Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux

Pull thermal management updates from Zhang Rui:

 - Add locking for cooling device sysfs attribute in case the cooling
   device state is changed by userspace and thermal framework
   simultaneously. (Thara Gopinath)

 - Fix a problem that passive cooling is reset improperly after system
   suspend/resume. (Wei Wang)

 - Cleanup the driver/thermal/ directory by moving intel and qcom
   platform specific drivers to platform specific sub-directories. (Amit
   Kucheria)

 - Some trivial cleanups. (Lukasz Luba, Wolfram Sang)

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/rzhang/linux:
  thermal/intel: fixup for Kconfig string parsing tightening up
  drivers: thermal: Move QCOM_SPMI_TEMP_ALARM into the qcom subdir
  drivers: thermal: Move various drivers for intel platforms into a subdir
  thermal: Fix locking in cooling device sysfs update cur_state
  Thermal: do not clear passive state during system sleep
  thermal: zx2967_thermal: simplify getting .driver_data
  thermal: st: st_thermal: simplify getting .driver_data
  thermal: spear_thermal: simplify getting .driver_data
  thermal: rockchip_thermal: simplify getting .driver_data
  thermal: int340x_thermal: int3400_thermal: simplify getting .driver_data
  thermal: remove unused function parameter

21 files changed, 5757 insertions, 0 deletions

diff --git a/drivers/thermal/intel/Kconfig b/drivers/thermal/intel/Kconfig
new file mode 100644
index 000000000000..2e013eeb4a1d
--- /dev/null
+++ b/drivers/thermal/intel/Kconfig
@@ -0,0 +1,77 @@
+config INTEL_POWERCLAMP
+	tristate "Intel PowerClamp idle injection driver"
+	depends on THERMAL
+	depends on X86
+	depends on CPU_SUP_INTEL
+	help
+	  Enable this to enable Intel PowerClamp idle injection driver. This
+	  enforce idle time which results in more package C-state residency. The
+	  user interface is exposed via generic thermal framework.
+
+config X86_PKG_TEMP_THERMAL
+	tristate "X86 package temperature thermal driver"
+	depends on X86_THERMAL_VECTOR
+	select THERMAL_GOV_USER_SPACE
+	select THERMAL_WRITABLE_TRIPS
+	default m
+	help
+	  Enable this to register CPU digital sensor for package temperature as
+	  thermal zone. Each package will have its own thermal zone. There are
+	  two trip points which can be set by user to get notifications via thermal
+	  notification methods.
+
+config INTEL_SOC_DTS_IOSF_CORE
+	tristate
+	depends on X86 && PCI
+	select IOSF_MBI
+	help
+	  This is becoming a common feature for Intel SoCs to expose the additional
+	  digital temperature sensors (DTSs) using side band interface (IOSF). This
+	  implements the common set of helper functions to register, get temperature
+	  and get/set thresholds on DTSs.
+
+config INTEL_SOC_DTS_THERMAL
+	tristate "Intel SoCs DTS thermal driver"
+	depends on X86 && PCI && ACPI
+	select INTEL_SOC_DTS_IOSF_CORE
+	select THERMAL_WRITABLE_TRIPS
+	help
+	  Enable this to register Intel SoCs (e.g. Bay Trail) platform digital
+	  temperature sensor (DTS). These SoCs have two additional DTSs in
+	  addition to DTSs on CPU cores. Each DTS will be registered as a
+	  thermal zone. There are two trip points. One of the trip point can
+	  be set by user mode programs to get notifications via Linux thermal
+	  notification methods.The other trip is a critical trip point, which
+	  was set by the driver based on the TJ MAX temperature.
+
+config INTEL_QUARK_DTS_THERMAL
+	tristate "Intel Quark DTS thermal driver"
+	depends on X86_INTEL_QUARK
+	help
+	  Enable this to register Intel Quark SoC (e.g. X1000) platform digital
+	  temperature sensor (DTS). For X1000 SoC, it has one on-die DTS.
+	  The DTS will be registered as a thermal zone. There are two trip points:
+	  hot & critical. The critical trip point default value is set by
+	  underlying BIOS/Firmware.
+
+menu "ACPI INT340X thermal drivers"
+source "drivers/thermal/intel/int340x_thermal/Kconfig"
+endmenu
+
+config INTEL_BXT_PMIC_THERMAL
+	tristate "Intel Broxton PMIC thermal driver"
+	depends on X86 && INTEL_SOC_PMIC_BXTWC && REGMAP
+	help
+	  Select this driver for Intel Broxton PMIC with ADC channels monitoring
+	  system temperature measurements and alerts.
+	  This driver is used for monitoring the ADC channels of PMIC and handles
+	  the alert trip point interrupts and notifies the thermal framework with
+	  the trip point and temperature details of the zone.
+
+config INTEL_PCH_THERMAL
+	tristate "Intel PCH Thermal Reporting Driver"
+	depends on X86 && PCI
+	help
+	  Enable this to support thermal reporting on certain intel PCHs.
+	  Thermal reporting device will provide temperature reading,
+	  programmable trip points and other information.
diff --git a/drivers/thermal/intel/Makefile b/drivers/thermal/intel/Makefile
new file mode 100644
index 000000000000..0d9736ced5d4
--- /dev/null
+++ b/drivers/thermal/intel/Makefile
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for various Intel thermal drivers.
+
+obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
+obj-$(CONFIG_X86_PKG_TEMP_THERMAL)	+= x86_pkg_temp_thermal.o
+obj-$(CONFIG_INTEL_SOC_DTS_IOSF_CORE)	+= intel_soc_dts_iosf.o
+obj-$(CONFIG_INTEL_SOC_DTS_THERMAL)	+= intel_soc_dts_thermal.o
+obj-$(CONFIG_INTEL_QUARK_DTS_THERMAL)	+= intel_quark_dts_thermal.o
+obj-$(CONFIG_INT340X_THERMAL)  += int340x_thermal/
+obj-$(CONFIG_INTEL_BXT_PMIC_THERMAL) += intel_bxt_pmic_thermal.o
+obj-$(CONFIG_INTEL_PCH_THERMAL)	+= intel_pch_thermal.o
diff --git a/drivers/thermal/intel/int340x_thermal/Kconfig b/drivers/thermal/intel/int340x_thermal/Kconfig
new file mode 100644
index 000000000000..0582bd12a239
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/Kconfig
@@ -0,0 +1,42 @@
+#
+# ACPI INT340x thermal drivers configuration
+#
+
+config INT340X_THERMAL
+	tristate "ACPI INT340X thermal drivers"
+	depends on X86 && ACPI
+	select THERMAL_GOV_USER_SPACE
+	select ACPI_THERMAL_REL
+	select ACPI_FAN
+	select INTEL_SOC_DTS_IOSF_CORE
+	help
+	  Newer laptops and tablets that use ACPI may have thermal sensors and
+	  other devices with thermal control capabilities outside the core
+	  CPU/SOC, for thermal safety reasons.
+	  They are exposed for the OS to use via the INT3400 ACPI device object
+	  as the master, and INT3401~INT340B ACPI device objects as the slaves.
+	  Enable this to expose the temperature information and cooling ability
+	  from these objects to userspace via the normal thermal framework.
+	  This means that a wide range of applications and GUI widgets can show
+	  the information to the user or use this information for making
+	  decisions. For example, the Intel Thermal Daemon can use this
+	  information to allow the user to select his laptop to run without
+	  turning on the fans.
+
+config ACPI_THERMAL_REL
+	tristate
+	depends on ACPI
+
+if INT340X_THERMAL
+
+config INT3406_THERMAL
+	tristate "ACPI INT3406 display thermal driver"
+	depends on ACPI_VIDEO
+	help
+	  The display thermal device represents the LED/LCD display panel
+	  that may or may not include touch support. The main function of
+	  the display thermal device is to allow control of the display
+	  brightness in order to address a thermal condition or to reduce
+	  power consumed by display device.
+
+endif
diff --git a/drivers/thermal/intel/int340x_thermal/Makefile b/drivers/thermal/intel/int340x_thermal/Makefile
new file mode 100644
index 000000000000..287eb0a1476d
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/Makefile
@@ -0,0 +1,8 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_INT340X_THERMAL)	+= int3400_thermal.o
+obj-$(CONFIG_INT340X_THERMAL)	+= int340x_thermal_zone.o
+obj-$(CONFIG_INT340X_THERMAL)	+= int3402_thermal.o
+obj-$(CONFIG_INT340X_THERMAL)	+= int3403_thermal.o
+obj-$(CONFIG_INT340X_THERMAL)	+= processor_thermal_device.o
+obj-$(CONFIG_INT3406_THERMAL)	+= int3406_thermal.o
+obj-$(CONFIG_ACPI_THERMAL_REL)	+= acpi_thermal_rel.o
diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
new file mode 100644
index 000000000000..45e7e5cbdffb
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.c
@@ -0,0 +1,394 @@
+/* acpi_thermal_rel.c driver for exporting ACPI thermal relationship
+ *
+ * Copyright (c) 2014 Intel Corp
+ *
+ * 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.
+ *
+ */
+
+/*
+ * Two functionalities included:
+ * 1. Export _TRT, _ART, via misc device interface to the userspace.
+ * 2. Provide parsing result to kernel drivers
+ *
+ */
+#include <linux/init.h>
+#include <linux/export.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/io.h>
+#include <linux/acpi.h>
+#include <linux/uaccess.h>
+#include <linux/miscdevice.h>
+#include "acpi_thermal_rel.h"
+
+static acpi_handle acpi_thermal_rel_handle;
+static DEFINE_SPINLOCK(acpi_thermal_rel_chrdev_lock);
+static int acpi_thermal_rel_chrdev_count;	/* #times opened */
+static int acpi_thermal_rel_chrdev_exclu;	/* already open exclusive? */
+
+static int acpi_thermal_rel_open(struct inode *inode, struct file *file)
+{
+	spin_lock(&acpi_thermal_rel_chrdev_lock);
+	if (acpi_thermal_rel_chrdev_exclu ||
+	    (acpi_thermal_rel_chrdev_count && (file->f_flags & O_EXCL))) {
+		spin_unlock(&acpi_thermal_rel_chrdev_lock);
+		return -EBUSY;
+	}
+
+	if (file->f_flags & O_EXCL)
+		acpi_thermal_rel_chrdev_exclu = 1;
+	acpi_thermal_rel_chrdev_count++;
+
+	spin_unlock(&acpi_thermal_rel_chrdev_lock);
+
+	return nonseekable_open(inode, file);
+}
+
+static int acpi_thermal_rel_release(struct inode *inode, struct file *file)
+{
+	spin_lock(&acpi_thermal_rel_chrdev_lock);
+	acpi_thermal_rel_chrdev_count--;
+	acpi_thermal_rel_chrdev_exclu = 0;
+	spin_unlock(&acpi_thermal_rel_chrdev_lock);
+
+	return 0;
+}
+
+/**
+ * acpi_parse_trt - Thermal Relationship Table _TRT for passive cooling
+ *
+ * @handle: ACPI handle of the device contains _TRT
+ * @trt_count: the number of valid entries resulted from parsing _TRT
+ * @trtp: pointer to pointer of array of _TRT entries in parsing result
+ * @create_dev: whether to create platform devices for target and source
+ *
+ */
+int acpi_parse_trt(acpi_handle handle, int *trt_count, struct trt **trtp,
+		bool create_dev)
+{
+	acpi_status status;
+	int result = 0;
+	int i;
+	int nr_bad_entries = 0;
+	struct trt *trts;
+	struct acpi_device *adev;
+	union acpi_object *p;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer element = { 0, NULL };
+	struct acpi_buffer trt_format = { sizeof("RRNNNNNN"), "RRNNNNNN" };
+
+	if (!acpi_has_method(handle, "_TRT"))
+		return -ENODEV;
+
+	status = acpi_evaluate_object(handle, "_TRT", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	p = buffer.pointer;
+	if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
+		pr_err("Invalid _TRT data\n");
+		result = -EFAULT;
+		goto end;
+	}
+
+	*trt_count = p->package.count;
+	trts = kcalloc(*trt_count, sizeof(struct trt), GFP_KERNEL);
+	if (!trts) {
+		result = -ENOMEM;
+		goto end;
+	}
+
+	for (i = 0; i < *trt_count; i++) {
+		struct trt *trt = &trts[i - nr_bad_entries];
+
+		element.length = sizeof(struct trt);
+		element.pointer = trt;
+
+		status = acpi_extract_package(&(p->package.elements[i]),
+					      &trt_format, &element);
+		if (ACPI_FAILURE(status)) {
+			nr_bad_entries++;
+			pr_warn("_TRT package %d is invalid, ignored\n", i);
+			continue;
+		}
+		if (!create_dev)
+			continue;
+
+		result = acpi_bus_get_device(trt->source, &adev);
+		if (result)
+			pr_warn("Failed to get source ACPI device\n");
+
+		result = acpi_bus_get_device(trt->target, &adev);
+		if (result)
+			pr_warn("Failed to get target ACPI device\n");
+	}
+
+	result = 0;
+
+	*trtp = trts;
+	/* don't count bad entries */
+	*trt_count -= nr_bad_entries;
+end:
+	kfree(buffer.pointer);
+	return result;
+}
+EXPORT_SYMBOL(acpi_parse_trt);
+
+/**
+ * acpi_parse_art - Parse Active Relationship Table _ART
+ *
+ * @handle: ACPI handle of the device contains _ART
+ * @art_count: the number of valid entries resulted from parsing _ART
+ * @artp: pointer to pointer of array of art entries in parsing result
+ * @create_dev: whether to create platform devices for target and source
+ *
+ */
+int acpi_parse_art(acpi_handle handle, int *art_count, struct art **artp,
+		bool create_dev)
+{
+	acpi_status status;
+	int result = 0;
+	int i;
+	int nr_bad_entries = 0;
+	struct art *arts;
+	struct acpi_device *adev;
+	union acpi_object *p;
+	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
+	struct acpi_buffer element = { 0, NULL };
+	struct acpi_buffer art_format =	{
+		sizeof("RRNNNNNNNNNNN"), "RRNNNNNNNNNNN" };
+
+	if (!acpi_has_method(handle, "_ART"))
+		return -ENODEV;
+
+	status = acpi_evaluate_object(handle, "_ART", NULL, &buffer);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	p = buffer.pointer;
+	if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
+		pr_err("Invalid _ART data\n");
+		result = -EFAULT;
+		goto end;
+	}
+
+	/* ignore p->package.elements[0], as this is _ART Revision field */
+	*art_count = p->package.count - 1;
+	arts = kcalloc(*art_count, sizeof(struct art), GFP_KERNEL);
+	if (!arts) {
+		result = -ENOMEM;
+		goto end;
+	}
+
+	for (i = 0; i < *art_count; i++) {
+		struct art *art = &arts[i - nr_bad_entries];
+
+		element.length = sizeof(struct art);
+		element.pointer = art;
+
+		status = acpi_extract_package(&(p->package.elements[i + 1]),
+					      &art_format, &element);
+		if (ACPI_FAILURE(status)) {
+			pr_warn("_ART package %d is invalid, ignored", i);
+			nr_bad_entries++;
+			continue;
+		}
+		if (!create_dev)
+			continue;
+
+		if (art->source) {
+			result = acpi_bus_get_device(art->source, &adev);
+			if (result)
+				pr_warn("Failed to get source ACPI device\n");
+		}
+		if (art->target) {
+			result = acpi_bus_get_device(art->target, &adev);
+			if (result)
+				pr_warn("Failed to get target ACPI device\n");
+		}
+	}
+
+	*artp = arts;
+	/* don't count bad entries */
+	*art_count -= nr_bad_entries;
+end:
+	kfree(buffer.pointer);
+	return result;
+}
+EXPORT_SYMBOL(acpi_parse_art);
+
+
+/* get device name from acpi handle */
+static void get_single_name(acpi_handle handle, char *name)
+{
+	struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER};
+
+	if (ACPI_FAILURE(acpi_get_name(handle, ACPI_SINGLE_NAME, &buffer)))
+		pr_warn("Failed to get device name from acpi handle\n");
+	else {
+		memcpy(name, buffer.pointer, ACPI_NAME_SIZE);
+		kfree(buffer.pointer);
+	}
+}
+
+static int fill_art(char __user *ubuf)
+{
+	int i;
+	int ret;
+	int count;
+	int art_len;
+	struct art *arts = NULL;
+	union art_object *art_user;
+
+	ret = acpi_parse_art(acpi_thermal_rel_handle, &count, &arts, false);
+	if (ret)
+		goto free_art;
+	art_len = count * sizeof(union art_object);
+	art_user = kzalloc(art_len, GFP_KERNEL);
+	if (!art_user) {
+		ret = -ENOMEM;
+		goto free_art;
+	}
+	/* now fill in user art data */
+	for (i = 0; i < count; i++) {
+		/* userspace art needs device name instead of acpi reference */
+		get_single_name(arts[i].source, art_user[i].source_device);
+		get_single_name(arts[i].target, art_user[i].target_device);
+		/* copy the rest int data in addition to source and target */
+		memcpy(&art_user[i].weight, &arts[i].weight,
+			sizeof(u64) * (ACPI_NR_ART_ELEMENTS - 2));
+	}
+
+	if (copy_to_user(ubuf, art_user, art_len))
+		ret = -EFAULT;
+	kfree(art_user);
+free_art:
+	kfree(arts);
+	return ret;
+}
+
+static int fill_trt(char __user *ubuf)
+{
+	int i;
+	int ret;
+	int count;
+	int trt_len;
+	struct trt *trts = NULL;
+	union trt_object *trt_user;
+
+	ret = acpi_parse_trt(acpi_thermal_rel_handle, &count, &trts, false);
+	if (ret)
+		goto free_trt;
+	trt_len = count * sizeof(union trt_object);
+	trt_user = kzalloc(trt_len, GFP_KERNEL);
+	if (!trt_user) {
+		ret = -ENOMEM;
+		goto free_trt;
+	}
+	/* now fill in user trt data */
+	for (i = 0; i < count; i++) {
+		/* userspace trt needs device name instead of acpi reference */
+		get_single_name(trts[i].source, trt_user[i].source_device);
+		get_single_name(trts[i].target, trt_user[i].target_device);
+		trt_user[i].sample_period = trts[i].sample_period;
+		trt_user[i].influence = trts[i].influence;
+	}
+
+	if (copy_to_user(ubuf, trt_user, trt_len))
+		ret = -EFAULT;
+	kfree(trt_user);
+free_trt:
+	kfree(trts);
+	return ret;
+}
+
+static long acpi_thermal_rel_ioctl(struct file *f, unsigned int cmd,
+				   unsigned long __arg)
+{
+	int ret = 0;
+	unsigned long length = 0;
+	int count = 0;
+	char __user *arg = (void __user *)__arg;
+	struct trt *trts = NULL;
+	struct art *arts = NULL;
