dvfs_info *info)
+{
+	if (!IS_ERR(info->proc_reg))
+		regulator_put(info->proc_reg);
+	if (!IS_ERR(info->sram_reg))
+		regulator_put(info->sram_reg);
+	if (!IS_ERR(info->cpu_clk))
+		clk_put(info->cpu_clk);
+	if (!IS_ERR(info->inter_clk))
+		clk_put(info->inter_clk);
+
+	dev_pm_opp_of_remove_table(info->cpu_dev);
+}
+
+static int mtk_cpufreq_init(struct cpufreq_policy *policy)
+{
+	struct mtk_cpu_dvfs_info *info;
+	struct cpufreq_frequency_table *freq_table;
+	int ret;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	ret = mtk_cpu_dvfs_info_init(info, policy->cpu);
+	if (ret) {
+		pr_err("%s failed to initialize dvfs info for cpu%d\n",
+		       __func__, policy->cpu);
+		goto out_free_dvfs_info;
+	}
+
+	ret = dev_pm_opp_init_cpufreq_table(info->cpu_dev, &freq_table);
+	if (ret) {
+		pr_err("failed to init cpufreq table for cpu%d: %d\n",
+		       policy->cpu, ret);
+		goto out_release_dvfs_info;
+	}
+
+	ret = cpufreq_table_validate_and_show(policy, freq_table);
+	if (ret) {
+		pr_err("%s: invalid frequency table: %d\n", __func__, ret);
+		goto out_free_cpufreq_table;
+	}
+
+	/* CPUs in the same cluster share a clock and power domain. */
+	cpumask_copy(policy->cpus, &cpu_topology[policy->cpu].core_sibling);
+	policy->driver_data = info;
+	policy->clk = info->cpu_clk;
+
+	return 0;
+
+out_free_cpufreq_table:
+	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &freq_table);
+
+out_release_dvfs_info:
+	mtk_cpu_dvfs_info_release(info);
+
+out_free_dvfs_info:
+	kfree(info);
+
+	return ret;
+}
+
+static int mtk_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	struct mtk_cpu_dvfs_info *info = policy->driver_data;
+
+	cpufreq_cooling_unregister(info->cdev);
+	dev_pm_opp_free_cpufreq_table(info->cpu_dev, &policy->freq_table);
+	mtk_cpu_dvfs_info_release(info);
+	kfree(info);
+
+	return 0;
+}
+
+static struct cpufreq_driver mt8173_cpufreq_driver = {
+	.flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK,
+	.verify = cpufreq_generic_frequency_table_verify,
+	.target_index = mtk_cpufreq_set_target,
+	.get = cpufreq_generic_get,
+	.init = mtk_cpufreq_init,
+	.exit = mtk_cpufreq_exit,
+	.ready = mtk_cpufreq_ready,
+	.name = "mtk-cpufreq",
+	.attr = cpufreq_generic_attr,
+};
+
+static int mt8173_cpufreq_probe(struct platform_device *pdev)
+{
+	int ret;
+
+	ret = cpufreq_register_driver(&mt8173_cpufreq_driver);
+	if (ret)
+		pr_err("failed to register mtk cpufreq driver\n");
+
+	return ret;
+}
+
+static struct platform_driver mt8173_cpufreq_platdrv = {
+	.driver = {
+		.name	= "mt8173-cpufreq",
+	},
+	.probe		= mt8173_cpufreq_probe,
+};
+
+static int mt8173_cpufreq_driver_init(void)
+{
+	struct platform_device *pdev;
+	int err;
+
+	if (!of_machine_is_compatible("mediatek,mt8173"))
+		return -ENODEV;
+
+	err = platform_driver_register(&mt8173_cpufreq_platdrv);
+	if (err)
+		return err;
+
+	/*
+	 * Since there's no place to hold device registration code and no
+	 * device tree based way to match cpufreq driver yet, both the driver
+	 * and the device registration codes are put here to handle defer
+	 * probing.
+	 */
+	pdev = platform_device_register_simple("mt8173-cpufreq", -1, NULL, 0);
+	if (IS_ERR(pdev)) {
+		pr_err("failed to register mtk-cpufreq platform device\n");
+		return PTR_ERR(pdev);
+	}
+
+	return 0;
+}
+device_initcall(mt8173_cpufreq_driver_init);
diff --git a/kernel/drivers/cpufreq/p4-clockmod.c b/kernel/drivers/cpufreq/p4-clockmod.c
index 529cfd921..5dd95dab5 100644
--- a/kernel/drivers/cpufreq/p4-clockmod.c
+++ b/kernel/drivers/cpufreq/p4-clockmod.c
@@ -172,7 +172,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/kernel/drivers/cpufreq/powernow-k7.c b/kernel/drivers/cpufreq/powernow-k7.c
index 37c574248..c1ae19997 100644
--- a/kernel/drivers/cpufreq/powernow-k7.c
+++ b/kernel/drivers/cpufreq/powernow-k7.c
@@ -421,7 +421,7 @@ static int powernow_acpi_init(void)
 	return 0;
 
 err2:
-	acpi_processor_unregister_performance(acpi_processor_perf, 0);
+	acpi_processor_unregister_performance(0);
 err1:
 	free_cpumask_var(acpi_processor_perf->shared_cpu_map);
 err05:
@@ -661,7 +661,7 @@ static int powernow_cpu_exit(struct cpufreq_policy *policy)
 {
 #ifdef CONFIG_X86_POWERNOW_K7_ACPI
 	if (acpi_processor_perf) {
-		acpi_processor_unregister_performance(acpi_processor_perf, 0);
+		acpi_processor_unregister_performance(0);
 		free_cpumask_var(acpi_processor_perf->shared_cpu_map);
 		kfree(acpi_processor_perf);
 	}
diff --git a/kernel/drivers/cpufreq/powernow-k8.c b/kernel/drivers/cpufreq/powernow-k8.c
index f9ce7e4bf..0b5bf135b 100644
--- a/kernel/drivers/cpufreq/powernow-k8.c
+++ b/kernel/drivers/cpufreq/powernow-k8.c
@@ -57,13 +57,6 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 
 static struct cpufreq_driver cpufreq_amd64_driver;
 
