Merge tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael J Wysocki: - Improved system suspend/resume and runtime PM handling for the SH TMU, CMT and MTU2 clock event devices (also used by ARM/shmobile). - Generic PM domains framework extensions related to cpuidle support and domain objects lookup using names. - ARM/shmobile power management updates including improved support for the SH7372's A4S power domain containing the CPU core. - cpufreq changes related to AMD CPUs support from Matthew Garrett, Andre Przywara and Borislav Petkov. - cpu0 cpufreq driver from Shawn Guo. - cpufreq governor fixes related to the relaxing of limit from Michal Pecio. - OMAP cpufreq updates from Axel Lin and Richard Zhao. - cpuidle ladder governor fixes related to the disabling of states from Carsten Emde and me. - Runtime PM core updates related to the interactions with the system suspend core from Alan Stern and Kevin Hilman. - Wakeup sources modification allowing more helper functions to be called from interrupt context from John Stultz and additional diagnostic code from Todd Poynor. - System suspend error code path fix from Feng Hong. Fixed up conflicts in cpufreq/powernow-k8 that stemmed from the workqueue fixes conflicting fairly badly with the removal of support for hardware P-state chips. The changes were independent but somewhat intertwined. * tag 'pm-for-3.7-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (76 commits) Revert "PM QoS: Use spinlock in the per-device PM QoS constraints code" PM / Runtime: let rpm_resume() succeed if RPM_ACTIVE, even when disabled, v2 cpuidle: rename function name "__cpuidle_register_driver", v2 cpufreq: OMAP: Check IS_ERR() instead of NULL for omap_device_get_by_hwmod_name cpuidle: remove some empty lines PM: Prevent runtime suspend during system resume PM QoS: Use spinlock in the per-device PM QoS constraints code PM / Sleep: use resume event when call dpm_resume_early cpuidle / ACPI : move cpuidle_device field out of the acpi_processor_power structure ACPI / processor: remove pointless variable initialization ACPI / processor: remove unused function parameter cpufreq: OMAP: remove loops_per_jiffy recalculate for smp sections: fix section conflicts in drivers/cpufreq cpufreq: conservative: update frequency when limits are relaxed cpufreq / ondemand: update frequency when limits are relaxed properly __init-annotate pm_sysrq_init() cpufreq: Add a generic cpufreq-cpu0 driver PM / OPP: Initialize OPP table from device tree ARM: add cpufreq transiton notifier to adjust loops_per_jiffy for smp cpufreq: Remove support for hardware P-state chips from powernow-k8 ...
2026-05-01 15:00:59 -07:00 · 2012-10-02 18:32:35 -07:00
parent 51562cba98 b9142167a2
commit 16642a2e7b
65 changed files with 2058 additions and 959 deletions
@@ -179,6 +179,17 @@ config CPU_FREQ_GOV_CONSERVATIVE

 	  If in doubt, say N.

+config GENERIC_CPUFREQ_CPU0
+	bool "Generic CPU0 cpufreq driver"
+	depends on HAVE_CLK && REGULATOR && PM_OPP && OF
+	select CPU_FREQ_TABLE
+	help
+	  This adds a generic cpufreq driver for CPU0 frequency management.
+	  It supports both uniprocessor (UP) and symmetric multiprocessor (SMP)
+	  systems which share clock and voltage across all CPUs.
+
+	  If in doubt, say N.
+
 menu "x86 CPU frequency scaling drivers"
 depends on X86
 source "drivers/cpufreq/Kconfig.x86"
@@ -23,7 +23,8 @@ config X86_ACPI_CPUFREQ
 	help
 	  This driver adds a CPUFreq driver which utilizes the ACPI
 	  Processor Performance States.
-	  This driver also supports Intel Enhanced Speedstep.
+	  This driver also supports Intel Enhanced Speedstep and newer
+	  AMD CPUs.

 	  To compile this driver as a module, choose M here: the
 	  module will be called acpi-cpufreq.
@@ -32,6 +33,18 @@ config X86_ACPI_CPUFREQ

 	  If in doubt, say N.

+config X86_ACPI_CPUFREQ_CPB
+	default y
+	bool "Legacy cpb sysfs knob support for AMD CPUs"
+	depends on X86_ACPI_CPUFREQ && CPU_SUP_AMD
+	help
+	  The powernow-k8 driver used to provide a sysfs knob called "cpb"
+	  to disable the Core Performance Boosting feature of AMD CPUs. This
+	  file has now been superseeded by the more generic "boost" entry.
+
+	  By enabling this option the acpi_cpufreq driver provides the old
+	  entry in addition to the new boost ones, for compatibility reasons.
+
 config ELAN_CPUFREQ
 	tristate "AMD Elan SC400 and SC410"
 	select CPU_FREQ_TABLE
@@ -95,7 +108,8 @@ config X86_POWERNOW_K8
 	select CPU_FREQ_TABLE
 	depends on ACPI && ACPI_PROCESSOR
 	help
-	  This adds the CPUFreq driver for K8/K10 Opteron/Athlon64 processors.
+	  This adds the CPUFreq driver for K8/early Opteron/Athlon64 processors.
+	  Support for K10 and newer processors is now in acpi-cpufreq.