+
+	switch (cmd) {
+	case ACPI_THERMAL_GET_TRT_COUNT:
+		ret = acpi_parse_trt(acpi_thermal_rel_handle, &count,
+				&trts, false);
+		kfree(trts);
+		if (!ret)
+			return put_user(count, (unsigned long __user *)__arg);
+		return ret;
+	case ACPI_THERMAL_GET_TRT_LEN:
+		ret = acpi_parse_trt(acpi_thermal_rel_handle, &count,
+				&trts, false);
+		kfree(trts);
+		length = count * sizeof(union trt_object);
+		if (!ret)
+			return put_user(length, (unsigned long __user *)__arg);
+		return ret;
+	case ACPI_THERMAL_GET_TRT:
+		return fill_trt(arg);
+	case ACPI_THERMAL_GET_ART_COUNT:
+		ret = acpi_parse_art(acpi_thermal_rel_handle, &count,
+				&arts, false);
+		kfree(arts);
+		if (!ret)
+			return put_user(count, (unsigned long __user *)__arg);
+		return ret;
+	case ACPI_THERMAL_GET_ART_LEN:
+		ret = acpi_parse_art(acpi_thermal_rel_handle, &count,
+				&arts, false);
+		kfree(arts);
+		length = count * sizeof(union art_object);
+		if (!ret)
+			return put_user(length, (unsigned long __user *)__arg);
+		return ret;
+
+	case ACPI_THERMAL_GET_ART:
+		return fill_art(arg);
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations acpi_thermal_rel_fops = {
+	.owner		= THIS_MODULE,
+	.open		= acpi_thermal_rel_open,
+	.release	= acpi_thermal_rel_release,
+	.unlocked_ioctl	= acpi_thermal_rel_ioctl,
+	.llseek		= no_llseek,
+};
+
+static struct miscdevice acpi_thermal_rel_misc_device = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	"acpi_thermal_rel",
+	&acpi_thermal_rel_fops
+};
+
+int acpi_thermal_rel_misc_device_add(acpi_handle handle)
+{
+	acpi_thermal_rel_handle = handle;
+
+	return misc_register(&acpi_thermal_rel_misc_device);
+}
+EXPORT_SYMBOL(acpi_thermal_rel_misc_device_add);
+
+int acpi_thermal_rel_misc_device_remove(acpi_handle handle)
+{
+	misc_deregister(&acpi_thermal_rel_misc_device);
+
+	return 0;
+}
+EXPORT_SYMBOL(acpi_thermal_rel_misc_device_remove);
+
+MODULE_AUTHOR("Zhang Rui <rui.zhang@intel.com>");
+MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@intel.com");
+MODULE_DESCRIPTION("Intel acpi thermal rel misc dev driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.h b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.h
new file mode 100644
index 000000000000..58822575fd54
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/acpi_thermal_rel.h
@@ -0,0 +1,85 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ACPI_ACPI_THERMAL_H
+#define __ACPI_ACPI_THERMAL_H
+
+#include <asm/ioctl.h>
+
+#define ACPI_THERMAL_MAGIC 's'
+
+#define ACPI_THERMAL_GET_TRT_LEN _IOR(ACPI_THERMAL_MAGIC, 1, unsigned long)
+#define ACPI_THERMAL_GET_ART_LEN _IOR(ACPI_THERMAL_MAGIC, 2, unsigned long)
+#define ACPI_THERMAL_GET_TRT_COUNT _IOR(ACPI_THERMAL_MAGIC, 3, unsigned long)
+#define ACPI_THERMAL_GET_ART_COUNT _IOR(ACPI_THERMAL_MAGIC, 4, unsigned long)
+
+#define ACPI_THERMAL_GET_TRT	_IOR(ACPI_THERMAL_MAGIC, 5, unsigned long)
+#define ACPI_THERMAL_GET_ART	_IOR(ACPI_THERMAL_MAGIC, 6, unsigned long)
+
+struct art {
+	acpi_handle source;
+	acpi_handle target;
+	u64 weight;
+	u64 ac0_max;
+	u64 ac1_max;
+	u64 ac2_max;
+	u64 ac3_max;
+	u64 ac4_max;
+	u64 ac5_max;
+	u64 ac6_max;
+	u64 ac7_max;
+	u64 ac8_max;
+	u64 ac9_max;
+} __packed;
+
+struct trt {
+	acpi_handle source;
+	acpi_handle target;
+	u64 influence;
+	u64 sample_period;
+	u64 reserved1;
+	u64 reserved2;
+	u64 reserved3;
+	u64 reserved4;
+} __packed;
+
+#define ACPI_NR_ART_ELEMENTS 13
+/* for usrspace */
+union art_object {
+	struct {
+		char source_device[8]; /* ACPI single name */
+		char target_device[8]; /* ACPI single name */
+		u64 weight;
+		u64 ac0_max_level;
+		u64 ac1_max_level;
+		u64 ac2_max_level;
+		u64 ac3_max_level;
+		u64 ac4_max_level;
+		u64 ac5_max_level;
+		u64 ac6_max_level;
+		u64 ac7_max_level;
+		u64 ac8_max_level;
+		u64 ac9_max_level;
+	};
+	u64 __data[ACPI_NR_ART_ELEMENTS];
+};
+
+union trt_object {
+	struct {
+		char source_device[8]; /* ACPI single name */
+		char target_device[8]; /* ACPI single name */
+		u64 influence;
+		u64 sample_period;
+		u64 reserved[4];
+	};
+	u64 __data[8];
+};
+
+#ifdef __KERNEL__
+int acpi_thermal_rel_misc_device_add(acpi_handle handle);
+int acpi_thermal_rel_misc_device_remove(acpi_handle handle);
+int acpi_parse_art(acpi_handle handle, int *art_count, struct art **arts,
+		bool create_dev);
+int acpi_parse_trt(acpi_handle handle, int *trt_count, struct trt **trts,
+		bool create_dev);
+#endif
+
+#endif /* __ACPI_ACPI_THERMAL_H */
diff --git a/drivers/thermal/intel/int340x_thermal/int3400_thermal.c b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
new file mode 100644
index 000000000000..61ca7ce3624e
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/int3400_thermal.c
@@ -0,0 +1,382 @@
+/*
+ * INT3400 thermal driver
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Authors: Zhang Rui <rui.zhang@intel.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.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include <linux/thermal.h>
+#include "acpi_thermal_rel.h"
+
+#define INT3400_THERMAL_TABLE_CHANGED 0x83
+
+enum int3400_thermal_uuid {
+	INT3400_THERMAL_PASSIVE_1,
+	INT3400_THERMAL_ACTIVE,
+	INT3400_THERMAL_CRITICAL,
+	INT3400_THERMAL_MAXIMUM_UUID,
+};
+
+static char *int3400_thermal_uuids[INT3400_THERMAL_MAXIMUM_UUID] = {
+	"42A441D6-AE6A-462b-A84B-4A8CE79027D3",
+	"3A95C389-E4B8-4629-A526-C52C88626BAE",
+	"97C68AE7-15FA-499c-B8C9-5DA81D606E0A",
+};
+
+struct int3400_thermal_priv {
+	struct acpi_device *adev;
+	struct thermal_zone_device *thermal;
+	int mode;
+	int art_count;
+	struct art *arts;
+	int trt_count;
+	struct trt *trts;
+	u8 uuid_bitmap;
+	int rel_misc_dev_res;
+	int current_uuid_index;
+};
+
+static ssize_t available_uuids_show(struct device *dev,
+				    struct device_attribute *attr,
+				    char *buf)
+{
+	struct int3400_thermal_priv *priv = dev_get_drvdata(dev);
+	int i;
+	int length = 0;
+
+	for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; i++) {
+		if (priv->uuid_bitmap & (1 << i))
+			if (PAGE_SIZE - length > 0)
+				length += snprintf(&buf[length],
+						   PAGE_SIZE - length,
+						   "%s\n",
+						   int3400_thermal_uuids[i]);
+	}
+
+	return length;
+}
+
+static ssize_t current_uuid_show(struct device *dev,
+				 struct device_attribute *devattr, char *buf)
+{
+	struct int3400_thermal_priv *priv = dev_get_drvdata(dev);
+
+	if (priv->uuid_bitmap & (1 << priv->current_uuid_index))
+		return sprintf(buf, "%s\n",
+			       int3400_thermal_uuids[priv->current_uuid_index]);
+	else
+		return sprintf(buf, "INVALID\n");
+}
+
+static ssize_t current_uuid_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct int3400_thermal_priv *priv = dev_get_drvdata(dev);
+	int i;
+
+	for (i = 0; i < INT3400_THERMAL_MAXIMUM_UUID; ++i) {
+		if ((priv->uuid_bitmap & (1 << i)) &&
+		    !(strncmp(buf, int3400_thermal_uuids[i],
+			      sizeof(int3400_thermal_uuids[i]) - 1))) {
+			priv->current_uuid_index = i;
+			return count;
+		}
+	}
+
+	return -EINVAL;
+}
+
+static DEVICE_ATTR_RW(current_uuid);
+static DEVICE_ATTR_RO(available_uuids);
+static struct attribute *uuid_attrs[] = {
+	&dev_attr_available_uuids.attr,
+	&dev_attr_current_uuid.attr,
+	NULL
+};
+
+static const struct attribute_group uuid_attribute_group = {
+	.attrs = uuid_attrs,
+	.name = "uuids"
+};
+
+static int int3400_thermal_get_uuids(struct int3400_thermal_priv *priv)
+{
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL};
+	union acpi_object *obja, *objb;
+	int i, j;
+	int result = 0;
+	acpi_status status;
+
+	status = acpi_evaluate_object(priv->adev->handle, "IDSP", NULL, &buf);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	obja = (union acpi_object *)buf.pointer;
+	if (obja->type != ACPI_TYPE_PACKAGE) {
+		result = -EINVAL;
+		goto end;
+	}
+
+	for (i = 0; i < obja->package.count; i++) {
+		objb = &obja->package.elements[i];
+		if (objb->type != ACPI_TYPE_BUFFER) {
+			result = -EINVAL;
+			goto end;
+		}
+
+		/* UUID must be 16 bytes */
+		if (objb->buffer.length != 16) {
+			result = -EINVAL;
+			goto end;
+		}
+
+		for (j = 0; j < INT3400_THERMAL_MAXIMUM_UUID; j++) {
+			guid_t guid;
+
+			guid_parse(int3400_thermal_uuids[j], &guid);
+			if (guid_equal((guid_t *)objb->buffer.pointer, &guid)) {
+				priv->uuid_bitmap |= (1 << j);
+				break;
+			}
+		}
+	}
+
+end:
+	kfree(buf.pointer);
+	return result;
+}
+
+static int int3400_thermal_run_osc(acpi_handle handle,
+				enum int3400_thermal_uuid uuid, bool enable)
+{
+	u32 ret, buf[2];
+	acpi_status status;
+	int result = 0;
+	struct acpi_osc_context context = {
+		.uuid_str = int3400_thermal_uuids[uuid],
+		.rev = 1,
+		.cap.length = 8,
+	};
+
+	buf[OSC_QUERY_DWORD] = 0;
+	buf[OSC_SUPPORT_DWORD] = enable;
+
+	context.cap.pointer = buf;
+
+	status = acpi_run_osc(handle, &context);
+	if (ACPI_SUCCESS(status)) {
+		ret = *((u32 *)(context.ret.pointer + 4));
+		if (ret != enable)
+			result = -EPERM;
+	} else
+		result = -EPERM;
+
+	kfree(context.ret.pointer);
+	return result;
+}
+
+static void int3400_notify(acpi_handle handle,
+			u32 event,
+			void *data)
+{
+	struct int3400_thermal_priv *priv = data;
+	char *thermal_prop[5];
+
+	if (!priv)
+		return;
+
+	switch (event) {
+	case INT3400_THERMAL_TABLE_CHANGED:
+		thermal_prop[0] = kasprintf(GFP_KERNEL, "NAME=%s",
+				priv->thermal->type);
+		thermal_prop[1] = kasprintf(GFP_KERNEL, "TEMP=%d",
+				priv->thermal->temperature);
+		thermal_prop[2] = kasprintf(GFP_KERNEL, "TRIP=");
+		thermal_prop[3] = kasprintf(GFP_KERNEL, "EVENT=%d",
+				THERMAL_TABLE_CHANGED);
+		thermal_prop[4] = NULL;
+		kobject_uevent_env(&priv->thermal->device.kobj, KOBJ_CHANGE,
+				thermal_prop);
+		break;
+	default:
+		/* Ignore unknown notification codes sent to INT3400 device */
+		break;
+	}
+}
+
+static int int3400_thermal_get_temp(struct thermal_zone_device *thermal,
+			int *temp)
+{
+	*temp = 20 * 1000; /* faked temp sensor with 20C */
+	return 0;
+}
+
+static int int3400_thermal_get_mode(struct thermal_zone_device *thermal,
+				enum thermal_device_mode *mode)
+{
+	struct int3400_thermal_priv *priv = thermal->devdata;
+
+	if (!priv)
+		return -EINVAL;
+
+	*mode = priv->mode;
+
+	return 0;
+}
+
+static int int3400_thermal_set_mode(struct thermal_zone_device *thermal,
+				enum thermal_device_mode mode)
+{
+	struct int3400_thermal_priv *priv = thermal->devdata;
+	bool enable;
+	int result = 0;
+
+	if (!priv)
+		return -EINVAL;
+
+	if (mode == THERMAL_DEVICE_ENABLED)
+		enable = true;
+	else if (mode == THERMAL_DEVICE_DISABLED)
+		enable = false;
+	else
+		return -EINVAL;
+
+	if (enable != priv->mode) {
+		priv->mode = enable;
+		result = int3400_thermal_run_osc(priv->adev->handle,
+						 priv->current_uuid_index,
+						 enable);
+	}
+	return result;
+}
+
+static struct thermal_zone_device_ops int3400_thermal_ops = {
+	.get_temp = int3400_thermal_get_temp,
+};
+
+static struct thermal_zone_params int3400_thermal_params = {
+	.governor_name = "user_space",
+	.no_hwmon = true,
+};
+
+static int int3400_thermal_probe(struct platform_device *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	struct int3400_thermal_priv *priv;
+	int result;
+
+	if (!adev)
+		return -ENODEV;
+
+	priv = kzalloc(sizeof(struct int3400_thermal_priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->adev = adev;
+
+	result = int3400_thermal_get_uuids(priv);
+	if (result)
+		goto free_priv;
+
+	result = acpi_parse_art(priv->adev->handle, &priv->art_count,
+				&priv->arts, true);
+	if (result)
+		dev_dbg(&pdev->dev, "_ART table parsing error\n");
+
+	result = acpi_parse_trt(priv->adev->handle, &priv->trt_count,
+				&priv->trts, true);
+	if (result)
+		dev_dbg(&pdev->dev, "_TRT table parsing error\n");
+
+	platform_set_drvdata(pdev, priv);
+
+	if (priv->uuid_bitmap & 1 << INT3400_THERMAL_PASSIVE_1) {
+		int3400_thermal_ops.get_mode = int3400_thermal_get_mode;
+		int3400_thermal_ops.set_mode = int3400_thermal_set_mode;
+	}
+	priv->thermal = thermal_zone_device_register("INT3400 Thermal", 0, 0,
+						priv, &int3400_thermal_ops,
+						&int3400_thermal_params, 0, 0);
+	if (IS_ERR(priv->thermal)) {
+		result = PTR_ERR(priv->thermal);
+		goto free_art_trt;
+	}
+
+	priv->rel_misc_dev_res = acpi_thermal_rel_misc_device_add(
+							priv->adev->handle);
+
+	result = sysfs_create_group(&pdev->dev.kobj, &uuid_attribute_group);
+	if (result)
+		goto free_rel_misc;
+
+	result = acpi_install_notify_handler(
+			priv->adev->handle, ACPI_DEVICE_NOTIFY, int3400_notify,
+			(void *)priv);
+	if (result)
+		goto free_sysfs;
+
+	return 0;
+
+free_sysfs:
+	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
+free_rel_misc:
+	if (!priv->rel_misc_dev_res)
+		acpi_thermal_rel_misc_device_remove(priv->adev->handle);
+	thermal_zone_device_unregister(priv->thermal);
+free_art_trt:
+	kfree(priv->trts);
+	kfree(priv->arts);
+free_priv:
+	kfree(priv);
+	return result;
+}
+
+static int int3400_thermal_remove(struct platform_device *pdev)
+{
+	struct int3400_thermal_priv *priv = platform_get_drvdata(pdev);
+
+	acpi_remove_notify_handler(
+			priv->adev->handle, ACPI_DEVICE_NOTIFY,
+			int3400_notify);
+
+	if (!priv->rel_misc_dev_res)
+		acpi_thermal_rel_misc_device_remove(priv->adev->handle);
+
+	sysfs_remove_group(&pdev->dev.kobj, &uuid_attribute_group);
+	thermal_zone_device_unregister(priv->thermal);
+	kfree(priv->trts);
+	kfree(priv->arts);
+	kfree(priv);
+	return 0;
+}
+
+static const struct acpi_device_id int3400_thermal_match[] = {
+	{"INT3400", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(acpi, int3400_thermal_match);
+
+static struct platform_driver int3400_thermal_driver = {
+	.probe = int3400_thermal_probe,
+	.remove = int3400_thermal_remove,
+	.driver = {
+		   .name = "int3400 thermal",
+		   .acpi_match_table = ACPI_PTR(int3400_thermal_match),
+		   },
+};
+
+module_platform_driver(int3400_thermal_driver);
+
+MODULE_DESCRIPTION("INT3400 Thermal driver");
+MODULE_AUTHOR("Zhang Rui <rui.zhang@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/intel/int340x_thermal/int3402_thermal.c b/drivers/thermal/intel/int340x_thermal/int3402_thermal.c
new file mode 100644
index 000000000000..8e90b3151a42
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/int3402_thermal.c
@@ -0,0 +1,108 @@
+/*
+ * INT3402 thermal driver for memory temperature reporting
+ *
+ * Copyright (C) 2014, Intel Corporation
+ * Authors: Aaron Lu <aaron.lu@intel.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.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include <linux/thermal.h>
+#include "int340x_thermal_zone.h"
+
+#define INT3402_PERF_CHANGED_EVENT	0x80
+#define INT3402_THERMAL_EVENT		0x90
+
+struct int3402_thermal_data {
+	acpi_handle *handle;
+	struct int34x_thermal_zone *int340x_zone;
+};
+
+static void int3402_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct int3402_thermal_data *priv = data;
+
+	if (!priv)
+		return;
+
+	switch (event) {
+	case INT3402_PERF_CHANGED_EVENT:
+		break;
+	case INT3402_THERMAL_EVENT:
+		int340x_thermal_zone_device_update(priv->int340x_zone,
+						   THERMAL_TRIP_VIOLATED);
+		break;
+	default:
+		break;
+	}
+}
+
+static int int3402_thermal_probe(struct platform_device *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	struct int3402_thermal_data *d;
+	int ret;
+
+	if (!acpi_has_method(adev->handle, "_TMP"))
+		return -ENODEV;
+
+	d = devm_kzalloc(&pdev->dev, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+
+	d->int340x_zone = int340x_thermal_zone_add(adev, NULL);
+	if (IS_ERR(d->int340x_zone))
+		return PTR_ERR(d->int340x_zone);
+
+	ret = acpi_install_notify_handler(adev->handle,
+					  ACPI_DEVICE_NOTIFY,
+					  int3402_notify,
+					  d);
+	if (ret) {
+		int340x_thermal_zone_remove(d->int340x_zone);
+		return ret;
+	}
+
+	d->handle = adev->handle;
+	platform_set_drvdata(pdev, d);
+
+	return 0;
+}
+
+static int int3402_thermal_remove(struct platform_device *pdev)
+{
+	struct int3402_thermal_data *d = platform_get_drvdata(pdev);
+
+	acpi_remove_notify_handler(d->handle,
+				   ACPI_DEVICE_NOTIFY, int3402_notify);
+	int340x_thermal_zone_remove(d->int340x_zone);
+
+	return 0;
+}
+
+static const struct acpi_device_id int3402_thermal_match[] = {
+	{"INT3402", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(acpi, int3402_thermal_match);
+
+static struct platform_driver int3402_thermal_driver = {
+	.probe = int3402_thermal_probe,
+	.remove = int3402_thermal_remove,
+	.driver = {
+		   .name = "int3402 thermal",
+		   .acpi_match_table = int3402_thermal_match,
+		   },
+};
+