-#ifndef CONFIG_SMP
-static inline const struct cpumask *cpu_core_mask(int cpu)
-{
-	return cpumask_of(0);
-}
-#endif
-
 /* Return a frequency in MHz, given an input fid */
 static u32 find_freq_from_fid(u32 fid)
 {
@@ -620,7 +613,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 
 	pr_debug("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -784,7 +777,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 		CPUFREQ_TABLE_END;
 	data->powernow_table = powernow_table;
 
-	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
+	if (cpumask_first(topology_core_cpumask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	/* notify BIOS that we exist */
@@ -802,7 +795,7 @@ err_out_mem:
 	kfree(powernow_table);
 
 err_out:
-	acpi_processor_unregister_performance(&data->acpi_data, data->cpu);
+	acpi_processor_unregister_performance(data->cpu);
 
 	/* data->acpi_data.state_count informs us at ->exit()
 	 * whether ACPI was used */
@@ -870,8 +863,7 @@ static int fill_powernow_table_fidvid(struct powernow_k8_data *data,
 static void powernow_k8_cpu_exit_acpi(struct powernow_k8_data *data)
 {
 	if (data->acpi_data.state_count)
-		acpi_processor_unregister_performance(&data->acpi_data,
-				data->cpu);
+		acpi_processor_unregister_performance(data->cpu);
 	free_cpumask_var(data->acpi_data.shared_cpu_map);
 }
 
@@ -1090,7 +1082,7 @@ static int powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (rc != 0)
 		goto err_out_exit_acpi;
 
-	cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
+	cpumask_copy(pol->cpus, topology_core_cpumask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	/* min/max the cpu is capable of */
diff --git a/kernel/drivers/cpufreq/powernv-cpufreq.c b/kernel/drivers/cpufreq/powernv-cpufreq.c
index ebef0d827..cb501386e 100644
--- a/kernel/drivers/cpufreq/powernv-cpufreq.c
+++ b/kernel/drivers/cpufreq/powernv-cpufreq.c
@@ -27,20 +27,31 @@
 #include <linux/smp.h>
 #include <linux/of.h>
 #include <linux/reboot.h>
+#include <linux/slab.h>
 
 #include <asm/cputhreads.h>
 #include <asm/firmware.h>
 #include <asm/reg.h>
 #include <asm/smp.h> /* Required for cpu_sibling_mask() in UP configs */
+#include <asm/opal.h>
 
 #define POWERNV_MAX_PSTATES	256
 #define PMSR_PSAFE_ENABLE	(1UL << 30)
 #define PMSR_SPR_EM_DISABLE	(1UL << 31)
 #define PMSR_MAX(x)		((x >> 32) & 0xFF)
-#define PMSR_LP(x)		((x >> 48) & 0xFF)
 
 static struct cpufreq_frequency_table powernv_freqs[POWERNV_MAX_PSTATES+1];
-static bool rebooting, throttled;
+static bool rebooting, throttled, occ_reset;
+
+static struct chip {
+	unsigned int id;
+	bool throttled;
+	cpumask_t mask;
+	struct work_struct throttle;
+	bool restore;
+} *chips;
+
+static int nr_chips;
 
 /*
  * Note: The set of pstates consists of contiguous integers, the
@@ -298,28 +309,41 @@ static inline unsigned int get_nominal_index(void)
 	return powernv_pstate_info.max - powernv_pstate_info.nominal;
 }
 
-static void powernv_cpufreq_throttle_check(unsigned int cpu)
+static void powernv_cpufreq_throttle_check(void *data)
 {
+	unsigned int cpu = smp_processor_id();
 	unsigned long pmsr;
-	int pmsr_pmax, pmsr_lp;
+	int pmsr_pmax, i;
 
 	pmsr = get_pmspr(SPRN_PMSR);
 
+	for (i = 0; i < nr_chips; i++)
+		if (chips[i].id == cpu_to_chip_id(cpu))
+			break;
+
 	/* Check for Pmax Capping */
 	pmsr_pmax = (s8)PMSR_MAX(pmsr);
 	if (pmsr_pmax != powernv_pstate_info.max) {
-		throttled = true;
-		pr_info("CPU %d Pmax is reduced to %d\n", cpu, pmsr_pmax);
-		pr_info("Max allowed Pstate is capped\n");
+		if (chips[i].throttled)
+			goto next;
+		chips[i].throttled = true;
+		if (pmsr_pmax < powernv_pstate_info.nominal)
+			pr_crit("CPU %d on Chip %u has Pmax reduced below nominal frequency (%d < %d)\n",
+				cpu, chips[i].id, pmsr_pmax,
+				powernv_pstate_info.nominal);
+		else
+			pr_info("CPU %d on Chip %u has Pmax reduced below turbo frequency (%d < %d)\n",
+				cpu, chips[i].id, pmsr_pmax,
+				powernv_pstate_info.max);
+	} else if (chips[i].throttled) {
+		chips[i].throttled = false;
+		pr_info("CPU %d on Chip %u has Pmax restored to %d\n", cpu,
+			chips[i].id, pmsr_pmax);
 	}
 