 	  To compile this driver as a module, choose M here: the
 	  module will be called powernow-k8.
@@ -13,13 +13,15 @@ obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 # CPUfreq cross-arch helpers
 obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o

+obj-$(CONFIG_GENERIC_CPUFREQ_CPU0)	+= cpufreq-cpu0.o
+
 ##################################################################################
 # x86 drivers.
 # Link order matters. K8 is preferred to ACPI because of firmware bugs in early
 # K8 systems. ACPI is preferred to all other hardware-specific drivers.
 # speedstep-* is preferred over p4-clockmod.

-obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o mperf.o
+obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
 obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
 obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
@@ -51,13 +51,19 @@ MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
 MODULE_DESCRIPTION("ACPI Processor P-States Driver");
 MODULE_LICENSE("GPL");

+#define PFX "acpi-cpufreq: "
+
 enum {
 	UNDEFINED_CAPABLE = 0,
 	SYSTEM_INTEL_MSR_CAPABLE,
+	SYSTEM_AMD_MSR_CAPABLE,
 	SYSTEM_IO_CAPABLE,
 };

 #define INTEL_MSR_RANGE		(0xffff)
+#define AMD_MSR_RANGE		(0x7)
+
+#define MSR_K7_HWCR_CPB_DIS	(1ULL << 25)

 struct acpi_cpufreq_data {
 	struct acpi_processor_performance *acpi_data;
@@ -74,6 +80,116 @@ static struct acpi_processor_performance __percpu *acpi_perf_data;
 static struct cpufreq_driver acpi_cpufreq_driver;

 static unsigned int acpi_pstate_strict;
+static bool boost_enabled, boost_supported;
+static struct msr __percpu *msrs;
+
+static bool boost_state(unsigned int cpu)
+{
+	u32 lo, hi;
+	u64 msr;
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi);
+		msr = lo | ((u64)hi << 32);
+		return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
+	case X86_VENDOR_AMD:
+		rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
+		msr = lo | ((u64)hi << 32);
+		return !(msr & MSR_K7_HWCR_CPB_DIS);
+	}
+	return false;
+}
+
+static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
+{
+	u32 cpu;
+	u32 msr_addr;
+	u64 msr_mask;
+
+	switch (boot_cpu_data.x86_vendor) {
+	case X86_VENDOR_INTEL:
+		msr_addr = MSR_IA32_MISC_ENABLE;
+		msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
+		break;
+	case X86_VENDOR_AMD:
+		msr_addr = MSR_K7_HWCR;
+		msr_mask = MSR_K7_HWCR_CPB_DIS;
+		break;
+	default:
+		return;
+	}
+
+	rdmsr_on_cpus(cpumask, msr_addr, msrs);
+
+	for_each_cpu(cpu, cpumask) {
+		struct msr *reg = per_cpu_ptr(msrs, cpu);
+		if (enable)
+			reg->q &= ~msr_mask;
+		else
+			reg->q |= msr_mask;
+	}
+
+	wrmsr_on_cpus(cpumask, msr_addr, msrs);
+}
+
+static ssize_t _store_boost(const char *buf, size_t count)
+{
+	int ret;
+	unsigned long val = 0;
+
+	if (!boost_supported)
+		return -EINVAL;
+
+	ret = kstrtoul(buf, 10, &val);
+	if (ret || (val > 1))
+		return -EINVAL;
+
+	if ((val && boost_enabled) || (!val && !boost_enabled))
+		return count;
+
+	get_online_cpus();
+
+	boost_set_msrs(val, cpu_online_mask);
+
+	put_online_cpus();
+
+	boost_enabled = val;
+	pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");
+
+	return count;
+}
+
+static ssize_t store_global_boost(struct kobject *kobj, struct attribute *attr,
+				  const char *buf, size_t count)
+{
+	return _store_boost(buf, count);
+}
+
+static ssize_t show_global_boost(struct kobject *kobj,
+				 struct attribute *attr, char *buf)
+{
+	return sprintf(buf, "%u\n", boost_enabled);
+}
+
+static struct global_attr global_boost = __ATTR(boost, 0644,
+						show_global_boost,
+						store_global_boost);
+
+#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
+static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
+			 size_t count)
+{
+	return _store_boost(buf, count);
+}
+
+static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
+{
+	return sprintf(buf, "%u\n", boost_enabled);
+}
+
+static struct freq_attr cpb = __ATTR(cpb, 0644, show_cpb, store_cpb);
+#endif

 static int check_est_cpu(unsigned int cpuid)
 {
@@ -82,6 +198,13 @@ static int check_est_cpu(unsigned int cpuid)
 	return cpu_has(cpu, X86_FEATURE_EST);
 }