+module_platform_driver(int3402_thermal_driver);
+
+MODULE_DESCRIPTION("INT3402 Thermal driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/thermal/intel/int340x_thermal/int3403_thermal.c b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
new file mode 100644
index 000000000000..0c19fcd56a0d
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/int3403_thermal.c
@@ -0,0 +1,311 @@
+/*
+ * ACPI INT3403 thermal driver
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/acpi.h>
+#include <linux/thermal.h>
+#include <linux/platform_device.h>
+#include "int340x_thermal_zone.h"
+
+#define INT3403_TYPE_SENSOR		0x03
+#define INT3403_TYPE_CHARGER		0x0B
+#define INT3403_TYPE_BATTERY		0x0C
+#define INT3403_PERF_CHANGED_EVENT	0x80
+#define INT3403_PERF_TRIP_POINT_CHANGED	0x81
+#define INT3403_THERMAL_EVENT		0x90
+
+/* Preserved structure for future expandbility */
+struct int3403_sensor {
+	struct int34x_thermal_zone *int340x_zone;
+};
+
+struct int3403_performance_state {
+	u64 performance;
+	u64 power;
+	u64 latency;
+	u64 linear;
+	u64 control;
+	u64 raw_performace;
+	char *raw_unit;
+	int reserved;
+};
+
+struct int3403_cdev {
+	struct thermal_cooling_device *cdev;
+	unsigned long max_state;
+};
+
+struct int3403_priv {
+	struct platform_device *pdev;
+	struct acpi_device *adev;
+	unsigned long long type;
+	void *priv;
+};
+
+static void int3403_notify(acpi_handle handle,
+		u32 event, void *data)
+{
+	struct int3403_priv *priv = data;
+	struct int3403_sensor *obj;
+
+	if (!priv)
+		return;
+
+	obj = priv->priv;
+	if (priv->type != INT3403_TYPE_SENSOR || !obj)
+		return;
+
+	switch (event) {
+	case INT3403_PERF_CHANGED_EVENT:
+		break;
+	case INT3403_THERMAL_EVENT:
+		int340x_thermal_zone_device_update(obj->int340x_zone,
+						   THERMAL_TRIP_VIOLATED);
+		break;
+	case INT3403_PERF_TRIP_POINT_CHANGED:
+		int340x_thermal_read_trips(obj->int340x_zone);
+		int340x_thermal_zone_device_update(obj->int340x_zone,
+						   THERMAL_TRIP_CHANGED);
+		break;
+	default:
+		dev_err(&priv->pdev->dev, "Unsupported event [0x%x]\n", event);
+		break;
+	}
+}
+
+static int int3403_sensor_add(struct int3403_priv *priv)
+{
+	int result = 0;
+	struct int3403_sensor *obj;
+
+	obj = devm_kzalloc(&priv->pdev->dev, sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+
+	priv->priv = obj;
+
+	obj->int340x_zone = int340x_thermal_zone_add(priv->adev, NULL);
+	if (IS_ERR(obj->int340x_zone))
+		return PTR_ERR(obj->int340x_zone);
+
+	result = acpi_install_notify_handler(priv->adev->handle,
+			ACPI_DEVICE_NOTIFY, int3403_notify,
+			(void *)priv);
+	if (result)
+		goto err_free_obj;
+
+	return 0;
+
+ err_free_obj:
+	int340x_thermal_zone_remove(obj->int340x_zone);
+	return result;
+}
+
+static int int3403_sensor_remove(struct int3403_priv *priv)
+{
+	struct int3403_sensor *obj = priv->priv;
+
+	acpi_remove_notify_handler(priv->adev->handle,
+				   ACPI_DEVICE_NOTIFY, int3403_notify);
+	int340x_thermal_zone_remove(obj->int340x_zone);
+
+	return 0;
+}
+
+/* INT3403 Cooling devices */
+static int int3403_get_max_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	struct int3403_priv *priv = cdev->devdata;
+	struct int3403_cdev *obj = priv->priv;
+
+	*state = obj->max_state;
+	return 0;
+}
+
+static int int3403_get_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	struct int3403_priv *priv = cdev->devdata;
+	unsigned long long level;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(priv->adev->handle, "PPPC", NULL, &level);
+	if (ACPI_SUCCESS(status)) {
+		*state = level;
+		return 0;
+	} else
+		return -EINVAL;
+}
+
+static int
+int3403_set_cur_state(struct thermal_cooling_device *cdev, unsigned long state)
+{
+	struct int3403_priv *priv = cdev->devdata;
+	acpi_status status;
+
+	status = acpi_execute_simple_method(priv->adev->handle, "SPPC", state);
+	if (ACPI_SUCCESS(status))
+		return 0;
+	else
+		return -EINVAL;
+}
+
+static const struct thermal_cooling_device_ops int3403_cooling_ops = {
+	.get_max_state = int3403_get_max_state,
+	.get_cur_state = int3403_get_cur_state,
+	.set_cur_state = int3403_set_cur_state,
+};
+
+static int int3403_cdev_add(struct int3403_priv *priv)
+{
+	int result = 0;
+	acpi_status status;
+	struct int3403_cdev *obj;
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *p;
+
+	obj = devm_kzalloc(&priv->pdev->dev, sizeof(*obj), GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+
+	status = acpi_evaluate_object(priv->adev->handle, "PPSS", NULL, &buf);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	p = buf.pointer;
+	if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
+		printk(KERN_WARNING "Invalid PPSS data\n");
+		kfree(buf.pointer);
+		return -EFAULT;
+	}
+
+	priv->priv = obj;
+	obj->max_state = p->package.count - 1;
+	obj->cdev =
+		thermal_cooling_device_register(acpi_device_bid(priv->adev),
+				priv, &int3403_cooling_ops);
+	if (IS_ERR(obj->cdev))
+		result = PTR_ERR(obj->cdev);
+
+	kfree(buf.pointer);
+	/* TODO: add ACPI notification support */
+
+	return result;
+}
+
+static int int3403_cdev_remove(struct int3403_priv *priv)
+{
+	struct int3403_cdev *obj = priv->priv;
+
+	thermal_cooling_device_unregister(obj->cdev);
+	return 0;
+}
+
+static int int3403_add(struct platform_device *pdev)
+{
+	struct int3403_priv *priv;
+	int result = 0;
+	acpi_status status;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(struct int3403_priv),
+			    GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->pdev = pdev;
+	priv->adev = ACPI_COMPANION(&(pdev->dev));
+	if (!priv->adev) {
+		result = -EINVAL;
+		goto err;
+	}
+
+	status = acpi_evaluate_integer(priv->adev->handle, "PTYP",
+				       NULL, &priv->type);
+	if (ACPI_FAILURE(status)) {
+		unsigned long long tmp;
+
+		status = acpi_evaluate_integer(priv->adev->handle, "_TMP",
+					       NULL, &tmp);
+		if (ACPI_FAILURE(status)) {
+			result = -EINVAL;
+			goto err;
+		} else {
+			priv->type = INT3403_TYPE_SENSOR;
+		}
+	}
+
+	platform_set_drvdata(pdev, priv);
+	switch (priv->type) {
+	case INT3403_TYPE_SENSOR:
+		result = int3403_sensor_add(priv);
+		break;
+	case INT3403_TYPE_CHARGER:
+	case INT3403_TYPE_BATTERY:
+		result = int3403_cdev_add(priv);
+		break;
+	default:
+		result = -EINVAL;
+	}
+
+	if (result)
+		goto err;
+	return result;
+
+err:
+	return result;
+}
+
+static int int3403_remove(struct platform_device *pdev)
+{
+	struct int3403_priv *priv = platform_get_drvdata(pdev);
+
+	switch (priv->type) {
+	case INT3403_TYPE_SENSOR:
+		int3403_sensor_remove(priv);
+		break;
+	case INT3403_TYPE_CHARGER:
+	case INT3403_TYPE_BATTERY:
+		int3403_cdev_remove(priv);
+		break;
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static const struct acpi_device_id int3403_device_ids[] = {
+	{"INT3403", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, int3403_device_ids);
+
+static struct platform_driver int3403_driver = {
+	.probe = int3403_add,
+	.remove = int3403_remove,
+	.driver = {
+		.name = "int3403 thermal",
+		.acpi_match_table = int3403_device_ids,
+	},
+};
+
+module_platform_driver(int3403_driver);
+
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("ACPI INT3403 thermal driver");
diff --git a/drivers/thermal/intel/int340x_thermal/int3406_thermal.c b/drivers/thermal/intel/int340x_thermal/int3406_thermal.c
new file mode 100644
index 000000000000..f69ab026ba24
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/int3406_thermal.c
@@ -0,0 +1,213 @@
+/*
+ * INT3406 thermal driver for display participant device
+ *
+ * Copyright (C) 2016, Intel Corporation
+ * Authors: Aaron Lu <aaron.lu@intel.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.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include <linux/backlight.h>
+#include <linux/thermal.h>
+#include <acpi/video.h>
+
+#define INT3406_BRIGHTNESS_LIMITS_CHANGED	0x80
+
+struct int3406_thermal_data {
+	int upper_limit;
+	int lower_limit;
+	acpi_handle handle;
+	struct acpi_video_device_brightness *br;
+	struct backlight_device *raw_bd;
+	struct thermal_cooling_device *cooling_dev;
+};
+
+/*
+ * According to the ACPI spec,
+ * "Each brightness level is represented by a number between 0 and 100,
+ * and can be thought of as a percentage. For example, 50 can be 50%
+ * power consumption or 50% brightness, as defined by the OEM."
+ *
+ * As int3406 device uses this value to communicate with the native
+ * graphics driver, we make the assumption that it represents
+ * the percentage of brightness only
+ */
+#define ACPI_TO_RAW(v, d) (d->raw_bd->props.max_brightness * v / 100)
+#define RAW_TO_ACPI(v, d) (v * 100 / d->raw_bd->props.max_brightness)
+
+static int
+int3406_thermal_get_max_state(struct thermal_cooling_device *cooling_dev,
+			      unsigned long *state)
+{
+	struct int3406_thermal_data *d = cooling_dev->devdata;
+
+	*state = d->upper_limit - d->lower_limit;
+	return 0;
+}
+
+static int
+int3406_thermal_set_cur_state(struct thermal_cooling_device *cooling_dev,
+			      unsigned long state)
+{
+	struct int3406_thermal_data *d = cooling_dev->devdata;
+	int acpi_level, raw_level;
+
+	if (state > d->upper_limit - d->lower_limit)
+		return -EINVAL;
+
+	acpi_level = d->br->levels[d->upper_limit - state];
+
+	raw_level = ACPI_TO_RAW(acpi_level, d);
+
+	return backlight_device_set_brightness(d->raw_bd, raw_level);
+}
+
+static int
+int3406_thermal_get_cur_state(struct thermal_cooling_device *cooling_dev,
+			      unsigned long *state)
+{
+	struct int3406_thermal_data *d = cooling_dev->devdata;
+	int acpi_level;
+	int index;
+
+	acpi_level = RAW_TO_ACPI(d->raw_bd->props.brightness, d);
+
+	/*
+	 * There is no 1:1 mapping between the firmware interface level
+	 * with the raw interface level, we will have to find one that is
+	 * right above it.
+	 */
+	for (index = d->lower_limit; index < d->upper_limit; index++) {
+		if (acpi_level <= d->br->levels[index])
+			break;
+	}
+
+	*state = d->upper_limit - index;
+	return 0;
+}
+
+static const struct thermal_cooling_device_ops video_cooling_ops = {
+	.get_max_state = int3406_thermal_get_max_state,
+	.get_cur_state = int3406_thermal_get_cur_state,
+	.set_cur_state = int3406_thermal_set_cur_state,
+};
+
+static int int3406_thermal_get_index(int *array, int nr, int value)
+{
+	int i;
+
+	for (i = 2; i < nr; i++) {
+		if (array[i] == value)
+			break;
+	}
+	return i == nr ? -ENOENT : i;
+}
+
+static void int3406_thermal_get_limit(struct int3406_thermal_data *d)
+{
+	acpi_status status;
+	unsigned long long lower_limit, upper_limit;
+
+	status = acpi_evaluate_integer(d->handle, "DDDL", NULL, &lower_limit);
+	if (ACPI_SUCCESS(status))
+		d->lower_limit = int3406_thermal_get_index(d->br->levels,
+					d->br->count, lower_limit);
+
+	status = acpi_evaluate_integer(d->handle, "DDPC", NULL, &upper_limit);
+	if (ACPI_SUCCESS(status))
+		d->upper_limit = int3406_thermal_get_index(d->br->levels,
+					d->br->count, upper_limit);
+
+	/* lower_limit and upper_limit should be always set */
+	d->lower_limit = d->lower_limit > 0 ? d->lower_limit : 2;
+	d->upper_limit = d->upper_limit > 0 ? d->upper_limit : d->br->count - 1;
+}
+
+static void int3406_notify(acpi_handle handle, u32 event, void *data)
+{
+	if (event == INT3406_BRIGHTNESS_LIMITS_CHANGED)
+		int3406_thermal_get_limit(data);
+}
+
+static int int3406_thermal_probe(struct platform_device *pdev)
+{
+	struct acpi_device *adev = ACPI_COMPANION(&pdev->dev);
+	struct int3406_thermal_data *d;
+	struct backlight_device *bd;
+	int ret;
+
+	if (!ACPI_HANDLE(&pdev->dev))
+		return -ENODEV;
+
+	d = devm_kzalloc(&pdev->dev, sizeof(*d), GFP_KERNEL);
+	if (!d)
+		return -ENOMEM;
+	d->handle = ACPI_HANDLE(&pdev->dev);
+
+	bd = backlight_device_get_by_type(BACKLIGHT_RAW);
+	if (!bd)
+		return -ENODEV;
+	d->raw_bd = bd;
+
+	ret = acpi_video_get_levels(ACPI_COMPANION(&pdev->dev), &d->br, NULL);
+	if (ret)
+		return ret;
+
+	int3406_thermal_get_limit(d);
+
+	d->cooling_dev = thermal_cooling_device_register(acpi_device_bid(adev),
+							 d, &video_cooling_ops);
+	if (IS_ERR(d->cooling_dev))
+		goto err;
+
+	ret = acpi_install_notify_handler(adev->handle, ACPI_DEVICE_NOTIFY,
+					  int3406_notify, d);
+	if (ret)
+		goto err_cdev;
+
+	platform_set_drvdata(pdev, d);
+
+	return 0;
+
+err_cdev:
+	thermal_cooling_device_unregister(d->cooling_dev);
+err:
+	kfree(d->br);
+	return -ENODEV;
+}
+
+static int int3406_thermal_remove(struct platform_device *pdev)
+{
+	struct int3406_thermal_data *d = platform_get_drvdata(pdev);
+
+	thermal_cooling_device_unregister(d->cooling_dev);
+	kfree(d->br);
+	return 0;
+}
+
+static const struct acpi_device_id int3406_thermal_match[] = {
+	{"INT3406", 0},
+	{}
+};
+
+MODULE_DEVICE_TABLE(acpi, int3406_thermal_match);
+
+static struct platform_driver int3406_thermal_driver = {
+	.probe = int3406_thermal_probe,
+	.remove = int3406_thermal_remove,
+	.driver = {
+		   .name = "int3406 thermal",
+		   .acpi_match_table = int3406_thermal_match,
+		   },
+};
+
+module_platform_driver(int3406_thermal_driver);
+
+MODULE_DESCRIPTION("INT3406 Thermal driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
new file mode 100644
index 000000000000..9ec27ac1856b
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.c
@@ -0,0 +1,295 @@
+/*
+ * int340x_thermal_zone.c
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/acpi.h>
+#include <linux/thermal.h>
+#include "int340x_thermal_zone.h"
+
+static int int340x_thermal_get_zone_temp(struct thermal_zone_device *zone,
+					 int *temp)
+{
+	struct int34x_thermal_zone *d = zone->devdata;
+	unsigned long long tmp;
+	acpi_status status;
+
+	if (d->override_ops && d->override_ops->get_temp)
+		return d->override_ops->get_temp(zone, temp);
+
+	status = acpi_evaluate_integer(d->adev->handle, "_TMP", NULL, &tmp);
+	if (ACPI_FAILURE(status))
+		return -EIO;
+
+	if (d->lpat_table) {
+		int conv_temp;
+
+		conv_temp = acpi_lpat_raw_to_temp(d->lpat_table, (int)tmp);
+		if (conv_temp < 0)
+			return conv_temp;
+
+		*temp = (unsigned long)conv_temp * 10;
+	} else
+		/* _TMP returns the temperature in tenths of degrees Kelvin */
+		*temp = DECI_KELVIN_TO_MILLICELSIUS(tmp);
+
+	return 0;
+}
+
+static int int340x_thermal_get_trip_temp(struct thermal_zone_device *zone,
+					 int trip, int *temp)
+{
+	struct int34x_thermal_zone *d = zone->devdata;
+	int i;
+
+	if (d->override_ops && d->override_ops->get_trip_temp)
+		return d->override_ops->get_trip_temp(zone, trip, temp);
+
+	if (trip < d->aux_trip_nr)
+		*temp = d->aux_trips[trip];
+	else if (trip == d->crt_trip_id)
+		*temp = d->crt_temp;
+	else if (trip == d->psv_trip_id)
+		*temp = d->psv_temp;
+	else if (trip == d->hot_trip_id)
+		*temp = d->hot_temp;
+	else {
+		for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) {
+			if (d->act_trips[i].valid &&
+			    d->act_trips[i].id == trip) {
+				*temp = d->act_trips[i].temp;
+				break;
+			}
+		}
+		if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int int340x_thermal_get_trip_type(struct thermal_zone_device *zone,
+					 int trip,
+					 enum thermal_trip_type *type)
+{
+	struct int34x_thermal_zone *d = zone->devdata;
+	int i;
+
+	if (d->override_ops && d->override_ops->get_trip_type)
+		return d->override_ops->get_trip_type(zone, trip, type);
+
+	if (trip < d->aux_trip_nr)
+		*type = THERMAL_TRIP_PASSIVE;
+	else if (trip == d->crt_trip_id)
+		*type = THERMAL_TRIP_CRITICAL;
+	else if (trip == d->hot_trip_id)
+		*type = THERMAL_TRIP_HOT;
+	else if (trip == d->psv_trip_id)
+		*type = THERMAL_TRIP_PASSIVE;
+	else {
+		for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) {
+			if (d->act_trips[i].valid &&
+			    d->act_trips[i].id == trip) {
+				*type = THERMAL_TRIP_ACTIVE;
+				break;
+			}
+		}
+		if (i == INT340X_THERMAL_MAX_ACT_TRIP_COUNT)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int int340x_thermal_set_trip_temp(struct thermal_zone_device *zone,
+				      int trip, int temp)
+{
+	struct int34x_thermal_zone *d = zone->devdata;
+	acpi_status status;
+	char name[10];
+
+	if (d->override_ops && d->override_ops->set_trip_temp)
+		return d->override_ops->set_trip_temp(zone, trip, temp);
+
+	snprintf(name, sizeof(name), "PAT%d", trip);
+	status = acpi_execute_simple_method(d->adev->handle, name,
+			MILLICELSIUS_TO_DECI_KELVIN(temp));
+	if (ACPI_FAILURE(status))
+		return -EIO;
+
+	d->aux_trips[trip] = temp;
+
+	return 0;
+}
+
+
+static int int340x_thermal_get_trip_hyst(struct thermal_zone_device *zone,
+		int trip, int *temp)
+{
+	struct int34x_thermal_zone *d = zone->devdata;
+	acpi_status status;
+	unsigned long long hyst;
+