-	/*
-	 * Check for Psafe by reading LocalPstate
-	 * or check if Psafe_mode_active is set in PMSR.
-	 */
-	pmsr_lp = (s8)PMSR_LP(pmsr);
-	if ((pmsr_lp < powernv_pstate_info.min) ||
-				(pmsr & PMSR_PSAFE_ENABLE)) {
+	/* Check if Psafe_mode_active is set in PMSR. */
+next:
+	if (pmsr & PMSR_PSAFE_ENABLE) {
 		throttled = true;
 		pr_info("Pstate set to safe frequency\n");
 	}
@@ -350,7 +374,7 @@ static int powernv_cpufreq_target_index(struct cpufreq_policy *policy,
 		return 0;
 
 	if (!throttled)
-		powernv_cpufreq_throttle_check(smp_processor_id());
+		powernv_cpufreq_throttle_check(NULL);
 
 	freq_data.pstate_id = powernv_freqs[new_index].driver_data;
 
@@ -395,6 +419,119 @@ static struct notifier_block powernv_cpufreq_reboot_nb = {
 	.notifier_call = powernv_cpufreq_reboot_notifier,
 };
 
+void powernv_cpufreq_work_fn(struct work_struct *work)
+{
+	struct chip *chip = container_of(work, struct chip, throttle);
+	unsigned int cpu;
+	cpumask_var_t mask;
+
+	smp_call_function_any(&chip->mask,
+			      powernv_cpufreq_throttle_check, NULL, 0);
+
+	if (!chip->restore)
+		return;
+
+	chip->restore = false;
+	cpumask_copy(mask, &chip->mask);
+	for_each_cpu_and(cpu, mask, cpu_online_mask) {
+		int index, tcpu;
+		struct cpufreq_policy policy;
+
+		cpufreq_get_policy(&policy, cpu);
+		cpufreq_frequency_table_target(&policy, policy.freq_table,
+					       policy.cur,
+					       CPUFREQ_RELATION_C, &index);
+		powernv_cpufreq_target_index(&policy, index);
+		for_each_cpu(tcpu, policy.cpus)
+			cpumask_clear_cpu(tcpu, mask);
+	}
+}
+
+static char throttle_reason[][30] = {
+					"No throttling",
+					"Power Cap",
+					"Processor Over Temperature",
+					"Power Supply Failure",
+					"Over Current",
+					"OCC Reset"
+				     };
+
+static int powernv_cpufreq_occ_msg(struct notifier_block *nb,
+				   unsigned long msg_type, void *_msg)
+{
+	struct opal_msg *msg = _msg;
+	struct opal_occ_msg omsg;
+	int i;
+
+	if (msg_type != OPAL_MSG_OCC)
+		return 0;
+
+	omsg.type = be64_to_cpu(msg->params[0]);
+
+	switch (omsg.type) {
+	case OCC_RESET:
+		occ_reset = true;
+		pr_info("OCC (On Chip Controller - enforces hard thermal/power limits) Resetting\n");
+		/*
+		 * powernv_cpufreq_throttle_check() is called in
+		 * target() callback which can detect the throttle state
+		 * for governors like ondemand.
+		 * But static governors will not call target() often thus
+		 * report throttling here.
+		 */
+		if (!throttled) {
+			throttled = true;
+			pr_crit("CPU frequency is throttled for duration\n");
+		}
+
+		break;
+	case OCC_LOAD:
+		pr_info("OCC Loading, CPU frequency is throttled until OCC is started\n");
+		break;
+	case OCC_THROTTLE:
+		omsg.chip = be64_to_cpu(msg->params[1]);
+		omsg.throttle_status = be64_to_cpu(msg->params[2]);
+
+		if (occ_reset) {
+			occ_reset = false;
+			throttled = false;
+			pr_info("OCC Active, CPU frequency is no longer throttled\n");
+
+			for (i = 0; i < nr_chips; i++) {
+				chips[i].restore = true;
+				schedule_work(&chips[i].throttle);
+			}
+
+			return 0;
+		}
+
+		if (omsg.throttle_status &&
+		    omsg.throttle_status <= OCC_MAX_THROTTLE_STATUS)
+			pr_info("OCC: Chip %u Pmax reduced due to %s\n",
+				(unsigned int)omsg.chip,
+				throttle_reason[omsg.throttle_status]);
+		else if (!omsg.throttle_status)
+			pr_info("OCC: Chip %u %s\n", (unsigned int)omsg.chip,
+				throttle_reason[omsg.throttle_status]);
+		else
+			return 0;
+
+		for (i = 0; i < nr_chips; i++)
+			if (chips[i].id == omsg.chip) {
+				if (!omsg.throttle_status)
+					chips[i].restore = true;
+				schedule_work(&chips[i].throttle);
+			}
+	}
+	return 0;
+}
+
+static struct notifier_block powernv_cpufreq_opal_nb = {
+	.notifier_call	= powernv_cpufreq_occ_msg,
+	.next		= NULL,
+	.priority	= 0,
+};
+
 static void powernv_cpufreq_stop_cpu(struct cpufreq_policy *policy)
 {
 	struct powernv_smp_call_data freq_data;
@@ -414,6 +551,36 @@ static struct cpufreq_driver powernv_cpufreq_driver = {
 	.attr		= powernv_cpu_freq_attr,
 };
 