+static int check_amd_hwpstate_cpu(unsigned int cpuid)
+{
+	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
+
+	return cpu_has(cpu, X86_FEATURE_HW_PSTATE);
+}
+
 static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
 {
 	struct acpi_processor_performance *perf;
@@ -101,7 +224,11 @@ static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
 	int i;
 	struct acpi_processor_performance *perf;

-	msr &= INTEL_MSR_RANGE;
+	if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
+		msr &= AMD_MSR_RANGE;
+	else
+		msr &= INTEL_MSR_RANGE;
+
 	perf = data->acpi_data;

 	for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
@@ -115,6 +242,7 @@ static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
 {
 	switch (data->cpu_feature) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
+	case SYSTEM_AMD_MSR_CAPABLE:
 		return extract_msr(val, data);
 	case SYSTEM_IO_CAPABLE:
 		return extract_io(val, data);
@@ -150,6 +278,7 @@ static void do_drv_read(void *_cmd)

 	switch (cmd->type) {
 	case SYSTEM_INTEL_MSR_CAPABLE:
+	case SYSTEM_AMD_MSR_CAPABLE:
 		rdmsr(cmd->addr.msr.reg, cmd->val, h);
 		break;
 	case SYSTEM_IO_CAPABLE:
@@ -174,6 +303,9 @@ static void do_drv_write(void *_cmd)
 		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
 		wrmsr(cmd->addr.msr.reg, lo, hi);
 		break;
+	case SYSTEM_AMD_MSR_CAPABLE:
+		wrmsr(cmd->addr.msr.reg, cmd->val, 0);
+		break;
 	case SYSTEM_IO_CAPABLE:
 		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
 				cmd->val,
@@ -217,6 +349,10 @@ static u32 get_cur_val(const struct cpumask *mask)
 		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
 		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
 		break;
+	case SYSTEM_AMD_MSR_CAPABLE:
+		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
+		cmd.addr.msr.reg = MSR_AMD_PERF_STATUS;
+		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
 		perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
@@ -326,6 +462,11 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
 		cmd.addr.msr.reg = MSR_IA32_PERF_CTL;
 		cmd.val = (u32) perf->states[next_perf_state].control;
 		break;
+	case SYSTEM_AMD_MSR_CAPABLE:
+		cmd.type = SYSTEM_AMD_MSR_CAPABLE;
+		cmd.addr.msr.reg = MSR_AMD_PERF_CTL;
+		cmd.val = (u32) perf->states[next_perf_state].control;
+		break;
 	case SYSTEM_IO_CAPABLE:
 		cmd.type = SYSTEM_IO_CAPABLE;
 		cmd.addr.io.port = perf->control_register.address;
@@ -419,6 +560,44 @@ static void free_acpi_perf_data(void)
 	free_percpu(acpi_perf_data);
 }

+static int boost_notify(struct notifier_block *nb, unsigned long action,
+		      void *hcpu)
+{
+	unsigned cpu = (long)hcpu;
+	const struct cpumask *cpumask;
+
+	cpumask = get_cpu_mask(cpu);
+
+	/*
+	 * Clear the boost-disable bit on the CPU_DOWN path so that
+	 * this cpu cannot block the remaining ones from boosting. On
+	 * the CPU_UP path we simply keep the boost-disable flag in
+	 * sync with the current global state.
+	 */
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		boost_set_msrs(boost_enabled, cpumask);
+		break;
+
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		boost_set_msrs(1, cpumask);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+
+static struct notifier_block boost_nb = {
+	.notifier_call          = boost_notify,
+};
+
 /*
 * acpi_cpufreq_early_init - initialize ACPI P-States library
 *
@@ -559,6 +738,14 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
 		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
 	}
+
+	if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
+		cpumask_clear(policy->cpus);
+		cpumask_set_cpu(cpu, policy->cpus);
+		cpumask_copy(policy->related_cpus, cpu_sibling_mask(cpu));
+		policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
+		pr_info_once(PFX "overriding BIOS provided _PSD data\n");
+	}
 #endif

 	/* capability check */
@@ -580,12 +767,16 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
 		break;
 	case ACPI_ADR_SPACE_FIXED_HARDWARE:
 		pr_debug("HARDWARE addr space\n");
-		if (!check_est_cpu(cpu)) {
-			result = -ENODEV;
-			goto err_unreg;
+		if (check_est_cpu(cpu)) {
+			data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
+			break;
 		}
-		data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
-		break;
+		if (check_amd_hwpstate_cpu(cpu)) {
+			data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE;
+			break;
+		}
+		result = -ENODEV;
+		goto err_unreg;
 	default:
 		pr_debug("Unknown addr space %d\n",
 			(u32) (perf->control_register.space_id));
@@ -718,6 +909,7 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy)

 static struct freq_attr *acpi_cpufreq_attr[] = {
 	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,	/* this is a placeholder for cpb, do not remove */
 	NULL,
 };