+	if (d->override_ops && d->override_ops->get_trip_hyst)
+		return d->override_ops->get_trip_hyst(zone, trip, temp);
+
+	status = acpi_evaluate_integer(d->adev->handle, "GTSH", NULL, &hyst);
+	if (ACPI_FAILURE(status))
+		*temp = 0;
+	else
+		*temp = hyst * 100;
+
+	return 0;
+}
+
+static struct thermal_zone_device_ops int340x_thermal_zone_ops = {
+	.get_temp       = int340x_thermal_get_zone_temp,
+	.get_trip_temp	= int340x_thermal_get_trip_temp,
+	.get_trip_type	= int340x_thermal_get_trip_type,
+	.set_trip_temp	= int340x_thermal_set_trip_temp,
+	.get_trip_hyst =  int340x_thermal_get_trip_hyst,
+};
+
+static int int340x_thermal_get_trip_config(acpi_handle handle, char *name,
+				      int *temp)
+{
+	unsigned long long r;
+	acpi_status status;
+
+	status = acpi_evaluate_integer(handle, name, NULL, &r);
+	if (ACPI_FAILURE(status))
+		return -EIO;
+
+	*temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+
+	return 0;
+}
+
+int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone)
+{
+	int trip_cnt = int34x_zone->aux_trip_nr;
+	int i;
+
+	int34x_zone->crt_trip_id = -1;
+	if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_CRT",
+					     &int34x_zone->crt_temp))
+		int34x_zone->crt_trip_id = trip_cnt++;
+
+	int34x_zone->hot_trip_id = -1;
+	if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_HOT",
+					     &int34x_zone->hot_temp))
+		int34x_zone->hot_trip_id = trip_cnt++;
+
+	int34x_zone->psv_trip_id = -1;
+	if (!int340x_thermal_get_trip_config(int34x_zone->adev->handle, "_PSV",
+					     &int34x_zone->psv_temp))
+		int34x_zone->psv_trip_id = trip_cnt++;
+
+	for (i = 0; i < INT340X_THERMAL_MAX_ACT_TRIP_COUNT; i++) {
+		char name[5] = { '_', 'A', 'C', '0' + i, '\0' };
+
+		if (int340x_thermal_get_trip_config(int34x_zone->adev->handle,
+					name,
+					&int34x_zone->act_trips[i].temp))
+			break;
+
+		int34x_zone->act_trips[i].id = trip_cnt++;
+		int34x_zone->act_trips[i].valid = true;
+	}
+
+	return trip_cnt;
+}
+EXPORT_SYMBOL_GPL(int340x_thermal_read_trips);
+
+static struct thermal_zone_params int340x_thermal_params = {
+	.governor_name = "user_space",
+	.no_hwmon = true,
+};
+
+struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *adev,
+				struct thermal_zone_device_ops *override_ops)
+{
+	struct int34x_thermal_zone *int34x_thermal_zone;
+	acpi_status status;
+	unsigned long long trip_cnt;
+	int trip_mask = 0;
+	int ret;
+
+	int34x_thermal_zone = kzalloc(sizeof(*int34x_thermal_zone),
+				      GFP_KERNEL);
+	if (!int34x_thermal_zone)
+		return ERR_PTR(-ENOMEM);
+
+	int34x_thermal_zone->adev = adev;
+	int34x_thermal_zone->override_ops = override_ops;
+
+	status = acpi_evaluate_integer(adev->handle, "PATC", NULL, &trip_cnt);
+	if (ACPI_FAILURE(status))
+		trip_cnt = 0;
+	else {
+		int34x_thermal_zone->aux_trips =
+			kcalloc(trip_cnt,
+				sizeof(*int34x_thermal_zone->aux_trips),
+				GFP_KERNEL);
+		if (!int34x_thermal_zone->aux_trips) {
+			ret = -ENOMEM;
+			goto err_trip_alloc;
+		}
+		trip_mask = BIT(trip_cnt) - 1;
+		int34x_thermal_zone->aux_trip_nr = trip_cnt;
+	}
+
+	trip_cnt = int340x_thermal_read_trips(int34x_thermal_zone);
+
+	int34x_thermal_zone->lpat_table = acpi_lpat_get_conversion_table(
+								adev->handle);
+
+	int34x_thermal_zone->zone = thermal_zone_device_register(
+						acpi_device_bid(adev),
+						trip_cnt,
+						trip_mask, int34x_thermal_zone,
+						&int340x_thermal_zone_ops,
+						&int340x_thermal_params,
+						0, 0);
+	if (IS_ERR(int34x_thermal_zone->zone)) {
+		ret = PTR_ERR(int34x_thermal_zone->zone);
+		goto err_thermal_zone;
+	}
+
+	return int34x_thermal_zone;
+
+err_thermal_zone:
+	acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
+	kfree(int34x_thermal_zone->aux_trips);
+err_trip_alloc:
+	kfree(int34x_thermal_zone);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(int340x_thermal_zone_add);
+
+void int340x_thermal_zone_remove(struct int34x_thermal_zone
+				 *int34x_thermal_zone)
+{
+	thermal_zone_device_unregister(int34x_thermal_zone->zone);
+	acpi_lpat_free_conversion_table(int34x_thermal_zone->lpat_table);
+	kfree(int34x_thermal_zone->aux_trips);
+	kfree(int34x_thermal_zone);
+}
+EXPORT_SYMBOL_GPL(int340x_thermal_zone_remove);
+
+MODULE_AUTHOR("Aaron Lu <aaron.lu@intel.com>");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Intel INT340x common thermal zone handler");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h
new file mode 100644
index 000000000000..5f3ba4775c5c
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/int340x_thermal_zone.h
@@ -0,0 +1,70 @@
+/*
+ * int340x_thermal_zone.h
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+
+#ifndef __INT340X_THERMAL_ZONE_H__
+#define __INT340X_THERMAL_ZONE_H__
+
+#include <acpi/acpi_lpat.h>
+
+#define INT340X_THERMAL_MAX_ACT_TRIP_COUNT	10
+
+struct active_trip {
+	int temp;
+	int id;
+	bool valid;
+};
+
+struct int34x_thermal_zone {
+	struct acpi_device *adev;
+	struct active_trip act_trips[INT340X_THERMAL_MAX_ACT_TRIP_COUNT];
+	unsigned long *aux_trips;
+	int aux_trip_nr;
+	int psv_temp;
+	int psv_trip_id;
+	int crt_temp;
+	int crt_trip_id;
+	int hot_temp;
+	int hot_trip_id;
+	struct thermal_zone_device *zone;
+	struct thermal_zone_device_ops *override_ops;
+	void *priv_data;
+	struct acpi_lpat_conversion_table *lpat_table;
+};
+
+struct int34x_thermal_zone *int340x_thermal_zone_add(struct acpi_device *,
+				struct thermal_zone_device_ops *override_ops);
+void int340x_thermal_zone_remove(struct int34x_thermal_zone *);
+int int340x_thermal_read_trips(struct int34x_thermal_zone *int34x_zone);
+
+static inline void int340x_thermal_zone_set_priv_data(
+			struct int34x_thermal_zone *tzone, void *priv_data)
+{
+	tzone->priv_data = priv_data;
+}
+
+static inline void *int340x_thermal_zone_get_priv_data(
+			struct int34x_thermal_zone *tzone)
+{
+	return tzone->priv_data;
+}
+
+static inline void int340x_thermal_zone_device_update(
+					struct int34x_thermal_zone *tzone,
+					enum thermal_notify_event event)
+{
+	thermal_zone_device_update(tzone->zone, event);
+}
+
+#endif
diff --git a/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c
new file mode 100644
index 000000000000..284cf2c5a8fd
--- /dev/null
+++ b/drivers/thermal/intel/int340x_thermal/processor_thermal_device.c
@@ -0,0 +1,525 @@
+/*
+ * processor_thermal_device.c
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/interrupt.h>
+#include <linux/platform_device.h>
+#include <linux/acpi.h>
+#include <linux/thermal.h>
+#include "int340x_thermal_zone.h"
+#include "../intel_soc_dts_iosf.h"
+
+/* Broadwell-U/HSB thermal reporting device */
+#define PCI_DEVICE_ID_PROC_BDW_THERMAL	0x1603
+#define PCI_DEVICE_ID_PROC_HSB_THERMAL	0x0A03
+
+/* Skylake thermal reporting device */
+#define PCI_DEVICE_ID_PROC_SKL_THERMAL	0x1903
+
+/* CannonLake thermal reporting device */
+#define PCI_DEVICE_ID_PROC_CNL_THERMAL	0x5a03
+#define PCI_DEVICE_ID_PROC_CFL_THERMAL	0x3E83
+
+/* Braswell thermal reporting device */
+#define PCI_DEVICE_ID_PROC_BSW_THERMAL	0x22DC
+
+/* Broxton thermal reporting device */
+#define PCI_DEVICE_ID_PROC_BXT0_THERMAL  0x0A8C
+#define PCI_DEVICE_ID_PROC_BXT1_THERMAL  0x1A8C
+#define PCI_DEVICE_ID_PROC_BXTX_THERMAL  0x4A8C
+#define PCI_DEVICE_ID_PROC_BXTP_THERMAL  0x5A8C
+
+/* GeminiLake thermal reporting device */
+#define PCI_DEVICE_ID_PROC_GLK_THERMAL	0x318C
+
+struct power_config {
+	u32	index;
+	u32	min_uw;
+	u32	max_uw;
+	u32	tmin_us;
+	u32	tmax_us;
+	u32	step_uw;
+};
+
+struct proc_thermal_device {
+	struct device *dev;
+	struct acpi_device *adev;
+	struct power_config power_limits[2];
+	struct int34x_thermal_zone *int340x_zone;
+	struct intel_soc_dts_sensors *soc_dts;
+};
+
+enum proc_thermal_emum_mode_type {
+	PROC_THERMAL_NONE,
+	PROC_THERMAL_PCI,
+	PROC_THERMAL_PLATFORM_DEV
+};
+
+/*
+ * We can have only one type of enumeration, PCI or Platform,
+ * not both. So we don't need instance specific data.
+ */
+static enum proc_thermal_emum_mode_type proc_thermal_emum_mode =
+							PROC_THERMAL_NONE;
+
+#define POWER_LIMIT_SHOW(index, suffix) \
+static ssize_t power_limit_##index##_##suffix##_show(struct device *dev, \
+					struct device_attribute *attr, \
+					char *buf) \
+{ \
+	struct pci_dev *pci_dev; \
+	struct platform_device *pdev; \
+	struct proc_thermal_device *proc_dev; \
+\
+	if (proc_thermal_emum_mode == PROC_THERMAL_PLATFORM_DEV) { \
+		pdev = to_platform_device(dev); \
+		proc_dev = platform_get_drvdata(pdev); \
+	} else { \
+		pci_dev = to_pci_dev(dev); \
+		proc_dev = pci_get_drvdata(pci_dev); \
+	} \
+	return sprintf(buf, "%lu\n",\
+	(unsigned long)proc_dev->power_limits[index].suffix * 1000); \
+}
+
+POWER_LIMIT_SHOW(0, min_uw)
+POWER_LIMIT_SHOW(0, max_uw)
+POWER_LIMIT_SHOW(0, step_uw)
+POWER_LIMIT_SHOW(0, tmin_us)
+POWER_LIMIT_SHOW(0, tmax_us)
+
+POWER_LIMIT_SHOW(1, min_uw)
+POWER_LIMIT_SHOW(1, max_uw)
+POWER_LIMIT_SHOW(1, step_uw)
+POWER_LIMIT_SHOW(1, tmin_us)
+POWER_LIMIT_SHOW(1, tmax_us)
+
+static DEVICE_ATTR_RO(power_limit_0_min_uw);
+static DEVICE_ATTR_RO(power_limit_0_max_uw);
+static DEVICE_ATTR_RO(power_limit_0_step_uw);
+static DEVICE_ATTR_RO(power_limit_0_tmin_us);
+static DEVICE_ATTR_RO(power_limit_0_tmax_us);
+
+static DEVICE_ATTR_RO(power_limit_1_min_uw);
+static DEVICE_ATTR_RO(power_limit_1_max_uw);
+static DEVICE_ATTR_RO(power_limit_1_step_uw);
+static DEVICE_ATTR_RO(power_limit_1_tmin_us);
+static DEVICE_ATTR_RO(power_limit_1_tmax_us);
+
+static struct attribute *power_limit_attrs[] = {
+	&dev_attr_power_limit_0_min_uw.attr,
+	&dev_attr_power_limit_1_min_uw.attr,
+	&dev_attr_power_limit_0_max_uw.attr,
+	&dev_attr_power_limit_1_max_uw.attr,
+	&dev_attr_power_limit_0_step_uw.attr,
+	&dev_attr_power_limit_1_step_uw.attr,
+	&dev_attr_power_limit_0_tmin_us.attr,
+	&dev_attr_power_limit_1_tmin_us.attr,
+	&dev_attr_power_limit_0_tmax_us.attr,
+	&dev_attr_power_limit_1_tmax_us.attr,
+	NULL
+};
+
+static const struct attribute_group power_limit_attribute_group = {
+	.attrs = power_limit_attrs,
+	.name = "power_limits"
+};
+
+static int stored_tjmax; /* since it is fixed, we can have local storage */
+
+static int get_tjmax(void)
+{
+	u32 eax, edx;
+	u32 val;
+	int err;
+
+	err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+	if (err)
+		return err;
+
+	val = (eax >> 16) & 0xff;
+	if (val)
+		return val;
+
+	return -EINVAL;
+}
+
+static int read_temp_msr(int *temp)
+{
+	int cpu;
+	u32 eax, edx;
+	int err;
+	unsigned long curr_temp_off = 0;
+
+	*temp = 0;
+
+	for_each_online_cpu(cpu) {
+		err = rdmsr_safe_on_cpu(cpu, MSR_IA32_THERM_STATUS, &eax,
+					&edx);
+		if (err)
+			goto err_ret;
+		else {
+			if (eax & 0x80000000) {
+				curr_temp_off = (eax >> 16) & 0x7f;
+				if (!*temp || curr_temp_off < *temp)
+					*temp = curr_temp_off;
+			} else {
+				err = -EINVAL;
+				goto err_ret;
+			}
+		}
+	}
+
+	return 0;
+err_ret:
+	return err;
+}
+
+static int proc_thermal_get_zone_temp(struct thermal_zone_device *zone,
+					 int *temp)
+{
+	int ret;
+
+	ret = read_temp_msr(temp);
+	if (!ret)
+		*temp = (stored_tjmax - *temp) * 1000;
+
+	return ret;
+}
+
+static struct thermal_zone_device_ops proc_thermal_local_ops = {
+	.get_temp       = proc_thermal_get_zone_temp,
+};
+
+static int proc_thermal_read_ppcc(struct proc_thermal_device *proc_priv)
+{
+	int i;
+	acpi_status status;
+	struct acpi_buffer buf = { ACPI_ALLOCATE_BUFFER, NULL };
+	union acpi_object *elements, *ppcc;
+	union acpi_object *p;
+	int ret = 0;
+
+	status = acpi_evaluate_object(proc_priv->adev->handle, "PPCC",
+				      NULL, &buf);
+	if (ACPI_FAILURE(status))
+		return -ENODEV;
+
+	p = buf.pointer;
+	if (!p || (p->type != ACPI_TYPE_PACKAGE)) {
+		dev_err(proc_priv->dev, "Invalid PPCC data\n");
+		ret = -EFAULT;
+		goto free_buffer;
+	}
+
+	if (!p->package.count) {
+		dev_err(proc_priv->dev, "Invalid PPCC package size\n");
+		ret = -EFAULT;
+		goto free_buffer;
+	}
+
+	for (i = 0; i < min((int)p->package.count - 1, 2); ++i) {
+		elements = &(p->package.elements[i+1]);
+		if (elements->type != ACPI_TYPE_PACKAGE ||
+		    elements->package.count != 6) {
+			ret = -EFAULT;
+			goto free_buffer;
+		}
+		ppcc = elements->package.elements;
+		proc_priv->power_limits[i].index = ppcc[0].integer.value;
+		proc_priv->power_limits[i].min_uw = ppcc[1].integer.value;
+		proc_priv->power_limits[i].max_uw = ppcc[2].integer.value;
+		proc_priv->power_limits[i].tmin_us = ppcc[3].integer.value;
+		proc_priv->power_limits[i].tmax_us = ppcc[4].integer.value;
+		proc_priv->power_limits[i].step_uw = ppcc[5].integer.value;
+	}
+
+free_buffer:
+	kfree(buf.pointer);
+
+	return ret;
+}
+
+#define PROC_POWER_CAPABILITY_CHANGED	0x83
+static void proc_thermal_notify(acpi_handle handle, u32 event, void *data)
+{
+	struct proc_thermal_device *proc_priv = data;
+
+	if (!proc_priv)
+		return;
+
+	switch (event) {
+	case PROC_POWER_CAPABILITY_CHANGED:
+		proc_thermal_read_ppcc(proc_priv);
+		int340x_thermal_zone_device_update(proc_priv->int340x_zone,
+				THERMAL_DEVICE_POWER_CAPABILITY_CHANGED);
+		break;
+	default:
+		dev_err(proc_priv->dev, "Unsupported event [0x%x]\n", event);
+		break;
+	}
+}
+
+
+static int proc_thermal_add(struct device *dev,
+			    struct proc_thermal_device **priv)
+{
+	struct proc_thermal_device *proc_priv;
+	struct acpi_device *adev;
+	acpi_status status;
+	unsigned long long tmp;
+	struct thermal_zone_device_ops *ops = NULL;
+	int ret;
+
+	adev = ACPI_COMPANION(dev);
+	if (!adev)
+		return -ENODEV;
+
+	proc_priv = devm_kzalloc(dev, sizeof(*proc_priv), GFP_KERNEL);
+	if (!proc_priv)
+		return -ENOMEM;
+
+	proc_priv->dev = dev;
+	proc_priv->adev = adev;
+	*priv = proc_priv;
+
+	ret = proc_thermal_read_ppcc(proc_priv);
+	if (!ret) {
+		ret = sysfs_create_group(&dev->kobj,
+					 &power_limit_attribute_group);
+
+	}
+	if (ret)
+		return ret;
+
+	status = acpi_evaluate_integer(adev->handle, "_TMP", NULL, &tmp);
+	if (ACPI_FAILURE(status)) {
+		/* there is no _TMP method, add local method */
+		stored_tjmax = get_tjmax();
+		if (stored_tjmax > 0)
+			ops = &proc_thermal_local_ops;
+	}
+
+	proc_priv->int340x_zone = int340x_thermal_zone_add(adev, ops);
+	if (IS_ERR(proc_priv->int340x_zone)) {
+		ret = PTR_ERR(proc_priv->int340x_zone);
+		goto remove_group;
+	} else
+		ret = 0;
+
+	ret = acpi_install_notify_handler(adev->handle, ACPI_DEVICE_NOTIFY,
+					  proc_thermal_notify,
+					  (void *)proc_priv);
+	if (ret)
+		goto remove_zone;
+
+	return 0;
+
+remove_zone:
+	int340x_thermal_zone_remove(proc_priv->int340x_zone);
+remove_group:
+	sysfs_remove_group(&proc_priv->dev->kobj,
+			   &power_limit_attribute_group);
+
+	return ret;
+}
+
+static void proc_thermal_remove(struct proc_thermal_device *proc_priv)
+{
+	acpi_remove_notify_handler(proc_priv->adev->handle,
+				   ACPI_DEVICE_NOTIFY, proc_thermal_notify);
+	int340x_thermal_zone_remove(proc_priv->int340x_zone);
+	sysfs_remove_group(&proc_priv->dev->kobj,
+			   &power_limit_attribute_group);
+}
+
+static int int3401_add(struct platform_device *pdev)
+{
+	struct proc_thermal_device *proc_priv;
+	int ret;
+
+	if (proc_thermal_emum_mode == PROC_THERMAL_PCI) {
+		dev_err(&pdev->dev, "error: enumerated as PCI dev\n");
+		return -ENODEV;
+	}
+
+	ret = proc_thermal_add(&pdev->dev, &proc_priv);
+	if (ret)
+		return ret;
+
+	platform_set_drvdata(pdev, proc_priv);
+	proc_thermal_emum_mode = PROC_THERMAL_PLATFORM_DEV;
+
+	return 0;
+}
+
+static int int3401_remove(struct platform_device *pdev)
+{
+	proc_thermal_remove(platform_get_drvdata(pdev));
+
+	return 0;
+}
+
+static irqreturn_t proc_thermal_pci_msi_irq(int irq, void *devid)
+{
+	struct proc_thermal_device *proc_priv;
+	struct pci_dev *pdev = devid;
+
+	proc_priv = pci_get_drvdata(pdev);
+
+	intel_soc_dts_iosf_interrupt_handler(proc_priv->soc_dts);
+
+	return IRQ_HANDLED;
+}
+
+static int  proc_thermal_pci_probe(struct pci_dev *pdev,
+				   const struct pci_device_id *unused)
+{
+	struct proc_thermal_device *proc_priv;
+	int ret;
+
+	if (proc_thermal_emum_mode == PROC_THERMAL_PLATFORM_DEV) {
+		dev_err(&pdev->dev, "error: enumerated as platform dev\n");
+		return -ENODEV;
+	}
+
+	ret = pci_enable_device(pdev);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "error: could not enable device\n");
+		return ret;
+	}
+
+	ret = proc_thermal_add(&pdev->dev, &proc_priv);
+	if (ret) {
+		pci_disable_device(pdev);
+		return ret;
+	}
+
+	pci_set_drvdata(pdev, proc_priv);
+	proc_thermal_emum_mode = PROC_THERMAL_PCI;
+
+	if (pdev->device == PCI_DEVICE_ID_PROC_BSW_THERMAL) {
+		/*
+		 * Enumerate additional DTS sensors available via IOSF.
