[CPUFREQ] Move x86 drivers to drivers/cpufreq/

Signed-off-by: Dave Jones <davej@redhat.com>

26 files changed, 10552 insertions, 1 deletions

diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
index b78baa547ef..9fb84853d8e 100644
--- a/drivers/cpufreq/Kconfig
+++ b/drivers/cpufreq/Kconfig
@@ -1,3 +1,5 @@
+menu "CPU Frequency scaling"
+
 config CPU_FREQ
 	bool "CPU Frequency scaling"
 	help
@@ -177,4 +179,10 @@ config CPU_FREQ_GOV_CONSERVATIVE
 
 	  If in doubt, say N.
 
-endif	# CPU_FREQ
+menu "x86 CPU frequency scaling drivers"
+depends on X86
+source "drivers/cpufreq/Kconfig.x86"
+endmenu
+
+endif
+endmenu
diff --git a/drivers/cpufreq/Kconfig.x86 b/drivers/cpufreq/Kconfig.x86
new file mode 100644
index 00000000000..343f8476048
--- /dev/null
+++ b/drivers/cpufreq/Kconfig.x86
@@ -0,0 +1,255 @@
+#
+# x86 CPU Frequency scaling drivers
+#
+
+config X86_PCC_CPUFREQ
+	tristate "Processor Clocking Control interface driver"
+	depends on ACPI && ACPI_PROCESSOR
+	help
+	  This driver adds support for the PCC interface.
+
+	  For details, take a look at:
+	  <file:Documentation/cpu-freq/pcc-cpufreq.txt>.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called pcc-cpufreq.
+
+	  If in doubt, say N.
+
+config X86_ACPI_CPUFREQ
+	tristate "ACPI Processor P-States driver"
+	select CPU_FREQ_TABLE
+	depends on ACPI_PROCESSOR
+	help
+	  This driver adds a CPUFreq driver which utilizes the ACPI
+	  Processor Performance States.
+	  This driver also supports Intel Enhanced Speedstep.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called acpi-cpufreq.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config ELAN_CPUFREQ
+	tristate "AMD Elan SC400 and SC410"
+	select CPU_FREQ_TABLE
+	depends on X86_ELAN
+	---help---
+	  This adds the CPUFreq driver for AMD Elan SC400 and SC410
+	  processors.
+
+	  You need to specify the processor maximum speed as boot
+	  parameter: elanfreq=maxspeed (in kHz) or as module
+	  parameter "max_freq".
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config SC520_CPUFREQ
+	tristate "AMD Elan SC520"
+	select CPU_FREQ_TABLE
+	depends on X86_ELAN
+	---help---
+	  This adds the CPUFreq driver for AMD Elan SC520 processor.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+
+config X86_POWERNOW_K6
+	tristate "AMD Mobile K6-2/K6-3 PowerNow!"
+	select CPU_FREQ_TABLE
+	depends on X86_32
+	help
+	  This adds the CPUFreq driver for mobile AMD K6-2+ and mobile
+	  AMD K6-3+ processors.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_POWERNOW_K7
+	tristate "AMD Mobile Athlon/Duron PowerNow!"
+	select CPU_FREQ_TABLE
+	depends on X86_32
+	help
+	  This adds the CPUFreq driver for mobile AMD K7 mobile processors.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_POWERNOW_K7_ACPI
+	bool
+	depends on X86_POWERNOW_K7 && ACPI_PROCESSOR
+	depends on !(X86_POWERNOW_K7 = y && ACPI_PROCESSOR = m)
+	depends on X86_32
+	default y
+
+config X86_POWERNOW_K8
+	tristate "AMD Opteron/Athlon64 PowerNow!"
+	select CPU_FREQ_TABLE
+	depends on ACPI && ACPI_PROCESSOR
+	help
+	  This adds the CPUFreq driver for K8/K10 Opteron/Athlon64 processors.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called powernow-k8.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+config X86_GX_SUSPMOD
+	tristate "Cyrix MediaGX/NatSemi Geode Suspend Modulation"
+	depends on X86_32 && PCI
+	help
+	 This add the CPUFreq driver for NatSemi Geode processors which
+	 support suspend modulation.