@@ -733,6 +925,49 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
 	.attr		= acpi_cpufreq_attr,
 };

+static void __init acpi_cpufreq_boost_init(void)
+{
+	if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
+		msrs = msrs_alloc();
+
+		if (!msrs)
+			return;
+
+		boost_supported = true;
+		boost_enabled = boost_state(0);
+
+		get_online_cpus();
+
+		/* Force all MSRs to the same value */
+		boost_set_msrs(boost_enabled, cpu_online_mask);
+
+		register_cpu_notifier(&boost_nb);
+
+		put_online_cpus();
+	} else
+		global_boost.attr.mode = 0444;
+
+	/* We create the boost file in any case, though for systems without
+	 * hardware support it will be read-only and hardwired to return 0.
+	 */
+	if (sysfs_create_file(cpufreq_global_kobject, &(global_boost.attr)))
+		pr_warn(PFX "could not register global boost sysfs file\n");
+	else
+		pr_debug("registered global boost sysfs file\n");
+}
+
+static void __exit acpi_cpufreq_boost_exit(void)
+{
+	sysfs_remove_file(cpufreq_global_kobject, &(global_boost.attr));
+
+	if (msrs) {
+		unregister_cpu_notifier(&boost_nb);
+
+		msrs_free(msrs);
+		msrs = NULL;
+	}
+}
+
 static int __init acpi_cpufreq_init(void)
 {
 	int ret;
@@ -746,9 +981,32 @@ static int __init acpi_cpufreq_init(void)
 	if (ret)
 		return ret;

+#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
+	/* this is a sysfs file with a strange name and an even stranger
+	 * semantic - per CPU instantiation, but system global effect.
+	 * Lets enable it only on AMD CPUs for compatibility reasons and
+	 * 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;
+
+		pr_debug("adding sysfs entry for cpb\n");
+
+		for (iter = acpi_cpufreq_attr; *iter != NULL; iter++)
+			;
+
+		/* make sure there is a terminator behind it */
+		if (iter[1] == NULL)
+			*iter = &cpb;
+	}
+#endif
+
 	ret = cpufreq_register_driver(&acpi_cpufreq_driver);
 	if (ret)
 		free_acpi_perf_data();
+	else
+		acpi_cpufreq_boost_init();

 	return ret;
 }
@@ -757,6 +1015,8 @@ static void __exit acpi_cpufreq_exit(void)
 {
 	pr_debug("acpi_cpufreq_exit\n");

+	acpi_cpufreq_boost_exit();
+
 	cpufreq_unregister_driver(&acpi_cpufreq_driver);