+		 * But we are not treating as a failure condition, if
+		 * there are no aux DTSs enabled or fails. This driver
+		 * already exposes sensors, which can be accessed via
+		 * ACPI/MSR. So we don't want to fail for auxiliary DTSs.
+		 */
+		proc_priv->soc_dts = intel_soc_dts_iosf_init(
+					INTEL_SOC_DTS_INTERRUPT_MSI, 2, 0);
+
+		if (proc_priv->soc_dts && pdev->irq) {
+			ret = pci_enable_msi(pdev);
+			if (!ret) {
+				ret = request_threaded_irq(pdev->irq, NULL,
+						proc_thermal_pci_msi_irq,
+						IRQF_ONESHOT, "proc_thermal",
+						pdev);
+				if (ret) {
+					intel_soc_dts_iosf_exit(
+							proc_priv->soc_dts);
+					pci_disable_msi(pdev);
+					proc_priv->soc_dts = NULL;
+				}
+			}
+		} else
+			dev_err(&pdev->dev, "No auxiliary DTSs enabled\n");
+	}
+
+	return 0;
+}
+
+static void  proc_thermal_pci_remove(struct pci_dev *pdev)
+{
+	struct proc_thermal_device *proc_priv = pci_get_drvdata(pdev);
+
+	if (proc_priv->soc_dts) {
+		intel_soc_dts_iosf_exit(proc_priv->soc_dts);
+		if (pdev->irq) {
+			free_irq(pdev->irq, pdev);
+			pci_disable_msi(pdev);
+		}
+	}
+	proc_thermal_remove(proc_priv);
+	pci_disable_device(pdev);
+}
+
+static const struct pci_device_id proc_thermal_pci_ids[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BDW_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_HSB_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_SKL_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BSW_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BXT0_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BXT1_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BXTX_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_BXTP_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_CNL_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_CFL_THERMAL)},
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_PROC_GLK_THERMAL)},
+	{ 0, },
+};
+
+MODULE_DEVICE_TABLE(pci, proc_thermal_pci_ids);
+
+static struct pci_driver proc_thermal_pci_driver = {
+	.name		= "proc_thermal",
+	.probe		= proc_thermal_pci_probe,
+	.remove		= proc_thermal_pci_remove,
+	.id_table	= proc_thermal_pci_ids,
+};
+
+static const struct acpi_device_id int3401_device_ids[] = {
+	{"INT3401", 0},
+	{"", 0},
+};
+MODULE_DEVICE_TABLE(acpi, int3401_device_ids);
+
+static struct platform_driver int3401_driver = {
+	.probe = int3401_add,
+	.remove = int3401_remove,
+	.driver = {
+		.name = "int3401 thermal",
+		.acpi_match_table = int3401_device_ids,
+	},
+};
+
+static int __init proc_thermal_init(void)
+{
+	int ret;
+
+	ret = platform_driver_register(&int3401_driver);
+	if (ret)
+		return ret;
+
+	ret = pci_register_driver(&proc_thermal_pci_driver);
+
+	return ret;
+}
+
+static void __exit proc_thermal_exit(void)
+{
+	platform_driver_unregister(&int3401_driver);
+	pci_unregister_driver(&proc_thermal_pci_driver);
+}
+
+module_init(proc_thermal_init);
+module_exit(proc_thermal_exit);
+
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_DESCRIPTION("Processor Thermal Reporting Device Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/intel_bxt_pmic_thermal.c b/drivers/thermal/intel/intel_bxt_pmic_thermal.c
new file mode 100644
index 000000000000..94cfd0064c43
--- /dev/null
+++ b/drivers/thermal/intel/intel_bxt_pmic_thermal.c
@@ -0,0 +1,299 @@
+/*
+ * Intel Broxton PMIC thermal driver
+ *
+ * Copyright (C) 2016 Intel Corporation. All rights reserved.
+ *
+ * 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/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/device.h>
+#include <linux/thermal.h>
+#include <linux/platform_device.h>
+#include <linux/sched.h>
+#include <linux/mfd/intel_soc_pmic.h>
+
+#define BXTWC_THRM0IRQ		0x4E04
+#define BXTWC_THRM1IRQ		0x4E05
+#define BXTWC_THRM2IRQ		0x4E06
+#define BXTWC_MTHRM0IRQ		0x4E12
+#define BXTWC_MTHRM1IRQ		0x4E13
+#define BXTWC_MTHRM2IRQ		0x4E14
+#define BXTWC_STHRM0IRQ		0x4F19
+#define BXTWC_STHRM1IRQ		0x4F1A
+#define BXTWC_STHRM2IRQ		0x4F1B
+
+struct trip_config_map {
+	u16 irq_reg;
+	u16 irq_en;
+	u16 evt_stat;
+	u8 irq_mask;
+	u8 irq_en_mask;
+	u8 evt_mask;
+	u8 trip_num;
+};
+
+struct thermal_irq_map {
+	char handle[20];
+	int num_trips;
+	const struct trip_config_map *trip_config;
+};
+
+struct pmic_thermal_data {
+	const struct thermal_irq_map *maps;
+	int num_maps;
+};
+
+static const struct trip_config_map bxtwc_str0_trip_config[] = {
+	{
+		.irq_reg = BXTWC_THRM0IRQ,
+		.irq_mask = 0x01,
+		.irq_en = BXTWC_MTHRM0IRQ,
+		.irq_en_mask = 0x01,
+		.evt_stat = BXTWC_STHRM0IRQ,
+		.evt_mask = 0x01,
+		.trip_num = 0
+	},
+	{
+		.irq_reg = BXTWC_THRM0IRQ,
+		.irq_mask = 0x10,
+		.irq_en = BXTWC_MTHRM0IRQ,
+		.irq_en_mask = 0x10,
+		.evt_stat = BXTWC_STHRM0IRQ,
+		.evt_mask = 0x10,
+		.trip_num = 1
+	}
+};
+
+static const struct trip_config_map bxtwc_str1_trip_config[] = {
+	{
+		.irq_reg = BXTWC_THRM0IRQ,
+		.irq_mask = 0x02,
+		.irq_en = BXTWC_MTHRM0IRQ,
+		.irq_en_mask = 0x02,
+		.evt_stat = BXTWC_STHRM0IRQ,
+		.evt_mask = 0x02,
+		.trip_num = 0
+	},
+	{
+		.irq_reg = BXTWC_THRM0IRQ,
+		.irq_mask = 0x20,
+		.irq_en = BXTWC_MTHRM0IRQ,
+		.irq_en_mask = 0x20,
+		.evt_stat = BXTWC_STHRM0IRQ,
+		.evt_mask = 0x20,
+		.trip_num = 1
+	},
+};
+
+static const struct trip_config_map bxtwc_str2_trip_config[] = {
+	{
+		.irq_reg = BXTWC_THRM0IRQ,
+		.irq_mask = 0x04,
+		.irq_en = BXTWC_MTHRM0IRQ,
+		.irq_en_mask = 0x04,
+		.evt_stat = BXTWC_STHRM0IRQ,
+		.evt_mask = 0x04,
+		.trip_num = 0
+	},
+	{
+		.irq_reg = BXTWC_THRM0IRQ,
+		.irq_mask = 0x40,
+		.irq_en = BXTWC_MTHRM0IRQ,
+		.irq_en_mask = 0x40,
+		.evt_stat = BXTWC_STHRM0IRQ,
+		.evt_mask = 0x40,
+		.trip_num = 1
+	},
+};
+
+static const struct trip_config_map bxtwc_str3_trip_config[] = {
+	{
+		.irq_reg = BXTWC_THRM2IRQ,
+		.irq_mask = 0x10,
+		.irq_en = BXTWC_MTHRM2IRQ,
+		.irq_en_mask = 0x10,
+		.evt_stat = BXTWC_STHRM2IRQ,
+		.evt_mask = 0x10,
+		.trip_num = 0
+	},
+};
+
+static const struct thermal_irq_map bxtwc_thermal_irq_map[] = {
+	{
+		.handle = "STR0",
+		.trip_config = bxtwc_str0_trip_config,
+		.num_trips = ARRAY_SIZE(bxtwc_str0_trip_config),
+	},
+	{
+		.handle = "STR1",
+		.trip_config = bxtwc_str1_trip_config,
+		.num_trips = ARRAY_SIZE(bxtwc_str1_trip_config),
+	},
+	{
+		.handle = "STR2",
+		.trip_config = bxtwc_str2_trip_config,
+		.num_trips = ARRAY_SIZE(bxtwc_str2_trip_config),
+	},
+	{
+		.handle = "STR3",
+		.trip_config = bxtwc_str3_trip_config,
+		.num_trips = ARRAY_SIZE(bxtwc_str3_trip_config),
+	},
+};
+
+static const struct pmic_thermal_data bxtwc_thermal_data = {
+	.maps = bxtwc_thermal_irq_map,
+	.num_maps = ARRAY_SIZE(bxtwc_thermal_irq_map),
+};
+
+static irqreturn_t pmic_thermal_irq_handler(int irq, void *data)
+{
+	struct platform_device *pdev = data;
+	struct thermal_zone_device *tzd;
+	struct pmic_thermal_data *td;
+	struct intel_soc_pmic *pmic;
+	struct regmap *regmap;
+	u8 reg_val, mask, irq_stat;
+	u16 reg, evt_stat_reg;
+	int i, j, ret;
+
+	pmic = dev_get_drvdata(pdev->dev.parent);
+	regmap = pmic->regmap;
+	td = (struct pmic_thermal_data *)
+		platform_get_device_id(pdev)->driver_data;
+
+	/* Resolve thermal irqs */
+	for (i = 0; i < td->num_maps; i++) {
+		for (j = 0; j < td->maps[i].num_trips; j++) {
+			reg = td->maps[i].trip_config[j].irq_reg;
+			mask = td->maps[i].trip_config[j].irq_mask;
+			/*
+			 * Read the irq register to resolve whether the
+			 * interrupt was triggered for this sensor
+			 */
+			if (regmap_read(regmap, reg, &ret))
+				return IRQ_HANDLED;
+
+			reg_val = (u8)ret;
+			irq_stat = ((u8)ret & mask);
+
+			if (!irq_stat)
+				continue;
+
+			/*
+			 * Read the status register to find out what
+			 * event occurred i.e a high or a low
+			 */
+			evt_stat_reg = td->maps[i].trip_config[j].evt_stat;
+			if (regmap_read(regmap, evt_stat_reg, &ret))
+				return IRQ_HANDLED;
+
+			tzd = thermal_zone_get_zone_by_name(td->maps[i].handle);
+			if (!IS_ERR(tzd))
+				thermal_zone_device_update(tzd,
+						THERMAL_EVENT_UNSPECIFIED);
+
+			/* Clear the appropriate irq */
+			regmap_write(regmap, reg, reg_val & mask);
+		}
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int pmic_thermal_probe(struct platform_device *pdev)
+{
+	struct regmap_irq_chip_data *regmap_irq_chip;
+	struct pmic_thermal_data *thermal_data;
+	int ret, irq, virq, i, j, pmic_irq_count;
+	struct intel_soc_pmic *pmic;
+	struct regmap *regmap;
+	struct device *dev;
+	u16 reg;
+	u8 mask;
+
+	dev = &pdev->dev;
+	pmic = dev_get_drvdata(pdev->dev.parent);
+	if (!pmic) {
+		dev_err(dev, "Failed to get struct intel_soc_pmic pointer\n");
+		return -ENODEV;
+	}
+
+	thermal_data = (struct pmic_thermal_data *)
+				platform_get_device_id(pdev)->driver_data;
+	if (!thermal_data) {
+		dev_err(dev, "No thermal data initialized!!\n");
+		return -ENODEV;
+	}
+
+	regmap = pmic->regmap;
+	regmap_irq_chip = pmic->irq_chip_data;
+
+	pmic_irq_count = 0;
+	while ((irq = platform_get_irq(pdev, pmic_irq_count)) != -ENXIO) {
+		virq = regmap_irq_get_virq(regmap_irq_chip, irq);
+		if (virq < 0) {
+			dev_err(dev, "failed to get virq by irq %d\n", irq);
+			return virq;
+		}
+
+		ret = devm_request_threaded_irq(&pdev->dev, virq,
+				NULL, pmic_thermal_irq_handler,
+				IRQF_ONESHOT, "pmic_thermal", pdev);
+
+		if (ret) {
+			dev_err(dev, "request irq(%d) failed: %d\n", virq, ret);
+			return ret;
+		}
+		pmic_irq_count++;
+	}
+
+	/* Enable thermal interrupts */
+	for (i = 0; i < thermal_data->num_maps; i++) {
+		for (j = 0; j < thermal_data->maps[i].num_trips; j++) {
+			reg = thermal_data->maps[i].trip_config[j].irq_en;
+			mask = thermal_data->maps[i].trip_config[j].irq_en_mask;
+			ret = regmap_update_bits(regmap, reg, mask, 0x00);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+static const struct platform_device_id pmic_thermal_id_table[] = {
+	{
+		.name = "bxt_wcove_thermal",
+		.driver_data = (kernel_ulong_t)&bxtwc_thermal_data,
+	},
+	{},
+};
+
+static struct platform_driver pmic_thermal_driver = {
+	.probe = pmic_thermal_probe,
+	.driver = {
+		.name = "pmic_thermal",
+	},
+	.id_table = pmic_thermal_id_table,
+};
+
+MODULE_DEVICE_TABLE(platform, pmic_thermal_id_table);
+module_platform_driver(pmic_thermal_driver);
+
+MODULE_AUTHOR("Yegnesh S Iyer <yegnesh.s.iyer@intel.com>");
+MODULE_DESCRIPTION("Intel Broxton PMIC Thermal Driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/intel_pch_thermal.c b/drivers/thermal/intel/intel_pch_thermal.c
new file mode 100644
index 000000000000..8a7f69b4b022
--- /dev/null
+++ b/drivers/thermal/intel/intel_pch_thermal.c
@@ -0,0 +1,432 @@
+/* intel_pch_thermal.c - Intel PCH Thermal driver
+ *
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * Authors:
+ *     Tushar Dave <tushar.n.dave@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/module.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/acpi.h>
+#include <linux/thermal.h>
+#include <linux/pm.h>
+
+/* Intel PCH thermal Device IDs */
+#define PCH_THERMAL_DID_HSW_1	0x9C24 /* Haswell PCH */
+#define PCH_THERMAL_DID_HSW_2	0x8C24 /* Haswell PCH */
+#define PCH_THERMAL_DID_WPT	0x9CA4 /* Wildcat Point */
+#define PCH_THERMAL_DID_SKL	0x9D31 /* Skylake PCH */
+#define PCH_THERMAL_DID_SKL_H	0xA131 /* Skylake PCH 100 series */
+#define PCH_THERMAL_DID_CNL	0x9Df9 /* CNL PCH */
+#define PCH_THERMAL_DID_CNL_H	0xA379 /* CNL-H PCH */
+
+/* Wildcat Point-LP  PCH Thermal registers */
+#define WPT_TEMP	0x0000	/* Temperature */
+#define WPT_TSC	0x04	/* Thermal Sensor Control */
+#define WPT_TSS	0x06	/* Thermal Sensor Status */
+#define WPT_TSEL	0x08	/* Thermal Sensor Enable and Lock */
+#define WPT_TSREL	0x0A	/* Thermal Sensor Report Enable and Lock */
+#define WPT_TSMIC	0x0C	/* Thermal Sensor SMI Control */
+#define WPT_CTT	0x0010	/* Catastrophic Trip Point */
+#define WPT_TAHV	0x0014	/* Thermal Alert High Value */
+#define WPT_TALV	0x0018	/* Thermal Alert Low Value */
+#define WPT_TL		0x00000040	/* Throttle Value */
+#define WPT_PHL	0x0060	/* PCH Hot Level */
+#define WPT_PHLC	0x62	/* PHL Control */
+#define WPT_TAS	0x80	/* Thermal Alert Status */
+#define WPT_TSPIEN	0x82	/* PCI Interrupt Event Enables */
+#define WPT_TSGPEN	0x84	/* General Purpose Event Enables */
+
+/*  Wildcat Point-LP  PCH Thermal Register bit definitions */
+#define WPT_TEMP_TSR	0x01ff	/* Temp TS Reading */
+#define WPT_TSC_CPDE	0x01	/* Catastrophic Power-Down Enable */
+#define WPT_TSS_TSDSS	0x10	/* Thermal Sensor Dynamic Shutdown Status */
+#define WPT_TSS_GPES	0x08	/* GPE status */
+#define WPT_TSEL_ETS	0x01    /* Enable TS */
+#define WPT_TSEL_PLDB	0x80	/* TSEL Policy Lock-Down Bit */
+#define WPT_TL_TOL	0x000001FF	/* T0 Level */
+#define WPT_TL_T1L	0x1ff00000	/* T1 Level */
+#define WPT_TL_TTEN	0x20000000	/* TT Enable */
+
+static char driver_name[] = "Intel PCH thermal driver";
+
+struct pch_thermal_device {
+	void __iomem *hw_base;
+	const struct pch_dev_ops *ops;
+	struct pci_dev *pdev;
+	struct thermal_zone_device *tzd;
+	int crt_trip_id;
+	unsigned long crt_temp;
+	int hot_trip_id;
+	unsigned long hot_temp;
+	int psv_trip_id;
+	unsigned long psv_temp;
+	bool bios_enabled;
+};
+
+#ifdef CONFIG_ACPI
+
+/*
+ * On some platforms, there is a companion ACPI device, which adds
+ * passive trip temperature using _PSV method. There is no specific
+ * passive temperature setting in MMIO interface of this PCI device.