+static int init_chip_info(void)
+{
+	unsigned int chip[256];
+	unsigned int cpu, i;
+	unsigned int prev_chip_id = UINT_MAX;
+
+	for_each_possible_cpu(cpu) {
+		unsigned int id = cpu_to_chip_id(cpu);
+
+		if (prev_chip_id != id) {
+			prev_chip_id = id;
+			chip[nr_chips++] = id;
+		}
+	}
+
+	chips = kmalloc_array(nr_chips, sizeof(struct chip), GFP_KERNEL);
+	if (!chips)
+		return -ENOMEM;
+
+	for (i = 0; i < nr_chips; i++) {
+		chips[i].id = chip[i];
+		chips[i].throttled = false;
+		cpumask_copy(&chips[i].mask, cpumask_of_node(chip[i]));
+		INIT_WORK(&chips[i].throttle, powernv_cpufreq_work_fn);
+		chips[i].restore = false;
+	}
+
+	return 0;
+}
+
 static int __init powernv_cpufreq_init(void)
 {
 	int rc = 0;
@@ -429,7 +596,13 @@ static int __init powernv_cpufreq_init(void)
 		return rc;
 	}
 
+	/* Populate chip info */
+	rc = init_chip_info();
+	if (rc)
+		return rc;
+
 	register_reboot_notifier(&powernv_cpufreq_reboot_nb);
+	opal_message_notifier_register(OPAL_MSG_OCC, &powernv_cpufreq_opal_nb);
 	return cpufreq_register_driver(&powernv_cpufreq_driver);
 }
 module_init(powernv_cpufreq_init);
@@ -437,6 +610,8 @@ module_init(powernv_cpufreq_init);
 static void __exit powernv_cpufreq_exit(void)
 {
 	unregister_reboot_notifier(&powernv_cpufreq_reboot_nb);
+	opal_message_notifier_unregister(OPAL_MSG_OCC,
+					 &powernv_cpufreq_opal_nb);
 	cpufreq_unregister_driver(&powernv_cpufreq_driver);
 }
 module_exit(powernv_cpufreq_exit);
diff --git a/kernel/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c b/kernel/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
index d29e8da39..7969f7690 100644
--- a/kernel/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
+++ b/kernel/drivers/cpufreq/ppc_cbe_cpufreq_pmi.c
@@ -97,8 +97,8 @@ static int pmi_notifier(struct notifier_block *nb,
 	struct cpufreq_frequency_table *cbe_freqs;
 	u8 node;
 
-	/* Should this really be called for CPUFREQ_ADJUST, CPUFREQ_INCOMPATIBLE
-	 * and CPUFREQ_NOTIFY policy events?)
+	/* Should this really be called for CPUFREQ_ADJUST and CPUFREQ_NOTIFY
+	 * policy events?)
 	 */
 	if (event == CPUFREQ_START)
 		return 0;
diff --git a/kernel/drivers/cpufreq/pxa2xx-cpufreq.c b/kernel/drivers/cpufreq/pxa2xx-cpufreq.c
index e24269ab4..096377232 100644
--- a/kernel/drivers/cpufreq/pxa2xx-cpufreq.c
+++ b/kernel/drivers/cpufreq/pxa2xx-cpufreq.c
@@ -56,7 +56,7 @@ module_param(pxa27x_maxfreq, uint, 0);
 MODULE_PARM_DESC(pxa27x_maxfreq, "Set the pxa27x maxfreq in MHz"
 		 "(typically 624=>pxa270, 416=>pxa271, 520=>pxa272)");
 
-typedef struct {
+struct pxa_freqs {
 	unsigned int khz;
 	unsigned int membus;
 	unsigned int cccr;
@@ -64,7 +64,7 @@ typedef struct {
 	unsigned int cclkcfg;
 	int vmin;
 	int vmax;
-} pxa_freqs_t;
+};
 
 /* Define the refresh period in mSec for the SDRAM and the number of rows */
 #define SDRAM_TREF	64	/* standard 64ms SDRAM */
@@ -86,7 +86,7 @@ static unsigned int sdram_rows;
 /* Use the run mode frequencies for the CPUFREQ_POLICY_PERFORMANCE policy */
 #define CCLKCFG			CCLKCFG_TURBO | CCLKCFG_FCS
 
-static pxa_freqs_t pxa255_run_freqs[] =
+static const struct pxa_freqs pxa255_run_freqs[] =
 {
 	/* CPU   MEMBUS  CCCR  DIV2 CCLKCFG	           run  turbo PXbus SDRAM */
 	{ 99500,  99500, 0x121, 1,  CCLKCFG, -1, -1},	/*  99,   99,   50,   50  */
@@ -98,7 +98,7 @@ static pxa_freqs_t pxa255_run_freqs[] =
 };
 
 /* Use the turbo mode frequencies for the CPUFREQ_POLICY_POWERSAVE policy */
-static pxa_freqs_t pxa255_turbo_freqs[] =
+static const struct pxa_freqs pxa255_turbo_freqs[] =
 {
 	/* CPU   MEMBUS  CCCR  DIV2 CCLKCFG	   run  turbo PXbus SDRAM */
 	{ 99500, 99500,  0x121, 1,  CCLKCFG, -1, -1},	/*  99,   99,   50,   50  */
@@ -153,7 +153,7 @@ MODULE_PARM_DESC(pxa255_turbo_table, "Selects the frequency table (0 = run table
    ((HT) ? CCLKCFG_HALFTURBO : 0) | \
    ((T)  ? CCLKCFG_TURBO : 0))
 
-static pxa_freqs_t pxa27x_freqs[] = {
+static struct pxa_freqs pxa27x_freqs[] = {
 	{104000, 104000, PXA27x_CCCR(1,	 8, 2), 0, CCLKCFG2(1, 0, 1),  900000, 1705000 },
 	{156000, 104000, PXA27x_CCCR(1,	 8, 3), 0, CCLKCFG2(1, 0, 1), 1000000, 1705000 },
 	{208000, 208000, PXA27x_CCCR(0, 16, 2), 1, CCLKCFG2(0, 0, 1), 1180000, 1705000 },
@@ -171,7 +171,7 @@ extern unsigned get_clk_frequency_khz(int info);
 