+
+	 For details, take a look at <file:Documentation/cpu-freq/>.
+
+	 If in doubt, say N.
+
+config X86_SPEEDSTEP_CENTRINO
+	tristate "Intel Enhanced SpeedStep (deprecated)"
+	select CPU_FREQ_TABLE
+	select X86_SPEEDSTEP_CENTRINO_TABLE if X86_32
+	depends on X86_32 || (X86_64 && ACPI_PROCESSOR)
+	help
+	  This is deprecated and this functionality is now merged into
+	  acpi_cpufreq (X86_ACPI_CPUFREQ). Use that driver instead of
+	  speedstep_centrino.
+	  This adds the CPUFreq driver for Enhanced SpeedStep enabled
+	  mobile CPUs.  This means Intel Pentium M (Centrino) CPUs
+	  or 64bit enabled Intel Xeons.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called speedstep-centrino.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_SPEEDSTEP_CENTRINO_TABLE
+	bool "Built-in tables for Banias CPUs"
+	depends on X86_32 && X86_SPEEDSTEP_CENTRINO
+	default y
+	help
+	  Use built-in tables for Banias CPUs if ACPI encoding
+	  is not available.
+
+	  If in doubt, say N.
+
+config X86_SPEEDSTEP_ICH
+	tristate "Intel Speedstep on ICH-M chipsets (ioport interface)"
+	select CPU_FREQ_TABLE
+	depends on X86_32
+	help
+	  This adds the CPUFreq driver for certain mobile Intel Pentium III
+	  (Coppermine), all mobile Intel Pentium III-M (Tualatin) and all
+	  mobile Intel Pentium 4 P4-M on systems which have an Intel ICH2,
+	  ICH3 or ICH4 southbridge.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_SPEEDSTEP_SMI
+	tristate "Intel SpeedStep on 440BX/ZX/MX chipsets (SMI interface)"
+	select CPU_FREQ_TABLE
+	depends on X86_32 && EXPERIMENTAL
+	help
+	  This adds the CPUFreq driver for certain mobile Intel Pentium III
+	  (Coppermine), all mobile Intel Pentium III-M (Tualatin)
+	  on systems which have an Intel 440BX/ZX/MX southbridge.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_P4_CLOCKMOD
+	tristate "Intel Pentium 4 clock modulation"
+	select CPU_FREQ_TABLE
+	help
+	  This adds the CPUFreq driver for Intel Pentium 4 / XEON
+	  processors.  When enabled it will lower CPU temperature by skipping
+	  clocks.
+
+	  This driver should be only used in exceptional
+	  circumstances when very low power is needed because it causes severe
+	  slowdowns and noticeable latencies.  Normally Speedstep should be used
+	  instead.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called p4-clockmod.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  Unless you are absolutely sure say N.
+
+config X86_CPUFREQ_NFORCE2
+	tristate "nVidia nForce2 FSB changing"
+	depends on X86_32 && EXPERIMENTAL
+	help
+	  This adds the CPUFreq driver for FSB changing on nVidia nForce2
+	  platforms.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_LONGRUN
+	tristate "Transmeta LongRun"
+	depends on X86_32
+	help
+	  This adds the CPUFreq driver for Transmeta Crusoe and Efficeon processors
+	  which support LongRun.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_LONGHAUL
+	tristate "VIA Cyrix III Longhaul"
+	select CPU_FREQ_TABLE
+	depends on X86_32 && ACPI_PROCESSOR
+	help
+	  This adds the CPUFreq driver for VIA Samuel/CyrixIII,
+	  VIA Cyrix Samuel/C3, VIA Cyrix Ezra and VIA Cyrix Ezra-T
+	  processors.
+
+	  For details, take a look at <file:Documentation/cpu-freq/>.
+
+	  If in doubt, say N.