+ */
+static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
+				      int *nr_trips)
+{
+	struct acpi_device *adev;
+
+	ptd->psv_trip_id = -1;
+
+	adev = ACPI_COMPANION(&ptd->pdev->dev);
+	if (adev) {
+		unsigned long long r;
+		acpi_status status;
+
+		status = acpi_evaluate_integer(adev->handle, "_PSV", NULL,
+					       &r);
+		if (ACPI_SUCCESS(status)) {
+			unsigned long trip_temp;
+
+			trip_temp = DECI_KELVIN_TO_MILLICELSIUS(r);
+			if (trip_temp) {
+				ptd->psv_temp = trip_temp;
+				ptd->psv_trip_id = *nr_trips;
+				++(*nr_trips);
+			}
+		}
+	}
+}
+#else
+static void pch_wpt_add_acpi_psv_trip(struct pch_thermal_device *ptd,
+				      int *nr_trips)
+{
+	ptd->psv_trip_id = -1;
+
+}
+#endif
+
+static int pch_wpt_init(struct pch_thermal_device *ptd, int *nr_trips)
+{
+	u8 tsel;
+	u16 trip_temp;
+
+	*nr_trips = 0;
+
+	/* Check if BIOS has already enabled thermal sensor */
+	if (WPT_TSEL_ETS & readb(ptd->hw_base + WPT_TSEL)) {
+		ptd->bios_enabled = true;
+		goto read_trips;
+	}
+
+	tsel = readb(ptd->hw_base + WPT_TSEL);
+	/*
+	 * When TSEL's Policy Lock-Down bit is 1, TSEL become RO.
+	 * If so, thermal sensor cannot enable. Bail out.
+	 */
+	if (tsel & WPT_TSEL_PLDB) {
+		dev_err(&ptd->pdev->dev, "Sensor can't be enabled\n");
+		return -ENODEV;
+	}
+
+	writeb(tsel|WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL);
+	if (!(WPT_TSEL_ETS & readb(ptd->hw_base + WPT_TSEL))) {
+		dev_err(&ptd->pdev->dev, "Sensor can't be enabled\n");
+		return -ENODEV;
+	}
+
+read_trips:
+	ptd->crt_trip_id = -1;
+	trip_temp = readw(ptd->hw_base + WPT_CTT);
+	trip_temp &= 0x1FF;
+	if (trip_temp) {
+		/* Resolution of 1/2 degree C and an offset of -50C */
+		ptd->crt_temp = trip_temp * 1000 / 2 - 50000;
+		ptd->crt_trip_id = 0;
+		++(*nr_trips);
+	}
+
+	ptd->hot_trip_id = -1;
+	trip_temp = readw(ptd->hw_base + WPT_PHL);
+	trip_temp &= 0x1FF;
+	if (trip_temp) {
+		/* Resolution of 1/2 degree C and an offset of -50C */
+		ptd->hot_temp = trip_temp * 1000 / 2 - 50000;
+		ptd->hot_trip_id = *nr_trips;
+		++(*nr_trips);
+	}
+
+	pch_wpt_add_acpi_psv_trip(ptd, nr_trips);
+
+	return 0;
+}
+
+static int pch_wpt_get_temp(struct pch_thermal_device *ptd, int *temp)
+{
+	u16 wpt_temp;
+
+	wpt_temp = WPT_TEMP_TSR & readw(ptd->hw_base + WPT_TEMP);
+
+	/* Resolution of 1/2 degree C and an offset of -50C */
+	*temp = (wpt_temp * 1000 / 2 - 50000);
+
+	return 0;
+}
+
+static int pch_wpt_suspend(struct pch_thermal_device *ptd)
+{
+	u8 tsel;
+
+	if (ptd->bios_enabled)
+		return 0;
+
+	tsel = readb(ptd->hw_base + WPT_TSEL);
+
+	writeb(tsel & 0xFE, ptd->hw_base + WPT_TSEL);
+
+	return 0;
+}
+
+static int pch_wpt_resume(struct pch_thermal_device *ptd)
+{
+	u8 tsel;
+
+	if (ptd->bios_enabled)
+		return 0;
+
+	tsel = readb(ptd->hw_base + WPT_TSEL);
+
+	writeb(tsel | WPT_TSEL_ETS, ptd->hw_base + WPT_TSEL);
+
+	return 0;
+}
+
+struct pch_dev_ops {
+	int (*hw_init)(struct pch_thermal_device *ptd, int *nr_trips);
+	int (*get_temp)(struct pch_thermal_device *ptd, int *temp);
+	int (*suspend)(struct pch_thermal_device *ptd);
+	int (*resume)(struct pch_thermal_device *ptd);
+};
+
+
+/* dev ops for Wildcat Point */
+static const struct pch_dev_ops pch_dev_ops_wpt = {
+	.hw_init = pch_wpt_init,
+	.get_temp = pch_wpt_get_temp,
+	.suspend = pch_wpt_suspend,
+	.resume = pch_wpt_resume,
+};
+
+static int pch_thermal_get_temp(struct thermal_zone_device *tzd, int *temp)
+{
+	struct pch_thermal_device *ptd = tzd->devdata;
+
+	return	ptd->ops->get_temp(ptd, temp);
+}
+
+static int pch_get_trip_type(struct thermal_zone_device *tzd, int trip,
+			     enum thermal_trip_type *type)
+{
+	struct pch_thermal_device *ptd = tzd->devdata;
+
+	if (ptd->crt_trip_id == trip)
+		*type = THERMAL_TRIP_CRITICAL;
+	else if (ptd->hot_trip_id == trip)
+		*type = THERMAL_TRIP_HOT;
+	else if (ptd->psv_trip_id == trip)
+		*type = THERMAL_TRIP_PASSIVE;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int pch_get_trip_temp(struct thermal_zone_device *tzd, int trip, int *temp)
+{
+	struct pch_thermal_device *ptd = tzd->devdata;
+
+	if (ptd->crt_trip_id == trip)
+		*temp = ptd->crt_temp;
+	else if (ptd->hot_trip_id == trip)
+		*temp = ptd->hot_temp;
+	else if (ptd->psv_trip_id == trip)
+		*temp = ptd->psv_temp;
+	else
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct thermal_zone_device_ops tzd_ops = {
+	.get_temp = pch_thermal_get_temp,
+	.get_trip_type = pch_get_trip_type,
+	.get_trip_temp = pch_get_trip_temp,
+};
+
+enum board_ids {
+	board_hsw,
+	board_wpt,
+	board_skl,
+	board_cnl,
+};
+
+static const struct board_info {
+	const char *name;
+	const struct pch_dev_ops *ops;
+} board_info[] = {
+	[board_hsw] = {
+		.name = "pch_haswell",
+		.ops = &pch_dev_ops_wpt,
+	},
+	[board_wpt] = {
+		.name = "pch_wildcat_point",
+		.ops = &pch_dev_ops_wpt,
+	},
+	[board_skl] = {
+		.name = "pch_skylake",
+		.ops = &pch_dev_ops_wpt,
+	},
+	[board_cnl] = {
+		.name = "pch_cannonlake",
+		.ops = &pch_dev_ops_wpt,
+	},
+};
+
+static int intel_pch_thermal_probe(struct pci_dev *pdev,
+				   const struct pci_device_id *id)
+{
+	enum board_ids board_id = id->driver_data;
+	const struct board_info *bi = &board_info[board_id];
+	struct pch_thermal_device *ptd;
+	int err;
+	int nr_trips;
+
+	ptd = devm_kzalloc(&pdev->dev, sizeof(*ptd), GFP_KERNEL);
+	if (!ptd)
+		return -ENOMEM;
+
+	ptd->ops = bi->ops;
+
+	pci_set_drvdata(pdev, ptd);
+	ptd->pdev = pdev;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		dev_err(&pdev->dev, "failed to enable pci device\n");
+		return err;
+	}
+
+	err = pci_request_regions(pdev, driver_name);
+	if (err) {
+		dev_err(&pdev->dev, "failed to request pci region\n");
+		goto error_disable;
+	}
+
+	ptd->hw_base = pci_ioremap_bar(pdev, 0);
+	if (!ptd->hw_base) {
+		err = -ENOMEM;
+		dev_err(&pdev->dev, "failed to map mem base\n");
+		goto error_release;
+	}
+
+	err = ptd->ops->hw_init(ptd, &nr_trips);
+	if (err)
+		goto error_cleanup;
+
+	ptd->tzd = thermal_zone_device_register(bi->name, nr_trips, 0, ptd,
+						&tzd_ops, NULL, 0, 0);
+	if (IS_ERR(ptd->tzd)) {
+		dev_err(&pdev->dev, "Failed to register thermal zone %s\n",
+			bi->name);
+		err = PTR_ERR(ptd->tzd);
+		goto error_cleanup;
+	}
+
+	return 0;
+
+error_cleanup:
+	iounmap(ptd->hw_base);
+error_release:
+	pci_release_regions(pdev);
+error_disable:
+	pci_disable_device(pdev);
+	dev_err(&pdev->dev, "pci device failed to probe\n");
+	return err;
+}
+
+static void intel_pch_thermal_remove(struct pci_dev *pdev)
+{
+	struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
+
+	thermal_zone_device_unregister(ptd->tzd);
+	iounmap(ptd->hw_base);
+	pci_set_drvdata(pdev, NULL);
+	pci_release_region(pdev, 0);
+	pci_disable_device(pdev);
+}
+
+static int intel_pch_thermal_suspend(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
+
+	return ptd->ops->suspend(ptd);
+}
+
+static int intel_pch_thermal_resume(struct device *device)
+{
+	struct pci_dev *pdev = to_pci_dev(device);
+	struct pch_thermal_device *ptd = pci_get_drvdata(pdev);
+
+	return ptd->ops->resume(ptd);
+}
+
+static const struct pci_device_id intel_pch_thermal_id[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_1),
+		.driver_data = board_hsw, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_HSW_2),
+		.driver_data = board_hsw, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_WPT),
+		.driver_data = board_wpt, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL),
+		.driver_data = board_skl, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_SKL_H),
+		.driver_data = board_skl, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL),
+		.driver_data = board_cnl, },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCH_THERMAL_DID_CNL_H),
+		.driver_data = board_cnl, },
+	{ 0, },
+};
+MODULE_DEVICE_TABLE(pci, intel_pch_thermal_id);
+
+static const struct dev_pm_ops intel_pch_pm_ops = {
+	.suspend = intel_pch_thermal_suspend,
+	.resume = intel_pch_thermal_resume,
+};
+
+static struct pci_driver intel_pch_thermal_driver = {
+	.name		= "intel_pch_thermal",
+	.id_table	= intel_pch_thermal_id,
+	.probe		= intel_pch_thermal_probe,
+	.remove		= intel_pch_thermal_remove,
+	.driver.pm	= &intel_pch_pm_ops,
+};
+
+module_pci_driver(intel_pch_thermal_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Intel PCH Thermal driver");
diff --git a/drivers/thermal/intel/intel_powerclamp.c b/drivers/thermal/intel/intel_powerclamp.c
new file mode 100644
index 000000000000..7571f7c2e7c9
--- /dev/null
+++ b/drivers/thermal/intel/intel_powerclamp.c
@@ -0,0 +1,803 @@
+/*
+ * intel_powerclamp.c - package c-state idle injection
+ *
+ * Copyright (c) 2012, Intel Corporation.
+ *
+ * Authors:
+ *     Arjan van de Ven <arjan@linux.intel.com>
+ *     Jacob Pan <jacob.jun.pan@linux.intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ *
+ *	TODO:
+ *           1. better handle wakeup from external interrupts, currently a fixed
+ *              compensation is added to clamping duration when excessive amount
+ *              of wakeups are observed during idle time. the reason is that in
+ *              case of external interrupts without need for ack, clamping down
+ *              cpu in non-irq context does not reduce irq. for majority of the
+ *              cases, clamping down cpu does help reduce irq as well, we should
+ *              be able to differentiate the two cases and give a quantitative
+ *              solution for the irqs that we can control. perhaps based on
+ *              get_cpu_iowait_time_us()
+ *
+ *	     2. synchronization with other hw blocks
+ *
+ *
+ */
+
+#define pr_fmt(fmt)	KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/delay.h>
+#include <linux/kthread.h>
+#include <linux/cpu.h>
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/tick.h>
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+#include <linux/sched/rt.h>
+#include <uapi/linux/sched/types.h>
+
+#include <asm/nmi.h>
+#include <asm/msr.h>
+#include <asm/mwait.h>
+#include <asm/cpu_device_id.h>
+#include <asm/hardirq.h>
+
+#define MAX_TARGET_RATIO (50U)
+/* For each undisturbed clamping period (no extra wake ups during idle time),
+ * we increment the confidence counter for the given target ratio.
+ * CONFIDENCE_OK defines the level where runtime calibration results are
+ * valid.
+ */
+#define CONFIDENCE_OK (3)
+/* Default idle injection duration, driver adjust sleep time to meet target
+ * idle ratio. Similar to frequency modulation.
+ */
+#define DEFAULT_DURATION_JIFFIES (6)
+
+static unsigned int target_mwait;
+static struct dentry *debug_dir;
+
+/* user selected target */
+static unsigned int set_target_ratio;
+static unsigned int current_ratio;
+static bool should_skip;
+static bool reduce_irq;
+static atomic_t idle_wakeup_counter;
+static unsigned int control_cpu; /* The cpu assigned to collect stat and update
+				  * control parameters. default to BSP but BSP
+				  * can be offlined.
+				  */
+static bool clamping;
+
+static const struct sched_param sparam = {
+	.sched_priority = MAX_USER_RT_PRIO / 2,
+};
+struct powerclamp_worker_data {
+	struct kthread_worker *worker;
+	struct kthread_work balancing_work;
+	struct kthread_delayed_work idle_injection_work;
+	unsigned int cpu;
+	unsigned int count;
+	unsigned int guard;
+	unsigned int window_size_now;
+	unsigned int target_ratio;
+	unsigned int duration_jiffies;
+	bool clamping;
+};
+
+static struct powerclamp_worker_data * __percpu worker_data;
+static struct thermal_cooling_device *cooling_dev;
+static unsigned long *cpu_clamping_mask;  /* bit map for tracking per cpu
+					   * clamping kthread worker
+					   */
+
+static unsigned int duration;
+static unsigned int pkg_cstate_ratio_cur;
+static unsigned int window_size;
+
+static int duration_set(const char *arg, const struct kernel_param *kp)
+{
+	int ret = 0;
+	unsigned long new_duration;
+
+	ret = kstrtoul(arg, 10, &new_duration);
+	if (ret)
+		goto exit;
+	if (new_duration > 25 || new_duration < 6) {
+		pr_err("Out of recommended range %lu, between 6-25ms\n",
+			new_duration);
+		ret = -EINVAL;
+	}
+
+	duration = clamp(new_duration, 6ul, 25ul);
+	smp_mb();
+
+exit:
+
+	return ret;
+}
+
+static const struct kernel_param_ops duration_ops = {
+	.set = duration_set,
+	.get = param_get_int,
+};
+
+
+module_param_cb(duration, &duration_ops, &duration, 0644);
+MODULE_PARM_DESC(duration, "forced idle time for each attempt in msec.");
+
+struct powerclamp_calibration_data {
+	unsigned long confidence;  /* used for calibration, basically a counter
+				    * gets incremented each time a clamping
+				    * period is completed without extra wakeups
+				    * once that counter is reached given level,
+				    * compensation is deemed usable.
+				    */
+	unsigned long steady_comp; /* steady state compensation used when
+				    * no extra wakeups occurred.
+				    */
+	unsigned long dynamic_comp; /* compensate excessive wakeup from idle
+				     * mostly from external interrupts.