 #ifdef CONFIG_REGULATOR
 
-static int pxa_cpufreq_change_voltage(pxa_freqs_t *pxa_freq)
+static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq)
 {
 	int ret = 0;
 	int vmin, vmax;
@@ -202,7 +202,7 @@ static void __init pxa_cpufreq_init_voltages(void)
 	}
 }
 #else
-static int pxa_cpufreq_change_voltage(pxa_freqs_t *pxa_freq)
+static int pxa_cpufreq_change_voltage(const struct pxa_freqs *pxa_freq)
 {
 	return 0;
 }
@@ -211,7 +211,7 @@ static void __init pxa_cpufreq_init_voltages(void) { }
 #endif
 
 static void find_freq_tables(struct cpufreq_frequency_table **freq_table,
-			     pxa_freqs_t **pxa_freqs)
+			     const struct pxa_freqs **pxa_freqs)
 {
 	if (cpu_is_pxa25x()) {
 		if (!pxa255_turbo_table) {
@@ -270,7 +270,7 @@ static unsigned int pxa_cpufreq_get(unsigned int cpu)
 static int pxa_set_target(struct cpufreq_policy *policy, unsigned int idx)
 {
 	struct cpufreq_frequency_table *pxa_freqs_table;
-	pxa_freqs_t *pxa_freq_settings;
+	const struct pxa_freqs *pxa_freq_settings;
 	unsigned long flags;
 	unsigned int new_freq_cpu, new_freq_mem;
 	unsigned int unused, preset_mdrefr, postset_mdrefr, cclkcfg;
@@ -361,7 +361,7 @@ static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 	int i;
 	unsigned int freq;
 	struct cpufreq_frequency_table *pxa255_freq_table;
-	pxa_freqs_t *pxa255_freqs;
+	const struct pxa_freqs *pxa255_freqs;
 
 	/* try to guess pxa27x cpu */
 	if (cpu_is_pxa27x())
diff --git a/kernel/drivers/cpufreq/qoriq-cpufreq.c b/kernel/drivers/cpufreq/qoriq-cpufreq.c
index 88b21ae0d..358f0752c 100644
--- a/kernel/drivers/cpufreq/qoriq-cpufreq.c
+++ b/kernel/drivers/cpufreq/qoriq-cpufreq.c
@@ -27,11 +27,11 @@
 
 /**
  * struct cpu_data
- * @parent: the parent node of cpu clock
+ * @pclk: the parent clock of cpu
  * @table: frequency table
  */
 struct cpu_data {
-	struct device_node *parent;
+	struct clk **pclk;
 	struct cpufreq_frequency_table *table;
 };
 
@@ -196,7 +196,7 @@ static void freq_table_sort(struct cpufreq_frequency_table *freq_table,
 
 static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 {
-	struct device_node *np;
+	struct device_node *np, *pnode;
 	int i, count, ret;
 	u32 freq, mask;
 	struct clk *clk;
@@ -219,17 +219,23 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		goto err_nomem2;
 	}
 
-	data->parent = of_parse_phandle(np, "clocks", 0);
-	if (!data->parent) {
+	pnode = of_parse_phandle(np, "clocks", 0);
+	if (!pnode) {
 		pr_err("%s: could not get clock information\n", __func__);
 		goto err_nomem2;
 	}
 
-	count = of_property_count_strings(data->parent, "clock-names");
+	count = of_property_count_strings(pnode, "clock-names");
+	data->pclk = kcalloc(count, sizeof(struct clk *), GFP_KERNEL);
+	if (!data->pclk) {
+		pr_err("%s: no memory\n", __func__);
+		goto err_node;
+	}
+
 	table = kcalloc(count + 1, sizeof(*table), GFP_KERNEL);
 	if (!table) {
 		pr_err("%s: no memory\n", __func__);
-		goto err_node;
+		goto err_pclk;
 	}
 
 	if (fmask)
@@ -238,7 +244,8 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		mask = 0x0;
 
 	for (i = 0; i < count; i++) {
-		clk = of_clk_get(data->parent, i);
+		clk = of_clk_get(pnode, i);
+		data->pclk[i] = clk;
 		freq = clk_get_rate(clk);
 		/*
 		 * the clock is valid if its frequency is not masked
@@ -273,13 +280,16 @@ static int qoriq_cpufreq_cpu_init(struct cpufreq_policy *policy)
 	policy->cpuinfo.transition_latency = u64temp + 1;
 
 	of_node_put(np);
+	of_node_put(pnode);
 
 	return 0;
 
 err_nomem1:
 	kfree(table);
+err_pclk:
+	kfree(data->pclk);
 err_node:
-	of_node_put(data->parent);
+	of_node_put(pnode);
 err_nomem2:
 	policy->driver_data = NULL;
 	kfree(data);
@@ -293,7 +303,7 @@ static int __exit qoriq_cpufreq_cpu_exit(struct cpufreq_policy *policy)
 {
 	struct cpu_data *data = policy->driver_data;
 
-	of_node_put(data->parent);
+	kfree(data->pclk);
 	kfree(data->table);
 	kfree(data);
 	policy->driver_data = NULL;
@@ -307,7 +317,7 @@ static int qoriq_cpufreq_target(struct cpufreq_policy *policy,
 	struct clk *parent;
 	struct cpu_data *data = policy->driver_data;
 