 	free_acpi_perf_data();
@@ -0,0 +1,269 @@
+/*
+ * Copyright (C) 2012 Freescale Semiconductor, Inc.
+ *
+ * The OPP code in function cpu0_set_target() is reused from
+ * drivers/cpufreq/omap-cpufreq.c
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/clk.h>
+#include <linux/cpu.h>
+#include <linux/cpufreq.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/opp.h>
+#include <linux/regulator/consumer.h>
+#include <linux/slab.h>
+
+static unsigned int transition_latency;
+static unsigned int voltage_tolerance; /* in percentage */
+
+static struct device *cpu_dev;
+static struct clk *cpu_clk;
+static struct regulator *cpu_reg;
+static struct cpufreq_frequency_table *freq_table;
+
+static int cpu0_verify_speed(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy, freq_table);
+}
+
+static unsigned int cpu0_get_speed(unsigned int cpu)
+{
+	return clk_get_rate(cpu_clk) / 1000;
+}
+
+static int cpu0_set_target(struct cpufreq_policy *policy,
+			   unsigned int target_freq, unsigned int relation)
+{
+	struct cpufreq_freqs freqs;
+	struct opp *opp;
+	unsigned long freq_Hz, volt = 0, volt_old = 0, tol = 0;
+	unsigned int index, cpu;
+	int ret;
+
+	ret = cpufreq_frequency_table_target(policy, freq_table, target_freq,
+					     relation, &index);
+	if (ret) {
+		pr_err("failed to match target freqency %d: %d\n",
+		       target_freq, ret);
+		return ret;
+	}
+
+	freq_Hz = clk_round_rate(cpu_clk, freq_table[index].frequency * 1000);
+	if (freq_Hz < 0)
+		freq_Hz = freq_table[index].frequency * 1000;
+	freqs.new = freq_Hz / 1000;
+	freqs.old = clk_get_rate(cpu_clk) / 1000;
+
+	if (freqs.old == freqs.new)
+		return 0;
+
+	for_each_online_cpu(cpu) {
+		freqs.cpu = cpu;
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+	}
+
+	if (cpu_reg) {
+		opp = opp_find_freq_ceil(cpu_dev, &freq_Hz);
+		if (IS_ERR(opp)) {
+			pr_err("failed to find OPP for %ld\n", freq_Hz);
+			return PTR_ERR(opp);
+		}
+		volt = opp_get_voltage(opp);
+		tol = volt * voltage_tolerance / 100;
+		volt_old = regulator_get_voltage(cpu_reg);
+	}
+
+	pr_debug("%u MHz, %ld mV --> %u MHz, %ld mV\n",
+		 freqs.old / 1000, volt_old ? volt_old / 1000 : -1,
+		 freqs.new / 1000, volt ? volt / 1000 : -1);
+
+	/* scaling up?  scale voltage before frequency */
+	if (cpu_reg && freqs.new > freqs.old) {
+		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
+		if (ret) {
+			pr_err("failed to scale voltage up: %d\n", ret);
+			freqs.new = freqs.old;
+			return ret;
+		}
+	}
+
+	ret = clk_set_rate(cpu_clk, freqs.new * 1000);
+	if (ret) {
+		pr_err("failed to set clock rate: %d\n", ret);
+		if (cpu_reg)
+			regulator_set_voltage_tol(cpu_reg, volt_old, tol);
+		return ret;
+	}
+
+	/* scaling down?  scale voltage after frequency */
+	if (cpu_reg && freqs.new < freqs.old) {
+		ret = regulator_set_voltage_tol(cpu_reg, volt, tol);
+		if (ret) {
+			pr_err("failed to scale voltage down: %d\n", ret);
+			clk_set_rate(cpu_clk, freqs.old * 1000);
+			freqs.new = freqs.old;
+			return ret;
+		}
+	}
+
+	for_each_online_cpu(cpu) {
+		freqs.cpu = cpu;
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	}
+
+	return 0;
+}
+
+static int cpu0_cpufreq_init(struct cpufreq_policy *policy)
+{
+	int ret;
+
+	if (policy->cpu != 0)
+		return -EINVAL;
+
+	ret = cpufreq_frequency_table_cpuinfo(policy, freq_table);
+	if (ret) {
+		pr_err("invalid frequency table: %d\n", ret);
+		return ret;
+	}
+
+	policy->cpuinfo.transition_latency = transition_latency;
+	policy->cur = clk_get_rate(cpu_clk) / 1000;
+
+	/*
+	 * The driver only supports the SMP configuartion where all processors
+	 * share the clock and voltage and clock.  Use cpufreq affected_cpus
+	 * interface to have all CPUs scaled together.
+	 */
+	policy->shared_type = CPUFREQ_SHARED_TYPE_ANY;
+	cpumask_setall(policy->cpus);
+
+	cpufreq_frequency_table_get_attr(freq_table, policy->cpu);
+
+	return 0;
+}
+
+static int cpu0_cpufreq_exit(struct cpufreq_policy *policy)
+{
+	cpufreq_frequency_table_put_attr(policy->cpu);
+
+	return 0;
+}
+
+static struct freq_attr *cpu0_cpufreq_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static struct cpufreq_driver cpu0_cpufreq_driver = {
+	.flags = CPUFREQ_STICKY,
+	.verify = cpu0_verify_speed,
+	.target = cpu0_set_target,
+	.get = cpu0_get_speed,
+	.init = cpu0_cpufreq_init,
+	.exit = cpu0_cpufreq_exit,
+	.name = "generic_cpu0",
+	.attr = cpu0_cpufreq_attr,
+};
+
+static int __devinit cpu0_cpufreq_driver_init(void)
+{
+	struct device_node *np;
+	int ret;
+
+	np = of_find_node_by_path("/cpus/cpu@0");
+	if (!np) {
+		pr_err("failed to find cpu0 node\n");
+		return -ENOENT;
+	}
+
+	cpu_dev = get_cpu_device(0);
+	if (!cpu_dev) {
+		pr_err("failed to get cpu0 device\n");
+		ret = -ENODEV;
+		goto out_put_node;
+	}
+
+	cpu_dev->of_node = np;
+
+	cpu_clk = clk_get(cpu_dev, NULL);
+	if (IS_ERR(cpu_clk)) {
+		ret = PTR_ERR(cpu_clk);
+		pr_err("failed to get cpu0 clock: %d\n", ret);
+		goto out_put_node;
+	}
+
+	cpu_reg = regulator_get(cpu_dev, "cpu0");
+	if (IS_ERR(cpu_reg)) {
+		pr_warn("failed to get cpu0 regulator\n");
+		cpu_reg = NULL;
+	}
+
+	ret = of_init_opp_table(cpu_dev);
+	if (ret) {
+		pr_err("failed to init OPP table: %d\n", ret);
+		goto out_put_node;
+	}
+
+	ret = opp_init_cpufreq_table(cpu_dev, &freq_table);
+	if (ret) {
+		pr_err("failed to init cpufreq table: %d\n", ret);
+		goto out_put_node;
+	}
+
+	of_property_read_u32(np, "voltage-tolerance", &voltage_tolerance);
+
+	if (of_property_read_u32(np, "clock-latency", &transition_latency))
+		transition_latency = CPUFREQ_ETERNAL;
+
+	if (cpu_reg) {
+		struct opp *opp;
+		unsigned long min_uV, max_uV;
+		int i;
+
+		/*
+		 * OPP is maintained in order of increasing frequency, and
+		 * freq_table initialised from OPP is therefore sorted in the
+		 * same order.
+		 */
+		for (i = 0; freq_table[i].frequency != CPUFREQ_TABLE_END; i++)
+			;
+		opp = opp_find_freq_exact(cpu_dev,
+				freq_table[0].frequency * 1000, true);
+		min_uV = opp_get_voltage(opp);
+		opp = opp_find_freq_exact(cpu_dev,
+				freq_table[i-1].frequency * 1000, true);
+		max_uV = opp_get_voltage(opp);
+		ret = regulator_set_voltage_time(cpu_reg, min_uV, max_uV);
+		if (ret > 0)
+			transition_latency += ret * 1000;
+	}
+
+	ret = cpufreq_register_driver(&cpu0_cpufreq_driver);
+	if (ret) {
+		pr_err("failed register driver: %d\n", ret);
+		goto out_free_table;
+	}
+
+	of_node_put(np);
+	return 0;
+
+out_free_table:
+	opp_free_cpufreq_table(cpu_dev, &freq_table);
+out_put_node:
+	of_node_put(np);
+	return ret;
+}
+late_initcall(cpu0_cpufreq_driver_init);
+
+MODULE_AUTHOR("Shawn Guo <shawn.guo@linaro.org>");
+MODULE_DESCRIPTION("Generic CPU0 cpufreq driver");
+MODULE_LICENSE("GPL");
@@ -504,6 +504,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 				j_dbs_info->prev_cpu_nice =
 						kcpustat_cpu(j).cpustat[CPUTIME_NICE];
 		}
+		this_dbs_info->cpu = cpu;
 		this_dbs_info->down_skip = 0;
 		this_dbs_info->requested_freq = policy->cur;