+
+config X86_E_POWERSAVER
+	tristate "VIA C7 Enhanced PowerSaver (DANGEROUS)"
+	select CPU_FREQ_TABLE
+	depends on X86_32 && EXPERIMENTAL
+	help
+	  This adds the CPUFreq driver for VIA C7 processors.  However, this driver
+	  does not have any safeguards to prevent operating the CPU out of spec
+	  and is thus considered dangerous.  Please use the regular ACPI cpufreq
+	  driver, enabled by CONFIG_X86_ACPI_CPUFREQ.
+
+	  If in doubt, say N.
+
+comment "shared options"
+
+config X86_SPEEDSTEP_LIB
+	tristate
+	default (X86_SPEEDSTEP_ICH || X86_SPEEDSTEP_SMI || X86_P4_CLOCKMOD)
+
+config X86_SPEEDSTEP_RELAXED_CAP_CHECK
+	bool "Relaxed speedstep capability checks"
+	depends on X86_32 && (X86_SPEEDSTEP_SMI || X86_SPEEDSTEP_ICH)
+	help
+	  Don't perform all checks for a speedstep capable system which would
+	  normally be done. Some ancient or strange systems, though speedstep
+	  capable, don't always indicate that they are speedstep capable. This
+	  option lets the probing code bypass some of those checks if the
+	  parameter "relaxed_check=1" is passed to the module.
+
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 71fc3b4173f..c7f1a6f16b6 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -13,3 +13,29 @@ obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE)	+= cpufreq_conservative.o
 # CPUfreq cross-arch helpers
 obj-$(CONFIG_CPU_FREQ_TABLE)		+= freq_table.o
 
+##################################################################################d
+# 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_ACPI_CPUFREQ)		+= acpi-cpufreq.o mperf.o
+obj-$(CONFIG_X86_PCC_CPUFREQ)		+= pcc-cpufreq.o
+obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
+obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
+obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
+obj-$(CONFIG_X86_E_POWERSAVER)		+= e_powersaver.o
+obj-$(CONFIG_ELAN_CPUFREQ)		+= elanfreq.o
+obj-$(CONFIG_SC520_CPUFREQ)		+= sc520_freq.o
+obj-$(CONFIG_X86_LONGRUN)		+= longrun.o
+obj-$(CONFIG_X86_GX_SUSPMOD)		+= gx-suspmod.o
+obj-$(CONFIG_X86_SPEEDSTEP_ICH)		+= speedstep-ich.o
+obj-$(CONFIG_X86_SPEEDSTEP_LIB)		+= speedstep-lib.o
+obj-$(CONFIG_X86_SPEEDSTEP_SMI)		+= speedstep-smi.o
+obj-$(CONFIG_X86_SPEEDSTEP_CENTRINO)	+= speedstep-centrino.o
+obj-$(CONFIG_X86_P4_CLOCKMOD)		+= p4-clockmod.o
+obj-$(CONFIG_X86_CPUFREQ_NFORCE2)	+= cpufreq-nforce2.o
+
+##################################################################################d
+
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
new file mode 100644
index 00000000000..4e04e127438
--- /dev/null
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -0,0 +1,773 @@
+/*
+ * acpi-cpufreq.c - ACPI Processor P-States Driver
+ *
+ *  Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
+ *  Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de>
+ *  Copyright (C) 2006       Denis Sadykov <denis.m.sadykov@intel.com>
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or (at
+ *  your option) any later version.
+ *
+ *  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.