-	parent = of_clk_get(data->parent, data->table[index].driver_data);
+	parent = data->pclk[data->table[index].driver_data];
 	return clk_set_parent(policy->clk, parent);
 }
 
diff --git a/kernel/drivers/cpufreq/s3c24xx-cpufreq.c b/kernel/drivers/cpufreq/s3c24xx-cpufreq.c
index 733aa5153..68ef8fd94 100644
--- a/kernel/drivers/cpufreq/s3c24xx-cpufreq.c
+++ b/kernel/drivers/cpufreq/s3c24xx-cpufreq.c
@@ -648,7 +648,7 @@ late_initcall(s3c_cpufreq_initcall);
  *
  * Register the given set of PLLs with the system.
  */
-int __init s3c_plltab_register(struct cpufreq_frequency_table *plls,
+int s3c_plltab_register(struct cpufreq_frequency_table *plls,
 			       unsigned int plls_no)
 {
 	struct cpufreq_frequency_table *vals;
diff --git a/kernel/drivers/cpufreq/s5pv210-cpufreq.c b/kernel/drivers/cpufreq/s5pv210-cpufreq.c
index b0dac7d6b..051a8a822 100644
--- a/kernel/drivers/cpufreq/s5pv210-cpufreq.c
+++ b/kernel/drivers/cpufreq/s5pv210-cpufreq.c
@@ -212,11 +212,11 @@ static void s5pv210_set_refresh(enum s5pv210_dmc_port ch, unsigned long freq)
 	/* Find current DRAM frequency */
 	tmp = s5pv210_dram_conf[ch].freq;
 
-	do_div(tmp, freq);
+	tmp /= freq;
 
 	tmp1 = s5pv210_dram_conf[ch].refresh;
 
-	do_div(tmp1, tmp);
+	tmp1 /= tmp;
 
 	__raw_writel(tmp1, reg);
 }
@@ -659,4 +659,4 @@ static struct platform_driver s5pv210_cpufreq_platdrv = {
 	},
 	.probe = s5pv210_cpufreq_probe,
 };
-module_platform_driver(s5pv210_cpufreq_platdrv);
+builtin_platform_driver(s5pv210_cpufreq_platdrv);
diff --git a/kernel/drivers/cpufreq/scpi-cpufreq.c b/kernel/drivers/cpufreq/scpi-cpufreq.c
new file mode 100644
index 000000000..de5e89b2e
--- /dev/null
+++ b/kernel/drivers/cpufreq/scpi-cpufreq.c
@@ -0,0 +1,124 @@
+/*
+ * System Control and Power Interface (SCPI) based CPUFreq Interface driver
+ *
+ * It provides necessary ops to arm_big_little cpufreq driver.
+ *
+ * Copyright (C) 2015 ARM Ltd.
+ * Sudeep Holla <sudeep.holla@arm.com>
+ *
+ * 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 program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpufreq.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/scpi_protocol.h>
+#include <linux/types.h>
+
+#include "arm_big_little.h"
+
+static struct scpi_ops *scpi_ops;
+
+static struct scpi_dvfs_info *scpi_get_dvfs_info(struct device *cpu_dev)
+{
+	int domain = topology_physical_package_id(cpu_dev->id);
+
+	if (domain < 0)
+		return ERR_PTR(-EINVAL);
+	return scpi_ops->dvfs_get_info(domain);
+}
+
+static int scpi_opp_table_ops(struct device *cpu_dev, bool remove)
+{
+	int idx, ret = 0;
+	struct scpi_opp *opp;
+	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+
+	if (!info->opps)
+		return -EIO;
+
+	for (opp = info->opps, idx = 0; idx < info->count; idx++, opp++) {
+		if (remove)
+			dev_pm_opp_remove(cpu_dev, opp->freq);
+		else
+			ret = dev_pm_opp_add(cpu_dev, opp->freq,
+					     opp->m_volt * 1000);
+		if (ret) {
+			dev_warn(cpu_dev, "failed to add opp %uHz %umV\n",
+				 opp->freq, opp->m_volt);
+			while (idx-- > 0)
+				dev_pm_opp_remove(cpu_dev, (--opp)->freq);
+			return ret;
+		}
+	}
+	return ret;
+}
+
+static int scpi_get_transition_latency(struct device *cpu_dev)
+{
+	struct scpi_dvfs_info *info = scpi_get_dvfs_info(cpu_dev);
+
+	if (IS_ERR(info))
+		return PTR_ERR(info);
+	return info->latency;
+}
+
+static int scpi_init_opp_table(struct device *cpu_dev)
+{
+	return scpi_opp_table_ops(cpu_dev, false);
+}
+
+static void scpi_free_opp_table(struct device *cpu_dev)
+{
+	scpi_opp_table_ops(cpu_dev, true);
+}
+
+static struct cpufreq_arm_bL_ops scpi_cpufreq_ops = {
+	.name	= "scpi",
+	.get_transition_latency = scpi_get_transition_latency,
+	.init_opp_table = scpi_init_opp_table,
+	.free_opp_table = scpi_free_opp_table,
+};
+
+static int scpi_cpufreq_probe(struct platform_device *pdev)
+{
+	scpi_ops = get_scpi_ops();
+	if (!scpi_ops)
+		return -EIO;
+
+	return bL_cpufreq_register(&scpi_cpufreq_ops);
+}
+
+static int scpi_cpufreq_remove(struct platform_device *pdev)
+{
+	bL_cpufreq_unregister(&scpi_cpufreq_ops);
+	scpi_ops = NULL;
+	return 0;
+}
+
+static struct platform_driver scpi_cpufreq_platdrv = {
+	.driver = {
+		.name	= "scpi-cpufreq",
+		.owner	= THIS_MODULE,
+	},
+	.probe		= scpi_cpufreq_probe,
+	.remove		= scpi_cpufreq_remove,
+};
+module_platform_driver(scpi_cpufreq_platdrv);
+
+MODULE_AUTHOR("Sudeep Holla <sudeep.holla@arm.com>");
+MODULE_DESCRIPTION("ARM SCPI CPUFreq interface driver");
+MODULE_LICENSE("GPL v2");
diff --git a/kernel/drivers/cpufreq/sfi-cpufreq.c b/kernel/drivers/cpufreq/sfi-cpufreq.c
index ffa3389e5..992ce6f9a 100644
--- a/kernel/drivers/cpufreq/sfi-cpufreq.c
+++ b/kernel/drivers/cpufreq/sfi-cpufreq.c
@@ -45,12 +45,10 @@ static int sfi_parse_freq(struct sfi_table_header *table)
 	pentry = (struct sfi_freq_table_entry *)sb->pentry;
 	totallen = num_freq_table_entries * sizeof(*pentry);
 