@@ -583,6 +584,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 			__cpufreq_driver_target(
 					this_dbs_info->cur_policy,
 					policy->min, CPUFREQ_RELATION_L);
+		dbs_check_cpu(this_dbs_info);
 		mutex_unlock(&this_dbs_info->timer_mutex);

 		break;
@@ -761,6 +761,7 @@ static int cpufreq_governor_dbs(struct cpufreq_policy *policy,
 		else if (policy->min > this_dbs_info->cur_policy->cur)
 			__cpufreq_driver_target(this_dbs_info->cur_policy,
 				policy->min, CPUFREQ_RELATION_L);
+		dbs_check_cpu(this_dbs_info);
 		mutex_unlock(&this_dbs_info->timer_mutex);
 		break;
 	}
@@ -56,7 +56,7 @@ union msr_longhaul {
 /*
 * VIA C3 Samuel 1  & Samuel 2 (stepping 0)
 */
-static const int __cpuinitdata samuel1_mults[16] = {
+static const int __cpuinitconst samuel1_mults[16] = {
 	-1, /* 0000 -> RESERVED */
 	30, /* 0001 ->  3.0x */
 	40, /* 0010 ->  4.0x */
@@ -75,7 +75,7 @@ static const int __cpuinitdata samuel1_mults[16] = {
 	-1, /* 1111 -> RESERVED */
 };

-static const int __cpuinitdata samuel1_eblcr[16] = {
+static const int __cpuinitconst samuel1_eblcr[16] = {
 	50, /* 0000 -> RESERVED */
 	30, /* 0001 ->  3.0x */
 	40, /* 0010 ->  4.0x */
@@ -97,7 +97,7 @@ static const int __cpuinitdata samuel1_eblcr[16] = {
 /*
 * VIA C3 Samuel2 Stepping 1->15
 */
-static const int __cpuinitdata samuel2_eblcr[16] = {
+static const int __cpuinitconst samuel2_eblcr[16] = {
 	50,  /* 0000 ->  5.0x */
 	30,  /* 0001 ->  3.0x */
 	40,  /* 0010 ->  4.0x */
@@ -119,7 +119,7 @@ static const int __cpuinitdata samuel2_eblcr[16] = {
 /*
 * VIA C3 Ezra
 */
-static const int __cpuinitdata ezra_mults[16] = {
+static const int __cpuinitconst ezra_mults[16] = {
 	100, /* 0000 -> 10.0x */
 	30,  /* 0001 ->  3.0x */
 	40,  /* 0010 ->  4.0x */
@@ -138,7 +138,7 @@ static const int __cpuinitdata ezra_mults[16] = {
 	120, /* 1111 -> 12.0x */
 };