+ *
+ *  You should have received a copy of the GNU General Public License along
+ *  with this program; if not, write to the Free Software Foundation, Inc.,
+ *  59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
+ *
+ * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/smp.h>
+#include <linux/sched.h>
+#include <linux/cpufreq.h>
+#include <linux/compiler.h>
+#include <linux/dmi.h>
+#include <linux/slab.h>
+
+#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+
+#include <acpi/processor.h>
+
+#include <asm/msr.h>
+#include <asm/processor.h>
+#include <asm/cpufeature.h>
+#include "mperf.h"
+
+MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
+MODULE_DESCRIPTION("ACPI Processor P-States Driver");
+MODULE_LICENSE("GPL");
+
+enum {
+	UNDEFINED_CAPABLE = 0,
+	SYSTEM_INTEL_MSR_CAPABLE,
+	SYSTEM_IO_CAPABLE,
+};
+
+#define INTEL_MSR_RANGE		(0xffff)
+
+struct acpi_cpufreq_data {
+	struct acpi_processor_performance *acpi_data;
+	struct cpufreq_frequency_table *freq_table;
+	unsigned int resume;
+	unsigned int cpu_feature;
+};
+
+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 struct cpufreq_driver acpi_cpufreq_driver;
+
+static unsigned int acpi_pstate_strict;
+
+static int check_est_cpu(unsigned int cpuid)
+{
+	struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
+
+	return cpu_has(cpu, X86_FEATURE_EST);
+}
+
+static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
+{
+	struct acpi_processor_performance *perf;
+	int i;
+
+	perf = data->acpi_data;
+
+	for (i = 0; i < perf->state_count; i++) {
+		if (value == perf->states[i].status)
+			return data->freq_table[i].frequency;
+	}
+	return 0;
+}
+
+static unsigned extract_msr(u32 msr, struct acpi_cpufreq_data *data)
+{
+	int i;
+	struct acpi_processor_performance *perf;
+
+	msr &= INTEL_MSR_RANGE;
+	perf = data->acpi_data;
+
+	for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
+		if (msr == perf->states[data->freq_table[i].index].status)
+			return data->freq_table[i].frequency;
+	}
+	return data->freq_table[0].frequency;
+}
+
+static unsigned extract_freq(u32 val, struct acpi_cpufreq_data *data)
+{
+	switch (data->cpu_feature) {
+	case SYSTEM_INTEL_MSR_CAPABLE:
+		return extract_msr(val, data);
+	case SYSTEM_IO_CAPABLE:
+		return extract_io(val, data);
+	default:
+		return 0;
+	}
+}
+
+struct msr_addr {
+	u32 reg;
+};
+
+struct io_addr {
+	u16 port;
+	u8 bit_width;
+};
+
+struct drv_cmd {
+	unsigned int type;
+	const struct cpumask *mask;
+	union {
+		struct msr_addr msr;
+		struct io_addr io;
+	} addr;
+	u32 val;
+};
+
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
+{
+	struct drv_cmd *cmd = _cmd;
+	u32 h;
+
+	switch (cmd->type) {
+	case SYSTEM_INTEL_MSR_CAPABLE:
+		rdmsr(cmd->addr.msr.reg, cmd->val, h);
+		break;
+	case SYSTEM_IO_CAPABLE:
+		acpi_os_read_port((acpi_io_address)cmd->addr.io.port,
+				&cmd->val,
+				(u32)cmd->addr.io.bit_width);
+		break;
+	default:
+		break;
+	}
+}
+
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
+{
+	struct drv_cmd *cmd = _cmd;
+	u32 lo, hi;
+
+	switch (cmd->type) {
+	case SYSTEM_INTEL_MSR_CAPABLE:
+		rdmsr(cmd->addr.msr.reg, lo, hi);
+		lo = (lo & ~INTEL_MSR_RANGE) | (cmd->val & INTEL_MSR_RANGE);
+		wrmsr(cmd->addr.msr.reg, lo, hi);
+		break;
+	case SYSTEM_IO_CAPABLE:
+		acpi_os_write_port((acpi_io_address)cmd->addr.io.port,
+				cmd->val,
+				(u32)cmd->addr.io.bit_width);
+		break;
+	default:
+		break;
+	}
+}
+
+static void drv_read(struct drv_cmd *cmd)
+{
+	int err;
+	cmd->val = 0;
+
+	err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
+	WARN_ON_ONCE(err);	/* smp_call_function_any() was buggy? */
+}
+
+static void drv_write(struct drv_cmd *cmd)
+{
+	int this_cpu;
+
+	this_cpu = get_cpu();
+	if (cpumask_test_cpu(this_cpu, cmd->mask))
+		do_drv_write(cmd);
+	smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+	put_cpu();
+}
+
+static u32 get_cur_val(const struct cpumask *mask)
+{
+	struct acpi_processor_performance *perf;
+	struct drv_cmd cmd;
+
+	if (unlikely(cpumask_empty(mask)))
+		return 0;
+
+	switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
+	case SYSTEM_INTEL_MSR_CAPABLE:
+		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
+		cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
+		break;
+	case SYSTEM_IO_CAPABLE:
+		cmd.type = SYSTEM_IO_CAPABLE;
+		perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
+		cmd.addr.io.port = perf->control_register.address;
+		cmd.addr.io.bit_width = perf->control_register.bit_width;
+		break;
+	default:
+		return 0;
+	}
+
+	cmd.mask = mask;
+	drv_read(&cmd);
+
+	pr_debug("get_cur_val = %u\n", cmd.val);
+
+	return cmd.val;
+}
+
+static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
+{
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
+	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)) {
+		return 0;
+	}
+
+	cached_freq = data->freq_table[data->acpi_data->state].frequency;
+	freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
+	if (freq != cached_freq) {
+		/*
+		 * The dreaded BIOS frequency change behind our back.