+				     */
+};
+
+static struct powerclamp_calibration_data cal_data[MAX_TARGET_RATIO];
+
+static int window_size_set(const char *arg, const struct kernel_param *kp)
+{
+	int ret = 0;
+	unsigned long new_window_size;
+
+	ret = kstrtoul(arg, 10, &new_window_size);
+	if (ret)
+		goto exit_win;
+	if (new_window_size > 10 || new_window_size < 2) {
+		pr_err("Out of recommended window size %lu, between 2-10\n",
+			new_window_size);
+		ret = -EINVAL;
+	}
+
+	window_size = clamp(new_window_size, 2ul, 10ul);
+	smp_mb();
+
+exit_win:
+
+	return ret;
+}
+
+static const struct kernel_param_ops window_size_ops = {
+	.set = window_size_set,
+	.get = param_get_int,
+};
+
+module_param_cb(window_size, &window_size_ops, &window_size, 0644);
+MODULE_PARM_DESC(window_size, "sliding window in number of clamping cycles\n"
+	"\tpowerclamp controls idle ratio within this window. larger\n"
+	"\twindow size results in slower response time but more smooth\n"
+	"\tclamping results. default to 2.");
+
+static void find_target_mwait(void)
+{
+	unsigned int eax, ebx, ecx, edx;
+	unsigned int highest_cstate = 0;
+	unsigned int highest_subcstate = 0;
+	int i;
+
+	if (boot_cpu_data.cpuid_level < CPUID_MWAIT_LEAF)
+		return;
+
+	cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &edx);
+
+	if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
+	    !(ecx & CPUID5_ECX_INTERRUPT_BREAK))
+		return;
+
+	edx >>= MWAIT_SUBSTATE_SIZE;
+	for (i = 0; i < 7 && edx; i++, edx >>= MWAIT_SUBSTATE_SIZE) {
+		if (edx & MWAIT_SUBSTATE_MASK) {
+			highest_cstate = i;
+			highest_subcstate = edx & MWAIT_SUBSTATE_MASK;
+		}
+	}
+	target_mwait = (highest_cstate << MWAIT_SUBSTATE_SIZE) |
+		(highest_subcstate - 1);
+
+}
+
+struct pkg_cstate_info {
+	bool skip;
+	int msr_index;
+	int cstate_id;
+};
+
+#define PKG_CSTATE_INIT(id) {				\
+		.msr_index = MSR_PKG_C##id##_RESIDENCY, \
+		.cstate_id = id				\
+			}
+
+static struct pkg_cstate_info pkg_cstates[] = {
+	PKG_CSTATE_INIT(2),
+	PKG_CSTATE_INIT(3),
+	PKG_CSTATE_INIT(6),
+	PKG_CSTATE_INIT(7),
+	PKG_CSTATE_INIT(8),
+	PKG_CSTATE_INIT(9),
+	PKG_CSTATE_INIT(10),
+	{NULL},
+};
+
+static bool has_pkg_state_counter(void)
+{
+	u64 val;
+	struct pkg_cstate_info *info = pkg_cstates;
+
+	/* check if any one of the counter msrs exists */
+	while (info->msr_index) {
+		if (!rdmsrl_safe(info->msr_index, &val))
+			return true;
+		info++;
+	}
+
+	return false;
+}
+
+static u64 pkg_state_counter(void)
+{
+	u64 val;
+	u64 count = 0;
+	struct pkg_cstate_info *info = pkg_cstates;
+
+	while (info->msr_index) {
+		if (!info->skip) {
+			if (!rdmsrl_safe(info->msr_index, &val))
+				count += val;
+			else
+				info->skip = true;
+		}
+		info++;
+	}
+
+	return count;
+}
+
+static unsigned int get_compensation(int ratio)
+{
+	unsigned int comp = 0;
+
+	/* we only use compensation if all adjacent ones are good */
+	if (ratio == 1 &&
+		cal_data[ratio].confidence >= CONFIDENCE_OK &&
+		cal_data[ratio + 1].confidence >= CONFIDENCE_OK &&
+		cal_data[ratio + 2].confidence >= CONFIDENCE_OK) {
+		comp = (cal_data[ratio].steady_comp +
+			cal_data[ratio + 1].steady_comp +
+			cal_data[ratio + 2].steady_comp) / 3;
+	} else if (ratio == MAX_TARGET_RATIO - 1 &&
+		cal_data[ratio].confidence >= CONFIDENCE_OK &&
+		cal_data[ratio - 1].confidence >= CONFIDENCE_OK &&
+		cal_data[ratio - 2].confidence >= CONFIDENCE_OK) {
+		comp = (cal_data[ratio].steady_comp +
+			cal_data[ratio - 1].steady_comp +
+			cal_data[ratio - 2].steady_comp) / 3;
+	} else if (cal_data[ratio].confidence >= CONFIDENCE_OK &&
+		cal_data[ratio - 1].confidence >= CONFIDENCE_OK &&
+		cal_data[ratio + 1].confidence >= CONFIDENCE_OK) {
+		comp = (cal_data[ratio].steady_comp +
+			cal_data[ratio - 1].steady_comp +
+			cal_data[ratio + 1].steady_comp) / 3;
+	}
+
+	/* REVISIT: simple penalty of double idle injection */
+	if (reduce_irq)
+		comp = ratio;
+	/* do not exceed limit */
+	if (comp + ratio >= MAX_TARGET_RATIO)
+		comp = MAX_TARGET_RATIO - ratio - 1;
+
+	return comp;
+}
+
+static void adjust_compensation(int target_ratio, unsigned int win)
+{
+	int delta;
+	struct powerclamp_calibration_data *d = &cal_data[target_ratio];
+
+	/*
+	 * adjust compensations if confidence level has not been reached or
+	 * there are too many wakeups during the last idle injection period, we
+	 * cannot trust the data for compensation.
+	 */
+	if (d->confidence >= CONFIDENCE_OK ||
+		atomic_read(&idle_wakeup_counter) >
+		win * num_online_cpus())
+		return;
+
+	delta = set_target_ratio - current_ratio;
+	/* filter out bad data */
+	if (delta >= 0 && delta <= (1+target_ratio/10)) {
+		if (d->steady_comp)
+			d->steady_comp =
+				roundup(delta+d->steady_comp, 2)/2;
+		else
+			d->steady_comp = delta;
+		d->confidence++;
+	}
+}
+
+static bool powerclamp_adjust_controls(unsigned int target_ratio,
+				unsigned int guard, unsigned int win)
+{
+	static u64 msr_last, tsc_last;
+	u64 msr_now, tsc_now;
+	u64 val64;
+
+	/* check result for the last window */
+	msr_now = pkg_state_counter();
+	tsc_now = rdtsc();
+
+	/* calculate pkg cstate vs tsc ratio */
+	if (!msr_last || !tsc_last)
+		current_ratio = 1;
+	else if (tsc_now-tsc_last) {
+		val64 = 100*(msr_now-msr_last);
+		do_div(val64, (tsc_now-tsc_last));
+		current_ratio = val64;
+	}
+
+	/* update record */
+	msr_last = msr_now;
+	tsc_last = tsc_now;
+
+	adjust_compensation(target_ratio, win);
+	/*
+	 * too many external interrupts, set flag such
+	 * that we can take measure later.
+	 */
+	reduce_irq = atomic_read(&idle_wakeup_counter) >=
+		2 * win * num_online_cpus();
+
+	atomic_set(&idle_wakeup_counter, 0);
+	/* if we are above target+guard, skip */
+	return set_target_ratio + guard <= current_ratio;
+}
+
+static void clamp_balancing_func(struct kthread_work *work)
+{
+	struct powerclamp_worker_data *w_data;
+	int sleeptime;
+	unsigned long target_jiffies;
+	unsigned int compensated_ratio;
+	int interval; /* jiffies to sleep for each attempt */
+
+	w_data = container_of(work, struct powerclamp_worker_data,
+			      balancing_work);
+
+	/*
+	 * make sure user selected ratio does not take effect until
+	 * the next round. adjust target_ratio if user has changed
+	 * target such that we can converge quickly.
+	 */
+	w_data->target_ratio = READ_ONCE(set_target_ratio);
+	w_data->guard = 1 + w_data->target_ratio / 20;
+	w_data->window_size_now = window_size;
+	w_data->duration_jiffies = msecs_to_jiffies(duration);
+	w_data->count++;
+
+	/*
+	 * systems may have different ability to enter package level
+	 * c-states, thus we need to compensate the injected idle ratio
+	 * to achieve the actual target reported by the HW.
+	 */
+	compensated_ratio = w_data->target_ratio +
+		get_compensation(w_data->target_ratio);
+	if (compensated_ratio <= 0)
+		compensated_ratio = 1;
+	interval = w_data->duration_jiffies * 100 / compensated_ratio;
+
+	/* align idle time */
+	target_jiffies = roundup(jiffies, interval);
+	sleeptime = target_jiffies - jiffies;
+	if (sleeptime <= 0)
+		sleeptime = 1;
+
+	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
+		kthread_queue_delayed_work(w_data->worker,
+					   &w_data->idle_injection_work,
+					   sleeptime);
+}
+
+static void clamp_idle_injection_func(struct kthread_work *work)
+{
+	struct powerclamp_worker_data *w_data;
+
+	w_data = container_of(work, struct powerclamp_worker_data,
+			      idle_injection_work.work);
+
+	/*
+	 * only elected controlling cpu can collect stats and update
+	 * control parameters.
+	 */
+	if (w_data->cpu == control_cpu &&
+	    !(w_data->count % w_data->window_size_now)) {
+		should_skip =
+			powerclamp_adjust_controls(w_data->target_ratio,
+						   w_data->guard,
+						   w_data->window_size_now);
+		smp_mb();
+	}
+
+	if (should_skip)
+		goto balance;
+
+	play_idle(jiffies_to_msecs(w_data->duration_jiffies));
+
+balance:
+	if (clamping && w_data->clamping && cpu_online(w_data->cpu))
+		kthread_queue_work(w_data->worker, &w_data->balancing_work);
+}
+
+/*
+ * 1 HZ polling while clamping is active, useful for userspace
+ * to monitor actual idle ratio.
+ */
+static void poll_pkg_cstate(struct work_struct *dummy);
+static DECLARE_DELAYED_WORK(poll_pkg_cstate_work, poll_pkg_cstate);
+static void poll_pkg_cstate(struct work_struct *dummy)
+{
+	static u64 msr_last;
+	static u64 tsc_last;
+
+	u64 msr_now;
+	u64 tsc_now;
+	u64 val64;
+
+	msr_now = pkg_state_counter();
+	tsc_now = rdtsc();
+
+	/* calculate pkg cstate vs tsc ratio */
+	if (!msr_last || !tsc_last)
+		pkg_cstate_ratio_cur = 1;
+	else {
+		if (tsc_now - tsc_last) {
+			val64 = 100 * (msr_now - msr_last);
+			do_div(val64, (tsc_now - tsc_last));
+			pkg_cstate_ratio_cur = val64;
+		}
+	}
+
+	/* update record */
+	msr_last = msr_now;
+	tsc_last = tsc_now;
+
+	if (true == clamping)
+		schedule_delayed_work(&poll_pkg_cstate_work, HZ);
+}
+
+static void start_power_clamp_worker(unsigned long cpu)
+{
+	struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
+	struct kthread_worker *worker;
+
+	worker = kthread_create_worker_on_cpu(cpu, 0, "kidle_inject/%ld", cpu);
+	if (IS_ERR(worker))
+		return;
+
+	w_data->worker = worker;
+	w_data->count = 0;
+	w_data->cpu = cpu;
+	w_data->clamping = true;
+	set_bit(cpu, cpu_clamping_mask);
+	sched_setscheduler(worker->task, SCHED_FIFO, &sparam);
+	kthread_init_work(&w_data->balancing_work, clamp_balancing_func);
+	kthread_init_delayed_work(&w_data->idle_injection_work,
+				  clamp_idle_injection_func);
+	kthread_queue_work(w_data->worker, &w_data->balancing_work);
+}
+
+static void stop_power_clamp_worker(unsigned long cpu)
+{
+	struct powerclamp_worker_data *w_data = per_cpu_ptr(worker_data, cpu);
+
+	if (!w_data->worker)
+		return;
+
+	w_data->clamping = false;
+	/*
+	 * Make sure that all works that get queued after this point see
+	 * the clamping disabled. The counter part is not needed because
+	 * there is an implicit memory barrier when the queued work
+	 * is proceed.
+	 */
+	smp_wmb();
+	kthread_cancel_work_sync(&w_data->balancing_work);
+	kthread_cancel_delayed_work_sync(&w_data->idle_injection_work);
+	/*
+	 * The balancing work still might be queued here because
+	 * the handling of the "clapming" variable, cancel, and queue
+	 * operations are not synchronized via a lock. But it is not
+	 * a big deal. The balancing work is fast and destroy kthread
+	 * will wait for it.
+	 */
+	clear_bit(w_data->cpu, cpu_clamping_mask);
+	kthread_destroy_worker(w_data->worker);
+
+	w_data->worker = NULL;
+}
+
+static int start_power_clamp(void)
+{
+	unsigned long cpu;
+
+	set_target_ratio = clamp(set_target_ratio, 0U, MAX_TARGET_RATIO - 1);
+	/* prevent cpu hotplug */
+	get_online_cpus();
+
+	/* prefer BSP */
+	control_cpu = 0;
+	if (!cpu_online(control_cpu))
+		control_cpu = smp_processor_id();
+
+	clamping = true;
+	schedule_delayed_work(&poll_pkg_cstate_work, 0);
+
+	/* start one kthread worker per online cpu */
+	for_each_online_cpu(cpu) {
+		start_power_clamp_worker(cpu);
+	}
+	put_online_cpus();
+
+	return 0;
+}
+
+static void end_power_clamp(void)
+{
+	int i;
+
+	/*
+	 * Block requeuing in all the kthread workers. They will flush and
+	 * stop faster.
+	 */
+	clamping = false;
+	if (bitmap_weight(cpu_clamping_mask, num_possible_cpus())) {
+		for_each_set_bit(i, cpu_clamping_mask, num_possible_cpus()) {
+			pr_debug("clamping worker for cpu %d alive, destroy\n",
+				 i);
+			stop_power_clamp_worker(i);
+		}
+	}
+}
+
+static int powerclamp_cpu_online(unsigned int cpu)
+{
+	if (clamping == false)
+		return 0;
+	start_power_clamp_worker(cpu);
+	/* prefer BSP as controlling CPU */
+	if (cpu == 0) {
+		control_cpu = 0;
+		smp_mb();
+	}
+	return 0;
+}
+
+static int powerclamp_cpu_predown(unsigned int cpu)
+{
+	if (clamping == false)
+		return 0;
+
+	stop_power_clamp_worker(cpu);
+	if (cpu != control_cpu)
+		return 0;
+
+	control_cpu = cpumask_first(cpu_online_mask);
+	if (control_cpu == cpu)
+		control_cpu = cpumask_next(cpu, cpu_online_mask);
+	smp_mb();
+	return 0;
+}
+
+static int powerclamp_get_max_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	*state = MAX_TARGET_RATIO;
+
+	return 0;
+}
+
+static int powerclamp_get_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long *state)
+{
+	if (true == clamping)
+		*state = pkg_cstate_ratio_cur;
+	else
+		/* to save power, do not poll idle ratio while not clamping */
+		*state = -1; /* indicates invalid state */
+
+	return 0;
+}
+
+static int powerclamp_set_cur_state(struct thermal_cooling_device *cdev,
+				 unsigned long new_target_ratio)
+{
+	int ret = 0;
+
+	new_target_ratio = clamp(new_target_ratio, 0UL,
+				(unsigned long) (MAX_TARGET_RATIO-1));
+	if (set_target_ratio == 0 && new_target_ratio > 0) {
+		pr_info("Start idle injection to reduce power\n");
+		set_target_ratio = new_target_ratio;
+		ret = start_power_clamp();
+		goto exit_set;
+	} else	if (set_target_ratio > 0 && new_target_ratio == 0) {
+		pr_info("Stop forced idle injection\n");
+		end_power_clamp();
+		set_target_ratio = 0;
+	} else	/* adjust currently running */ {
+		set_target_ratio = new_target_ratio;
+		/* make new set_target_ratio visible to other cpus */
+		smp_mb();
+	}
+
+exit_set:
+	return ret;
+}
+
+/* bind to generic thermal layer as cooling device*/
+static struct thermal_cooling_device_ops powerclamp_cooling_ops = {
+	.get_max_state = powerclamp_get_max_state,
+	.get_cur_state = powerclamp_get_cur_state,
+	.set_cur_state = powerclamp_set_cur_state,
+};
+
+static const struct x86_cpu_id __initconst intel_powerclamp_ids[] = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_MWAIT },
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, intel_powerclamp_ids);
+
+static int __init powerclamp_probe(void)
+{
+
+	if (!x86_match_cpu(intel_powerclamp_ids)) {
+		pr_err("CPU does not support MWAIT\n");
+		return -ENODEV;
+	}
+
+	/* The goal for idle time alignment is to achieve package cstate. */
+	if (!has_pkg_state_counter()) {
+		pr_info("No package C-state available\n");
+		return -ENODEV;
+	}
+
+	/* find the deepest mwait value */
+	find_target_mwait();
+
+	return 0;
+}
+
+static int powerclamp_debug_show(struct seq_file *m, void *unused)
+{
+	int i = 0;
+
+	seq_printf(m, "controlling cpu: %d\n", control_cpu);
+	seq_printf(m, "pct confidence steady dynamic (compensation)\n");
+	for (i = 0; i < MAX_TARGET_RATIO; i++) {
+		seq_printf(m, "%d\t%lu\t%lu\t%lu\n",
+			i,
+			cal_data[i].confidence,
+			cal_data[i].steady_comp,
+			cal_data[i].dynamic_comp);
+	}
+
+	return 0;
+}
+
+DEFINE_SHOW_ATTRIBUTE(powerclamp_debug);
+
+static inline void powerclamp_create_debug_files(void)
+{
+	debug_dir = debugfs_create_dir("intel_powerclamp", NULL);
+	if (!debug_dir)
+		return;
+
+	if (!debugfs_create_file("powerclamp_calib", S_IRUGO, debug_dir,
+					cal_data, &powerclamp_debug_fops))
+		goto file_error;
+
+	return;
+
+file_error:
+	debugfs_remove_recursive(debug_dir);
+}
+
+static enum cpuhp_state hp_state;
+
+static int __init powerclamp_init(void)
+{
+	int retval;
+	int bitmap_size;
+
+	bitmap_size = BITS_TO_LONGS(num_possible_cpus()) * sizeof(long);
+	cpu_clamping_mask = kzalloc(bitmap_size, GFP_KERNEL);
+	if (!cpu_clamping_mask)
+		return -ENOMEM;
+
+	/* probe cpu features and ids here */
+	retval = powerclamp_probe();
+	if (retval)
+		goto exit_free;
+
+	/* set default limit, maybe adjusted during runtime based on feedback */
+	window_size = 2;
+	retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					   "thermal/intel_powerclamp:online",
+					   powerclamp_cpu_online,
+					   powerclamp_cpu_predown);
+	if (retval < 0)
+		goto exit_free;
+
+	hp_state = retval;
+
+	worker_data = alloc_percpu(struct powerclamp_worker_data);
+	if (!worker_data) {
+		retval = -ENOMEM;
+		goto exit_unregister;
+	}
+
+	cooling_dev = thermal_cooling_device_register("intel_powerclamp", NULL,
+						&powerclamp_cooling_ops);
+	if (IS_ERR(cooling_dev)) {
+		retval = -ENODEV;
+		goto exit_free_thread;
+	}
+
+	if (!duration)
+		duration = jiffies_to_msecs(DEFAULT_DURATION_JIFFIES);
+
+	powerclamp_create_debug_files();
+
+	return 0;
+
+exit_free_thread:
+	free_percpu(worker_data);
+exit_unregister:
+	cpuhp_remove_state_nocalls(hp_state);
+exit_free:
+	kfree(cpu_clamping_mask);
+	return retval;
+}
+module_init(powerclamp_init);
+
+static void __exit powerclamp_exit(void)
+{
+	end_power_clamp();
+	cpuhp_remove_state_nocalls(hp_state);
+	free_percpu(worker_data);
+	thermal_cooling_device_unregister(cooling_dev);
+	kfree(cpu_clamping_mask);
+
+	cancel_delayed_work_sync(&poll_pkg_cstate_work);
+	debugfs_remove_recursive(debug_dir);
+}
+module_exit(powerclamp_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
+MODULE_AUTHOR("Jacob Pan <jacob.jun.pan@linux.intel.com>");
+MODULE_DESCRIPTION("Package Level C-state Idle Injection for Intel CPUs");
diff --git a/drivers/thermal/intel/intel_quark_dts_thermal.c b/drivers/thermal/intel/intel_quark_dts_thermal.c
new file mode 100644
index 000000000000..5d33b350da1c
--- /dev/null
+++ b/drivers/thermal/intel/intel_quark_dts_thermal.c
@@ -0,0 +1,471 @@
+/*
+ * intel_quark_dts_thermal.c
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License 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.
+ *
+ * Contact Information:
+ *  Ong Boon Leong <boon.leong.ong@intel.com>
+ *  Intel Malaysia, Penang
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ *   * Redistributions of source code must retain the above copyright
+ *     notice, this list of conditions and the following disclaimer.
+ *   * Redistributions in binary form must reproduce the above copyright
+ *     notice, this list of conditions and the following disclaimer in
+ *     the documentation and/or other materials provided with the
+ *     distribution.