-static const int __cpuinitdata ezra_eblcr[16] = {
+static const int __cpuinitconst ezra_eblcr[16] = {
 	50,  /* 0000 ->  5.0x */
 	30,  /* 0001 ->  3.0x */
 	40,  /* 0010 ->  4.0x */
@@ -160,7 +160,7 @@ static const int __cpuinitdata ezra_eblcr[16] = {
 /*
 * VIA C3 (Ezra-T) [C5M].
 */
-static const int __cpuinitdata ezrat_mults[32] = {
+static const int __cpuinitconst ezrat_mults[32] = {
 	100, /* 0000 -> 10.0x */
 	30,  /* 0001 ->  3.0x */
 	40,  /* 0010 ->  4.0x */
@@ -196,7 +196,7 @@ static const int __cpuinitdata ezrat_mults[32] = {
 	-1,  /* 1111 -> RESERVED (12.0x) */
 };

-static const int __cpuinitdata ezrat_eblcr[32] = {
+static const int __cpuinitconst ezrat_eblcr[32] = {
 	50,  /* 0000 ->  5.0x */
 	30,  /* 0001 ->  3.0x */
 	40,  /* 0010 ->  4.0x */
@@ -235,7 +235,7 @@ static const int __cpuinitdata ezrat_eblcr[32] = {
 /*
 * VIA C3 Nehemiah */

-static const int __cpuinitdata nehemiah_mults[32] = {
+static const int __cpuinitconst nehemiah_mults[32] = {
 	100, /* 0000 -> 10.0x */
 	-1, /* 0001 -> 16.0x */
 	40,  /* 0010 ->  4.0x */
@@ -270,7 +270,7 @@ static const int __cpuinitdata nehemiah_mults[32] = {
 	-1, /* 1111 -> 12.0x */
 };

-static const int __cpuinitdata nehemiah_eblcr[32] = {
+static const int __cpuinitconst nehemiah_eblcr[32] = {
 	50,  /* 0000 ->  5.0x */
 	160, /* 0001 -> 16.0x */
 	40,  /* 0010 ->  4.0x */
@@ -315,7 +315,7 @@ struct mV_pos {
 	unsigned short pos;
 };

-static const struct mV_pos __cpuinitdata vrm85_mV[32] = {
+static const struct mV_pos __cpuinitconst vrm85_mV[32] = {
 	{1250, 8},	{1200, 6},	{1150, 4},	{1100, 2},
 	{1050, 0},	{1800, 30},	{1750, 28},	{1700, 26},
 	{1650, 24},	{1600, 22},	{1550, 20},	{1500, 18},
@@ -326,14 +326,14 @@ static const struct mV_pos __cpuinitdata vrm85_mV[32] = {
 	{1475, 17},	{1425, 15},	{1375, 13},	{1325, 11}
 };

-static const unsigned char __cpuinitdata mV_vrm85[32] = {
+static const unsigned char __cpuinitconst mV_vrm85[32] = {
 	0x04,	0x14,	0x03,	0x13,	0x02,	0x12,	0x01,	0x11,
 	0x00,	0x10,	0x0f,	0x1f,	0x0e,	0x1e,	0x0d,	0x1d,
 	0x0c,	0x1c,	0x0b,	0x1b,	0x0a,	0x1a,	0x09,	0x19,
 	0x08,	0x18,	0x07,	0x17,	0x06,	0x16,	0x05,	0x15
 };

-static const struct mV_pos __cpuinitdata mobilevrm_mV[32] = {
+static const struct mV_pos __cpuinitconst mobilevrm_mV[32] = {
 	{1750, 31},	{1700, 30},	{1650, 29},	{1600, 28},
 	{1550, 27},	{1500, 26},	{1450, 25},	{1400, 24},
 	{1350, 23},	{1300, 22},	{1250, 21},	{1200, 20},
@@ -344,7 +344,7 @@ static const struct mV_pos __cpuinitdata mobilevrm_mV[32] = {
 	{675, 3},	{650, 2},	{625, 1},	{600, 0}
 };

-static const unsigned char __cpuinitdata mV_mobilevrm[32] = {
+static const unsigned char __cpuinitconst mV_mobilevrm[32] = {
 	0x1f,	0x1e,	0x1d,	0x1c,	0x1b,	0x1a,	0x19,	0x18,
 	0x17,	0x16,	0x15,	0x14,	0x13,	0x12,	0x11,	0x10,
 	0x0f,	0x0e,	0x0d,	0x0c,	0x0b,	0x0a,	0x09,	0x08,
@@ -40,16 +40,6 @@
 /* OPP tolerance in percentage */
 #define	OPP_TOLERANCE	4