-	sfi_cpufreq_array = kzalloc(totallen, GFP_KERNEL);
+	sfi_cpufreq_array = kmemdup(pentry, totallen, GFP_KERNEL);
 	if (!sfi_cpufreq_array)
 		return -ENOMEM;
 
-	memcpy(sfi_cpufreq_array, pentry, totallen);
-
 	return 0;
 }
 
diff --git a/kernel/drivers/cpufreq/speedstep-ich.c b/kernel/drivers/cpufreq/speedstep-ich.c
index e56d632a8..37555c6b8 100644
--- a/kernel/drivers/cpufreq/speedstep-ich.c
+++ b/kernel/drivers/cpufreq/speedstep-ich.c
@@ -292,7 +292,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
+	cpumask_copy(policy->cpus, topology_sibling_cpumask(policy->cpu));
 #endif
 	policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);
 
diff --git a/kernel/drivers/cpufreq/speedstep-lib.c b/kernel/drivers/cpufreq/speedstep-lib.c
index 4ab7a2156..15d3214aa 100644
--- a/kernel/drivers/cpufreq/speedstep-lib.c
+++ b/kernel/drivers/cpufreq/speedstep-lib.c
@@ -386,7 +386,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 	unsigned int prev_speed;
 	unsigned int ret = 0;
 	unsigned long flags;
-	struct timeval tv1, tv2;
+	ktime_t tv1, tv2;
 
 	if ((!processor) || (!low_speed) || (!high_speed) || (!set_state))
 		return -EINVAL;
@@ -415,14 +415,14 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 
 	/* start latency measurement */
 	if (transition_latency)
-		do_gettimeofday(&tv1);
+		tv1 = ktime_get();
 
 	/* switch to high state */
 	set_state(SPEEDSTEP_HIGH);
 
 	/* end latency measurement */
 	if (transition_latency)
-		do_gettimeofday(&tv2);
+		tv2 = ktime_get();
 
 	*high_speed = speedstep_get_frequency(processor);
 	if (!*high_speed) {
@@ -442,8 +442,7 @@ unsigned int speedstep_get_freqs(enum speedstep_processor processor,
 		set_state(SPEEDSTEP_LOW);
 
 	if (transition_latency) {
-		*transition_latency = (tv2.tv_sec - tv1.tv_sec) * USEC_PER_SEC +
-			tv2.tv_usec - tv1.tv_usec;
+		*transition_latency = ktime_to_us(ktime_sub(tv2, tv1));
 		pr_debug("transition latency is %u uSec\n", *transition_latency);
 