+		 * Force set the frequency on next target call.
+		 */
+		data->resume = 1;
+	}
+
+	pr_debug("cur freq = %u\n", freq);
+
+	return freq;
+}
+
+static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
+				struct acpi_cpufreq_data *data)
+{
+	unsigned int cur_freq;
+	unsigned int i;
+
+	for (i = 0; i < 100; i++) {
+		cur_freq = extract_freq(get_cur_val(mask), data);
+		if (cur_freq == freq)
+			return 1;
+		udelay(10);
+	}
+	return 0;
+}
+
+static int acpi_cpufreq_target(struct cpufreq_policy *policy,
+			       unsigned int target_freq, unsigned int relation)
+{
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+	struct acpi_processor_performance *perf;
+	struct cpufreq_freqs freqs;
+	struct drv_cmd cmd;
+	unsigned int next_state = 0; /* Index into freq_table */
+	unsigned int next_perf_state = 0; /* Index into perf table */
+	unsigned int i;
+	int result = 0;
+
+	pr_debug("acpi_cpufreq_target %d (%d)\n", target_freq, policy->cpu);
+
+	if (unlikely(data == NULL ||
+	     data->acpi_data == NULL || data->freq_table == NULL)) {
+		return -ENODEV;
+	}
+
+	perf = data->acpi_data;
+	result = cpufreq_frequency_table_target(policy,
+						data->freq_table,
+						target_freq,
+						relation, &next_state);
+	if (unlikely(result)) {
+		result = -ENODEV;
+		goto out;
+	}
+
+	next_perf_state = data->freq_table[next_state].index;
+	if (perf->state == next_perf_state) {
+		if (unlikely(data->resume)) {
+			pr_debug("Called after resume, resetting to P%d\n",
+				next_perf_state);
+			data->resume = 0;
+		} else {
+			pr_debug("Already at target state (P%d)\n",
+				next_perf_state);
+			goto out;
+		}
+	}
+
+	switch (data->cpu_feature) {
+	case SYSTEM_INTEL_MSR_CAPABLE:
+		cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
+		cmd.addr.msr.reg = MSR_IA32_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;
+		cmd.addr.io.bit_width = perf->control_register.bit_width;
+		cmd.val = (u32) perf->states[next_perf_state].control;
+		break;
+	default:
+		result = -ENODEV;
+		goto out;
+	}
+
+	/* cpufreq holds the hotplug lock, so we are safe from here on */
+	if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
+		cmd.mask = policy->cpus;
+	else
+		cmd.mask = cpumask_of(policy->cpu);
+
+	freqs.old = perf->states[perf->state].core_frequency * 1000;
+	freqs.new = data->freq_table[next_state].frequency;
+	for_each_cpu(i, policy->cpus) {
+		freqs.cpu = i;
+		cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+	}
+
+	drv_write(&cmd);
+
+	if (acpi_pstate_strict) {
+		if (!check_freqs(cmd.mask, freqs.new, data)) {
+			pr_debug("acpi_cpufreq_target failed (%d)\n",
+				policy->cpu);
+			result = -EAGAIN;
+			goto out;
+		}
+	}
+