-#ifdef CONFIG_SMP
-struct lpj_info {
-	unsigned long	ref;
-	unsigned int	freq;
-};
-
-static DEFINE_PER_CPU(struct lpj_info, lpj_ref);
-static struct lpj_info global_lpj_ref;
-#endif
-
 static struct cpufreq_frequency_table *freq_table;
 static atomic_t freq_table_users = ATOMIC_INIT(0);
 static struct clk *mpu_clk;
@@ -161,31 +151,6 @@ static int omap_target(struct cpufreq_policy *policy,
 	}

 	freqs.new = omap_getspeed(policy->cpu);
-#ifdef CONFIG_SMP
-	/*
-	 * Note that loops_per_jiffy is not updated on SMP systems in
-	 * cpufreq driver. So, update the per-CPU loops_per_jiffy value
-	 * on frequency transition. We need to update all dependent CPUs.
-	 */
-	for_each_cpu(i, policy->cpus) {
-		struct lpj_info *lpj = &per_cpu(lpj_ref, i);
-		if (!lpj->freq) {
-			lpj->ref = per_cpu(cpu_data, i).loops_per_jiffy;
-			lpj->freq = freqs.old;
-		}
-
-		per_cpu(cpu_data, i).loops_per_jiffy =
-			cpufreq_scale(lpj->ref, lpj->freq, freqs.new);
-	}
-
-	/* And don't forget to adjust the global one */
-	if (!global_lpj_ref.freq) {
-		global_lpj_ref.ref = loops_per_jiffy;
-		global_lpj_ref.freq = freqs.old;
-	}
-	loops_per_jiffy = cpufreq_scale(global_lpj_ref.ref, global_lpj_ref.freq,
-					freqs.new);
-#endif

 done:
 	/* notifiers */
@@ -301,9 +266,9 @@ static int __init omap_cpufreq_init(void)
 	}

 	mpu_dev = omap_device_get_by_hwmod_name("mpu");
-	if (!mpu_dev) {
+	if (IS_ERR(mpu_dev)) {
 		pr_warning("%s: unable to get the mpu device\n", __func__);
-		return -EINVAL;
+		return PTR_ERR(mpu_dev);
 	}

 	mpu_reg = regulator_get(mpu_dev, "vcc");
@@ -5,24 +5,11 @@
 *  http://www.gnu.org/licenses/gpl.html
 */

-enum pstate {
-	HW_PSTATE_INVALID = 0xff,
-	HW_PSTATE_0 = 0,
-	HW_PSTATE_1 = 1,
-	HW_PSTATE_2 = 2,
-	HW_PSTATE_3 = 3,
-	HW_PSTATE_4 = 4,
-	HW_PSTATE_5 = 5,
-	HW_PSTATE_6 = 6,
-	HW_PSTATE_7 = 7,
-};
-
 struct powernow_k8_data {
 	unsigned int cpu;

 	u32 numps;  /* number of p-states */
 	u32 batps;  /* number of p-states supported on battery */
-	u32 max_hw_pstate; /* maximum legal hardware pstate */

 	/* these values are constant when the PSB is used to determine
 	 * vid/fid pairings, but are modified during the ->target() call
@@ -37,7 +24,6 @@ struct powernow_k8_data {
 	/* keep track of the current fid / vid or pstate */
 	u32 currvid;
 	u32 currfid;
-	enum pstate currpstate;

 	/* the powernow_table includes all frequency and vid/fid pairings:
 	 * fid are the lower 8 bits of the index, vid are the upper 8 bits.
@@ -97,23 +83,6 @@ struct powernow_k8_data {
 #define MSR_S_HI_CURRENT_VID      0x0000003f
 #define MSR_C_HI_STP_GNT_BENIGN	  0x00000001

-
-/* Hardware Pstate _PSS and MSR definitions */
-#define USE_HW_PSTATE		0x00000080
-#define HW_PSTATE_MASK 		0x00000007
-#define HW_PSTATE_VALID_MASK 	0x80000000
-#define HW_PSTATE_MAX_MASK	0x000000f0
-#define HW_PSTATE_MAX_SHIFT	4
-#define MSR_PSTATE_DEF_BASE 	0xc0010064 /* base of Pstate MSRs */
-#define MSR_PSTATE_STATUS 	0xc0010063 /* Pstate Status MSR */
-#define MSR_PSTATE_CTRL 	0xc0010062 /* Pstate control MSR */
-#define MSR_PSTATE_CUR_LIMIT	0xc0010061 /* pstate current limit MSR */
-
-/* define the two driver architectures */
-#define CPU_OPTERON 0
-#define CPU_HW_PSTATE 1
-
-
 /*
 * There are restrictions frequencies have to follow:
 * - only 1 entry in the low fid table ( <=1.4GHz )
@@ -218,5 +187,4 @@ static int core_frequency_transition(struct powernow_k8_data *data, u32 reqfid);

 static void powernow_k8_acpi_pst_values(struct powernow_k8_data *data, unsigned int index);

-static int fill_powernow_table_pstate(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);
 static int fill_powernow_table_fidvid(struct powernow_k8_data *data, struct cpufreq_frequency_table *powernow_table);