 		/* convert uSec to nSec and add 20% for safety reasons */
diff --git a/kernel/drivers/cpufreq/tegra124-cpufreq.c b/kernel/drivers/cpufreq/tegra124-cpufreq.c
new file mode 100644
index 000000000..20bcceb58
--- /dev/null
+++ b/kernel/drivers/cpufreq/tegra124-cpufreq.c
@@ -0,0 +1,214 @@
+/*
+ * Tegra 124 cpufreq driver
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpufreq-dt.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/regulator/consumer.h>
+#include <linux/types.h>
+
+struct tegra124_cpufreq_priv {
+	struct regulator *vdd_cpu_reg;
+	struct clk *cpu_clk;
+	struct clk *pllp_clk;
+	struct clk *pllx_clk;
+	struct clk *dfll_clk;
+	struct platform_device *cpufreq_dt_pdev;
+};
+
+static int tegra124_cpu_switch_to_dfll(struct tegra124_cpufreq_priv *priv)
+{
+	struct clk *orig_parent;
+	int ret;
+
+	ret = clk_set_rate(priv->dfll_clk, clk_get_rate(priv->cpu_clk));
+	if (ret)
+		return ret;
+
+	orig_parent = clk_get_parent(priv->cpu_clk);
+	clk_set_parent(priv->cpu_clk, priv->pllp_clk);
+
+	ret = clk_prepare_enable(priv->dfll_clk);
+	if (ret)
+		goto out;
+
+	clk_set_parent(priv->cpu_clk, priv->dfll_clk);
+
+	return 0;
+
+out:
+	clk_set_parent(priv->cpu_clk, orig_parent);
+
+	return ret;
+}
+
+static void tegra124_cpu_switch_to_pllx(struct tegra124_cpufreq_priv *priv)
+{
+	clk_set_parent(priv->cpu_clk, priv->pllp_clk);
+	clk_disable_unprepare(priv->dfll_clk);
+	regulator_sync_voltage(priv->vdd_cpu_reg);
+	clk_set_parent(priv->cpu_clk, priv->pllx_clk);
+}
+
+static struct cpufreq_dt_platform_data cpufreq_dt_pd = {
+	.independent_clocks = false,
+};
+
+static int tegra124_cpufreq_probe(struct platform_device *pdev)
+{
+	struct tegra124_cpufreq_priv *priv;
+	struct device_node *np;
+	struct device *cpu_dev;
+	struct platform_device_info cpufreq_dt_devinfo = {};
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev)
+		return -ENODEV;
+
+	np = of_cpu_device_node_get(0);
+	if (!np)
+		return -ENODEV;
+
+	priv->vdd_cpu_reg = regulator_get(cpu_dev, "vdd-cpu");
+	if (IS_ERR(priv->vdd_cpu_reg)) {
+		ret = PTR_ERR(priv->vdd_cpu_reg);
+		goto out_put_np;
+	}
+
+	priv->cpu_clk = of_clk_get_by_name(np, "cpu_g");
+	if (IS_ERR(priv->cpu_clk)) {
+		ret = PTR_ERR(priv->cpu_clk);
+		goto out_put_vdd_cpu_reg;
+	}
+
+	priv->dfll_clk = of_clk_get_by_name(np, "dfll");
+	if (IS_ERR(priv->dfll_clk)) {
+		ret = PTR_ERR(priv->dfll_clk);
+		goto out_put_cpu_clk;
+	}
+
+	priv->pllx_clk = of_clk_get_by_name(np, "pll_x");
+	if (IS_ERR(priv->pllx_clk)) {
+		ret = PTR_ERR(priv->pllx_clk);
+		goto out_put_dfll_clk;
+	}
+
+	priv->pllp_clk = of_clk_get_by_name(np, "pll_p");
+	if (IS_ERR(priv->pllp_clk)) {
+		ret = PTR_ERR(priv->pllp_clk);
+		goto out_put_pllx_clk;
+	}
+
+	ret = tegra124_cpu_switch_to_dfll(priv);
+	if (ret)
+		goto out_put_pllp_clk;
+
+	cpufreq_dt_devinfo.name = "cpufreq-dt";
+	cpufreq_dt_devinfo.parent = &pdev->dev;
+	cpufreq_dt_devinfo.data = &cpufreq_dt_pd;
+	cpufreq_dt_devinfo.size_data = sizeof(cpufreq_dt_pd);
+
+	priv->cpufreq_dt_pdev =
+		platform_device_register_full(&cpufreq_dt_devinfo);
+	if (IS_ERR(priv->cpufreq_dt_pdev)) {
+		ret = PTR_ERR(priv->cpufreq_dt_pdev);
+		goto out_switch_to_pllx;
+	}
+
+	platform_set_drvdata(pdev, priv);
+
+	return 0;
+
+out_switch_to_pllx:
+	tegra124_cpu_switch_to_pllx(priv);
+out_put_pllp_clk:
+	clk_put(priv->pllp_clk);
+out_put_pllx_clk:
+	clk_put(priv->pllx_clk);
+out_put_dfll_clk:
+	clk_put(priv->dfll_clk);
+out_put_cpu_clk:
+	clk_put(priv->cpu_clk);
+out_put_vdd_cpu_reg:
+	regulator_put(priv->vdd_cpu_reg);
+out_put_np:
+	of_node_put(np);
+
+	return ret;
+}
+
+static int tegra124_cpufreq_remove(struct platform_device *pdev)
+{
+	struct tegra124_cpufreq_priv *priv = platform_get_drvdata(pdev);
+
+	platform_device_unregister(priv->cpufreq_dt_pdev);
+	tegra124_cpu_switch_to_pllx(priv);
+
+	clk_put(priv->pllp_clk);
+	clk_put(priv->pllx_clk);
+	clk_put(priv->dfll_clk);
+	clk_put(priv->cpu_clk);
+	regulator_put(priv->vdd_cpu_reg);
+
+	return 0;
+}
+
+static struct platform_driver tegra124_cpufreq_platdrv = {
+	.driver.name	= "cpufreq-tegra124",
+	.probe		= tegra124_cpufreq_probe,
+	.remove		= tegra124_cpufreq_remove,
+};
+
+static int __init tegra_cpufreq_init(void)
+{
+	int ret;
+	struct platform_device *pdev;
+
+	if (!of_machine_is_compatible("nvidia,tegra124"))
+		return -ENODEV;
+
+	/*
+	 * Platform driver+device required for handling EPROBE_DEFER with
+	 * the regulator and the DFLL clock
+	 */
+	ret = platform_driver_register(&tegra124_cpufreq_platdrv);
+	if (ret)
+		return ret;
+
+	pdev = platform_device_register_simple("cpufreq-tegra124", -1, NULL, 0);
+	if (IS_ERR(pdev)) {
+		platform_driver_unregister(&tegra124_cpufreq_platdrv);
+		return PTR_ERR(pdev);
+	}
+
+	return 0;
+}
+module_init(tegra_cpufreq_init);
+
+MODULE_AUTHOR("Tuomas Tynkkynen <ttynkkynen@nvidia.com>");
+MODULE_DESCRIPTION("cpufreq driver for NVIDIA Tegra124");
+MODULE_LICENSE("GPL v2");
diff --git a/kernel/drivers/cpufreq/tegra-cpufreq.c b/kernel/drivers/cpufreq/tegra20-cpufreq.c
index 8084c7f7e..2bd62845e 100644
--- a/kernel/drivers/cpufreq/tegra-cpufreq.c
+++ b/kernel/drivers/cpufreq/tegra20-cpufreq.c
@@ -175,9 +175,7 @@ static struct cpufreq_driver tegra_cpufreq_driver = {
 	.exit			= tegra_cpu_exit,
 	.name			= "tegra",
 	.attr			= cpufreq_generic_attr,
-#ifdef CONFIG_PM
 	.suspend		= cpufreq_generic_suspend,
-#endif
 };
 
 static int __init tegra_cpufreq_init(void)