+	for_each_cpu(i, policy->cpus) {
+		freqs.cpu = i;
+		cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	}
+	perf->state = next_perf_state;
+
+out:
+	return result;
+}
+
+static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
+{
+	struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
+
+	pr_debug("acpi_cpufreq_verify\n");
+
+	return cpufreq_frequency_table_verify(policy, data->freq_table);
+}
+
+static unsigned long
+acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
+{
+	struct acpi_processor_performance *perf = data->acpi_data;
+
+	if (cpu_khz) {
+		/* search the closest match to cpu_khz */
+		unsigned int i;
+		unsigned long freq;
+		unsigned long freqn = perf->states[0].core_frequency * 1000;
+
+		for (i = 0; i < (perf->state_count-1); i++) {
+			freq = freqn;
+			freqn = perf->states[i+1].core_frequency * 1000;
+			if ((2 * cpu_khz) > (freqn + freq)) {
+				perf->state = i;
+				return freq;
+			}
+		}
+		perf->state = perf->state_count-1;
+		return freqn;
+	} else {
+		/* assume CPU is at P0... */
+		perf->state = 0;
+		return perf->states[0].core_frequency * 1000;
+	}
+}
+
+static void free_acpi_perf_data(void)
+{
+	unsigned int i;
+
+	/* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */
+	for_each_possible_cpu(i)
+		free_cpumask_var(per_cpu_ptr(acpi_perf_data, i)
+				 ->shared_cpu_map);
+	free_percpu(acpi_perf_data);
+}
+
+/*
+ * acpi_cpufreq_early_init - initialize ACPI P-States library
+ *
+ * Initialize the ACPI P-States library (drivers/acpi/processor_perflib.c)
+ * in order to determine correct frequency and voltage pairings. We can
+ * do _PDC and _PSD and find out the processor dependency for the
+ * actual init that will happen later...
+ */
+static int __init acpi_cpufreq_early_init(void)
+{
+	unsigned int i;
+	pr_debug("acpi_cpufreq_early_init\n");
+
+	acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
+	if (!acpi_perf_data) {
+		pr_debug("Memory allocation error for acpi_perf_data.\n");
+		return -ENOMEM;
+	}
+	for_each_possible_cpu(i) {
+		if (!zalloc_cpumask_var_node(
+			&per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
+			GFP_KERNEL, cpu_to_node(i))) {
+
+			/* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
+			free_acpi_perf_data();
+			return -ENOMEM;
+		}
+	}
+
+	/* Do initialization in ACPI core */
+	acpi_processor_preregister_performance(acpi_perf_data);
+	return 0;
+}
+
+#ifdef CONFIG_SMP
+/*
+ * Some BIOSes do SW_ANY coordination internally, either set it up in hw
+ * or do it in BIOS firmware and won't inform about it to OS. If not
+ * detected, this has a side effect of making CPU run at a different speed
+ * than OS intended it to run at. Detect it and handle it cleanly.
+ */
+static int bios_with_sw_any_bug;
+
+static int sw_any_bug_found(const struct dmi_system_id *d)
+{
+	bios_with_sw_any_bug = 1;
+	return 0;
+}
+
+static const struct dmi_system_id sw_any_bug_dmi_table[] = {
+	{
+		.callback = sw_any_bug_found,
+		.ident = "Supermicro Server X6DLP",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
+			DMI_MATCH(DMI_BIOS_VERSION, "080010"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X6DLP"),
+		},
+	},
+	{ }
+};
+
+static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
+{
+	/* Intel Xeon Processor 7100 Series Specification Update
+	 * http://www.intel.com/Assets/PDF/specupdate/314554.pdf
+	 * AL30: A Machine Check Exception (MCE) Occurring during an
+	 * Enhanced Intel SpeedStep Technology Ratio Change May Cause
+	 * Both Processor Cores to Lock Up. */
+	if (c->x86_vendor == X86_VENDOR_INTEL) {
+		if ((c->x86 == 15) &&
+		    (c->x86_model == 6) &&
+		    (c->x86_mask == 8)) {
+			printk(KERN_INFO "acpi-cpufreq: Intel(R) "
+			    "Xeon(R) 7100 Errata AL30, processors may "
+			    "lock up on frequency changes: disabling "
+			    "acpi-cpufreq.\n");
+			return -ENODEV;
+		    }
+		}
+	return 0;
+}
+#endif
+
+static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int i;
+	unsigned int valid_states = 0;
+	unsigned int cpu = policy->cpu;
+	struct acpi_cpufreq_data *data;
+	unsigned int result = 0;
+	struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
+	struct acpi_processor_performance *perf;
+#ifdef CONFIG_SMP
+	static int blacklisted;
+#endif
+
+	pr_debug("acpi_cpufreq_cpu_init\n");
+
+#ifdef CONFIG_SMP
+	if (blacklisted)
+		return blacklisted;
+	blacklisted = acpi_cpufreq_blacklist(c);
+	if (blacklisted)
+		return blacklisted;
+#endif
+
+	data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
+	per_cpu(acfreq_data, cpu) = 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);
+	if (result)
+		goto err_free;
+
+	perf = data->acpi_data;
+	policy->shared_type = perf->shared_type;
+
+	/*
+	 * Will let policy->cpus know about dependency only when software
+	 * coordination is required.
+	 */
+	if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
+	    policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
+		cpumask_copy(policy->cpus, perf->shared_cpu_map);
+	}
+	cpumask_copy(policy->related_cpus, perf->shared_cpu_map);
+
+#ifdef CONFIG_SMP
+	dmi_check_system(sw_any_bug_dmi_table);
+	if (bios_with_sw_any_bug && cpumask_weight(policy->cpus) == 1) {
+		policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
+		cpumask_copy(policy->cpus, cpu_core_mask(cpu));
+	}
+#endif
+
+	/* capability check */
+	if (perf->state_count <= 1) {
+		pr_debug("No P-States\n");
+		result = -ENODEV;
+		goto err_unreg;
+	}
+
+	if (perf->control_register.space_id != perf->status_register.space_id) {
+		result = -ENODEV;
+		goto err_unreg;
+	}
+
+	switch (perf->control_register.space_id) {
+	case ACPI_ADR_SPACE_SYSTEM_IO:
+		pr_debug("SYSTEM IO addr space\n");
+		data->cpu_feature = SYSTEM_IO_CAPABLE;
+		break;
+	case ACPI_ADR_SPACE_FIXED_HARDWARE:
+		pr_debug("HARDWARE addr space\n");
+		if (!check_est_cpu(cpu)) {
+			result = -ENODEV;
+			goto err_unreg;
+		}
+		data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
+		break;
+	default:
+		pr_debug("Unknown addr space %d\n",
+			(u32) (perf->control_register.space_id));
+		result = -ENODEV;
+		goto err_unreg;
+	}
+
+	data->freq_table = kmalloc(sizeof(struct cpufreq_frequency_table) *
+		    (perf->state_count+1), GFP_KERNEL);
+	if (!data->freq_table) {
+		result = -ENOMEM;
+		goto err_unreg;
+	}
+
+	/* detect transition latency */
+	policy->cpuinfo.transition_latency = 0;
+	for (i = 0; i < perf->state_count; i++) {
+		if ((perf->states[i].transition_latency * 1000) >
+		    policy->cpuinfo.transition_latency)
+			policy->cpuinfo.transition_latency =
+			    perf->states[i].transition_latency * 1000;
+	}
+
+	/* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
+	if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
+	    policy->cpuinfo.transition_latency > 20 * 1000) {
+		policy->cpuinfo.transition_latency = 20 * 1000;
+		printk_once(KERN_INFO