+ *   * Neither the name of Intel Corporation nor the names of its
+ *     contributors may be used to endorse or promote products derived
+ *     from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ * Quark DTS thermal driver is implemented by referencing
+ * intel_soc_dts_thermal.c.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <linux/thermal.h>
+#include <asm/cpu_device_id.h>
+#include <asm/iosf_mbi.h>
+
+#define X86_FAMILY_QUARK	0x5
+#define X86_MODEL_QUARK_X1000	0x9
+
+/* DTS reset is programmed via QRK_MBI_UNIT_SOC */
+#define QRK_DTS_REG_OFFSET_RESET	0x34
+#define QRK_DTS_RESET_BIT		BIT(0)
+
+/* DTS enable is programmed via QRK_MBI_UNIT_RMU */
+#define QRK_DTS_REG_OFFSET_ENABLE	0xB0
+#define QRK_DTS_ENABLE_BIT		BIT(15)
+
+/* Temperature Register is read via QRK_MBI_UNIT_RMU */
+#define QRK_DTS_REG_OFFSET_TEMP		0xB1
+#define QRK_DTS_MASK_TEMP		0xFF
+#define QRK_DTS_OFFSET_TEMP		0
+#define QRK_DTS_OFFSET_REL_TEMP		16
+#define QRK_DTS_TEMP_BASE		50
+
+/* Programmable Trip Point Register is configured via QRK_MBI_UNIT_RMU */
+#define QRK_DTS_REG_OFFSET_PTPS		0xB2
+#define QRK_DTS_MASK_TP_THRES		0xFF
+#define QRK_DTS_SHIFT_TP		8
+#define QRK_DTS_ID_TP_CRITICAL		0
+#define QRK_DTS_SAFE_TP_THRES		105
+
+/* Thermal Sensor Register Lock */
+#define QRK_DTS_REG_OFFSET_LOCK		0x71
+#define QRK_DTS_LOCK_BIT		BIT(5)
+
+/* Quark DTS has 2 trip points: hot & catastrophic */
+#define QRK_MAX_DTS_TRIPS	2
+/* If DTS not locked, all trip points are configurable */
+#define QRK_DTS_WR_MASK_SET	0x3
+/* If DTS locked, all trip points are not configurable */
+#define QRK_DTS_WR_MASK_CLR	0
+
+#define DEFAULT_POLL_DELAY	2000
+
+struct soc_sensor_entry {
+	bool locked;
+	u32 store_ptps;
+	u32 store_dts_enable;
+	enum thermal_device_mode mode;
+	struct thermal_zone_device *tzone;
+};
+
+static struct soc_sensor_entry *soc_dts;
+
+static int polling_delay = DEFAULT_POLL_DELAY;
+module_param(polling_delay, int, 0644);
+MODULE_PARM_DESC(polling_delay,
+	"Polling interval for checking trip points (in milliseconds)");
+
+static DEFINE_MUTEX(dts_update_mutex);
+
+static int soc_dts_enable(struct thermal_zone_device *tzd)
+{
+	u32 out;
+	struct soc_sensor_entry *aux_entry = tzd->devdata;
+	int ret;
+
+	ret = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+			    QRK_DTS_REG_OFFSET_ENABLE, &out);
+	if (ret)
+		return ret;
+
+	if (out & QRK_DTS_ENABLE_BIT) {
+		aux_entry->mode = THERMAL_DEVICE_ENABLED;
+		return 0;
+	}
+
+	if (!aux_entry->locked) {
+		out |= QRK_DTS_ENABLE_BIT;
+		ret = iosf_mbi_write(QRK_MBI_UNIT_RMU, MBI_REG_WRITE,
+				     QRK_DTS_REG_OFFSET_ENABLE, out);
+		if (ret)
+			return ret;
+
+		aux_entry->mode = THERMAL_DEVICE_ENABLED;
+	} else {
+		aux_entry->mode = THERMAL_DEVICE_DISABLED;
+		pr_info("DTS is locked. Cannot enable DTS\n");
+		ret = -EPERM;
+	}
+
+	return ret;
+}
+
+static int soc_dts_disable(struct thermal_zone_device *tzd)
+{
+	u32 out;
+	struct soc_sensor_entry *aux_entry = tzd->devdata;
+	int ret;
+
+	ret = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+			    QRK_DTS_REG_OFFSET_ENABLE, &out);
+	if (ret)
+		return ret;
+
+	if (!(out & QRK_DTS_ENABLE_BIT)) {
+		aux_entry->mode = THERMAL_DEVICE_DISABLED;
+		return 0;
+	}
+
+	if (!aux_entry->locked) {
+		out &= ~QRK_DTS_ENABLE_BIT;
+		ret = iosf_mbi_write(QRK_MBI_UNIT_RMU, MBI_REG_WRITE,
+				     QRK_DTS_REG_OFFSET_ENABLE, out);
+
+		if (ret)
+			return ret;
+
+		aux_entry->mode = THERMAL_DEVICE_DISABLED;
+	} else {
+		aux_entry->mode = THERMAL_DEVICE_ENABLED;
+		pr_info("DTS is locked. Cannot disable DTS\n");
+		ret = -EPERM;
+	}
+
+	return ret;
+}
+
+static int _get_trip_temp(int trip, int *temp)
+{
+	int status;
+	u32 out;
+
+	mutex_lock(&dts_update_mutex);
+	status = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+			       QRK_DTS_REG_OFFSET_PTPS, &out);
+	mutex_unlock(&dts_update_mutex);
+
+	if (status)
+		return status;
+
+	/*
+	 * Thermal Sensor Programmable Trip Point Register has 8-bit
+	 * fields for critical (catastrophic) and hot set trip point
+	 * thresholds. The threshold value is always offset by its
+	 * temperature base (50 degree Celsius).
+	 */
+	*temp = (out >> (trip * QRK_DTS_SHIFT_TP)) & QRK_DTS_MASK_TP_THRES;
+	*temp -= QRK_DTS_TEMP_BASE;
+
+	return 0;
+}
+
+static inline int sys_get_trip_temp(struct thermal_zone_device *tzd,
+				int trip, int *temp)
+{
+	return _get_trip_temp(trip, temp);
+}
+
+static inline int sys_get_crit_temp(struct thermal_zone_device *tzd, int *temp)
+{
+	return _get_trip_temp(QRK_DTS_ID_TP_CRITICAL, temp);
+}
+
+static int update_trip_temp(struct soc_sensor_entry *aux_entry,
+				int trip, int temp)
+{
+	u32 out;
+	u32 temp_out;
+	u32 store_ptps;
+	int ret;
+
+	mutex_lock(&dts_update_mutex);
+	if (aux_entry->locked) {
+		ret = -EPERM;
+		goto failed;
+	}
+
+	ret = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+			    QRK_DTS_REG_OFFSET_PTPS, &store_ptps);
+	if (ret)
+		goto failed;
+
+	/*
+	 * Protection against unsafe trip point thresdhold value.
+	 * As Quark X1000 data-sheet does not provide any recommendation
+	 * regarding the safe trip point threshold value to use, we choose
+	 * the safe value according to the threshold value set by UEFI BIOS.
+	 */
+	if (temp > QRK_DTS_SAFE_TP_THRES)
+		temp = QRK_DTS_SAFE_TP_THRES;
+
+	/*
+	 * Thermal Sensor Programmable Trip Point Register has 8-bit
+	 * fields for critical (catastrophic) and hot set trip point
+	 * thresholds. The threshold value is always offset by its
+	 * temperature base (50 degree Celsius).
+	 */
+	temp_out = temp + QRK_DTS_TEMP_BASE;
+	out = (store_ptps & ~(QRK_DTS_MASK_TP_THRES <<
+		(trip * QRK_DTS_SHIFT_TP)));
+	out |= (temp_out & QRK_DTS_MASK_TP_THRES) <<
+		(trip * QRK_DTS_SHIFT_TP);
+
+	ret = iosf_mbi_write(QRK_MBI_UNIT_RMU, MBI_REG_WRITE,
+			     QRK_DTS_REG_OFFSET_PTPS, out);
+
+failed:
+	mutex_unlock(&dts_update_mutex);
+	return ret;
+}
+
+static inline int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip,
+				int temp)
+{
+	return update_trip_temp(tzd->devdata, trip, temp);
+}
+
+static int sys_get_trip_type(struct thermal_zone_device *thermal,
+		int trip, enum thermal_trip_type *type)
+{
+	if (trip)
+		*type = THERMAL_TRIP_HOT;
+	else
+		*type = THERMAL_TRIP_CRITICAL;
+
+	return 0;
+}
+
+static int sys_get_curr_temp(struct thermal_zone_device *tzd,
+				int *temp)
+{
+	u32 out;
+	int ret;
+
+	mutex_lock(&dts_update_mutex);
+	ret = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+			    QRK_DTS_REG_OFFSET_TEMP, &out);
+	mutex_unlock(&dts_update_mutex);
+
+	if (ret)
+		return ret;
+
+	/*
+	 * Thermal Sensor Temperature Register has 8-bit field
+	 * for temperature value (offset by temperature base
+	 * 50 degree Celsius).
+	 */
+	out = (out >> QRK_DTS_OFFSET_TEMP) & QRK_DTS_MASK_TEMP;
+	*temp = out - QRK_DTS_TEMP_BASE;
+
+	return 0;
+}
+
+static int sys_get_mode(struct thermal_zone_device *tzd,
+				enum thermal_device_mode *mode)
+{
+	struct soc_sensor_entry *aux_entry = tzd->devdata;
+	*mode = aux_entry->mode;
+	return 0;
+}
+
+static int sys_set_mode(struct thermal_zone_device *tzd,
+				enum thermal_device_mode mode)
+{
+	int ret;
+
+	mutex_lock(&dts_update_mutex);
+	if (mode == THERMAL_DEVICE_ENABLED)
+		ret = soc_dts_enable(tzd);
+	else
+		ret = soc_dts_disable(tzd);
+	mutex_unlock(&dts_update_mutex);
+
+	return ret;
+}
+
+static struct thermal_zone_device_ops tzone_ops = {
+	.get_temp = sys_get_curr_temp,
+	.get_trip_temp = sys_get_trip_temp,
+	.get_trip_type = sys_get_trip_type,
+	.set_trip_temp = sys_set_trip_temp,
+	.get_crit_temp = sys_get_crit_temp,
+	.get_mode = sys_get_mode,
+	.set_mode = sys_set_mode,
+};
+
+static void free_soc_dts(struct soc_sensor_entry *aux_entry)
+{
+	if (aux_entry) {
+		if (!aux_entry->locked) {
+			mutex_lock(&dts_update_mutex);
+			iosf_mbi_write(QRK_MBI_UNIT_RMU, MBI_REG_WRITE,
+				       QRK_DTS_REG_OFFSET_ENABLE,
+				       aux_entry->store_dts_enable);
+
+			iosf_mbi_write(QRK_MBI_UNIT_RMU, MBI_REG_WRITE,
+				       QRK_DTS_REG_OFFSET_PTPS,
+				       aux_entry->store_ptps);
+			mutex_unlock(&dts_update_mutex);
+		}
+		thermal_zone_device_unregister(aux_entry->tzone);
+		kfree(aux_entry);
+	}
+}
+
+static struct soc_sensor_entry *alloc_soc_dts(void)
+{
+	struct soc_sensor_entry *aux_entry;
+	int err;
+	u32 out;
+	int wr_mask;
+
+	aux_entry = kzalloc(sizeof(*aux_entry), GFP_KERNEL);
+	if (!aux_entry) {
+		err = -ENOMEM;
+		return ERR_PTR(-ENOMEM);
+	}
+
+	/* Check if DTS register is locked */
+	err = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+			    QRK_DTS_REG_OFFSET_LOCK, &out);
+	if (err)
+		goto err_ret;
+
+	if (out & QRK_DTS_LOCK_BIT) {
+		aux_entry->locked = true;
+		wr_mask = QRK_DTS_WR_MASK_CLR;
+	} else {
+		aux_entry->locked = false;
+		wr_mask = QRK_DTS_WR_MASK_SET;
+	}
+
+	/* Store DTS default state if DTS registers are not locked */
+	if (!aux_entry->locked) {
+		/* Store DTS default enable for restore on exit */
+		err = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+				    QRK_DTS_REG_OFFSET_ENABLE,
+				    &aux_entry->store_dts_enable);
+		if (err)
+			goto err_ret;
+
+		/* Store DTS default PTPS register for restore on exit */
+		err = iosf_mbi_read(QRK_MBI_UNIT_RMU, MBI_REG_READ,
+				    QRK_DTS_REG_OFFSET_PTPS,
+				    &aux_entry->store_ptps);
+		if (err)
+			goto err_ret;
+	}
+
+	aux_entry->tzone = thermal_zone_device_register("quark_dts",
+			QRK_MAX_DTS_TRIPS,
+			wr_mask,
+			aux_entry, &tzone_ops, NULL, 0, polling_delay);
+	if (IS_ERR(aux_entry->tzone)) {
+		err = PTR_ERR(aux_entry->tzone);
+		goto err_ret;
+	}
+
+	mutex_lock(&dts_update_mutex);
+	err = soc_dts_enable(aux_entry->tzone);
+	mutex_unlock(&dts_update_mutex);
+	if (err)
+		goto err_aux_status;
+
+	return aux_entry;
+
+err_aux_status:
+	thermal_zone_device_unregister(aux_entry->tzone);
+err_ret:
+	kfree(aux_entry);
+	return ERR_PTR(err);
+}
+
+static const struct x86_cpu_id qrk_thermal_ids[] __initconst  = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_QUARK, X86_MODEL_QUARK_X1000 },
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, qrk_thermal_ids);
+
+static int __init intel_quark_thermal_init(void)
+{
+	int err = 0;
+
+	if (!x86_match_cpu(qrk_thermal_ids) || !iosf_mbi_available())
+		return -ENODEV;
+
+	soc_dts = alloc_soc_dts();
+	if (IS_ERR(soc_dts)) {
+		err = PTR_ERR(soc_dts);
+		goto err_free;
+	}
+
+	return 0;
+
+err_free:
+	free_soc_dts(soc_dts);
+	return err;
+}
+
+static void __exit intel_quark_thermal_exit(void)
+{
+	free_soc_dts(soc_dts);
+}
+
+module_init(intel_quark_thermal_init)
+module_exit(intel_quark_thermal_exit)
+
+MODULE_DESCRIPTION("Intel Quark DTS Thermal Driver");
+MODULE_AUTHOR("Ong Boon Leong <boon.leong.ong@intel.com>");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/drivers/thermal/intel/intel_soc_dts_iosf.c b/drivers/thermal/intel/intel_soc_dts_iosf.c
new file mode 100644
index 000000000000..e0813dfaa278
--- /dev/null
+++ b/drivers/thermal/intel/intel_soc_dts_iosf.c
@@ -0,0 +1,478 @@
+/*
+ * intel_soc_dts_iosf.c
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/module.h>
+#include <linux/slab.h>
+#include <linux/interrupt.h>
+#include <asm/iosf_mbi.h>
+#include "intel_soc_dts_iosf.h"
+
+#define SOC_DTS_OFFSET_ENABLE		0xB0
+#define SOC_DTS_OFFSET_TEMP		0xB1
+
+#define SOC_DTS_OFFSET_PTPS		0xB2
+#define SOC_DTS_OFFSET_PTTS		0xB3
+#define SOC_DTS_OFFSET_PTTSS		0xB4
+#define SOC_DTS_OFFSET_PTMC		0x80
+#define SOC_DTS_TE_AUX0			0xB5
+#define SOC_DTS_TE_AUX1			0xB6
+
+#define SOC_DTS_AUX0_ENABLE_BIT		BIT(0)
+#define SOC_DTS_AUX1_ENABLE_BIT		BIT(1)
+#define SOC_DTS_CPU_MODULE0_ENABLE_BIT	BIT(16)
+#define SOC_DTS_CPU_MODULE1_ENABLE_BIT	BIT(17)
+#define SOC_DTS_TE_SCI_ENABLE		BIT(9)
+#define SOC_DTS_TE_SMI_ENABLE		BIT(10)
+#define SOC_DTS_TE_MSI_ENABLE		BIT(11)
+#define SOC_DTS_TE_APICA_ENABLE		BIT(14)
+#define SOC_DTS_PTMC_APIC_DEASSERT_BIT	BIT(4)
+
+/* DTS encoding for TJ MAX temperature */
+#define SOC_DTS_TJMAX_ENCODING		0x7F
+
+/* Only 2 out of 4 is allowed for OSPM */
+#define SOC_MAX_DTS_TRIPS		2
+
+/* Mask for two trips in status bits */
+#define SOC_DTS_TRIP_MASK		0x03
+
+/* DTS0 and DTS 1 */
+#define SOC_MAX_DTS_SENSORS		2
+
+static int get_tj_max(u32 *tj_max)
+{
+	u32 eax, edx;
+	u32 val;
+	int err;
+
+	err = rdmsr_safe(MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+	if (err)
+		goto err_ret;
+	else {
+		val = (eax >> 16) & 0xff;
+		if (val)
+			*tj_max = val * 1000;
+		else {
+			err = -EINVAL;
+			goto err_ret;
+		}
+	}
+
+	return 0;
+err_ret:
+	*tj_max = 0;
+
+	return err;
+}
+
+static int sys_get_trip_temp(struct thermal_zone_device *tzd, int trip,
+			     int *temp)
+{
+	int status;
+	u32 out;
+	struct intel_soc_dts_sensor_entry *dts;
+	struct intel_soc_dts_sensors *sensors;
+
+	dts = tzd->devdata;
+	sensors = dts->sensors;
+	mutex_lock(&sensors->dts_update_lock);
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_OFFSET_PTPS, &out);
+	mutex_unlock(&sensors->dts_update_lock);
+	if (status)
+		return status;
+
+	out = (out >> (trip * 8)) & SOC_DTS_TJMAX_ENCODING;
+	if (!out)
+		*temp = 0;
+	else
+		*temp = sensors->tj_max - out * 1000;
+
+	return 0;
+}
+
+static int update_trip_temp(struct intel_soc_dts_sensor_entry *dts,
+			    int thres_index, int temp,
+			    enum thermal_trip_type trip_type)
+{
+	int status;
+	u32 temp_out;
+	u32 out;
+	u32 store_ptps;
+	u32 store_ptmc;
+	u32 store_te_out;
+	u32 te_out;
+	u32 int_enable_bit = SOC_DTS_TE_APICA_ENABLE;
+	struct intel_soc_dts_sensors *sensors = dts->sensors;
+
+	if (sensors->intr_type == INTEL_SOC_DTS_INTERRUPT_MSI)
+		int_enable_bit |= SOC_DTS_TE_MSI_ENABLE;
+
+	temp_out = (sensors->tj_max - temp) / 1000;
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_OFFSET_PTPS, &store_ptps);
+	if (status)
+		return status;
+
+	out = (store_ptps & ~(0xFF << (thres_index * 8)));
+	out |= (temp_out & 0xFF) << (thres_index * 8);
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+				SOC_DTS_OFFSET_PTPS, out);
+	if (status)
+		return status;
+
+	pr_debug("update_trip_temp PTPS = %x\n", out);
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_OFFSET_PTMC, &out);
+	if (status)
+		goto err_restore_ptps;
+
+	store_ptmc = out;
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_TE_AUX0 + thres_index,
+			       &te_out);
+	if (status)
+		goto err_restore_ptmc;
+
+	store_te_out = te_out;
+	/* Enable for CPU module 0 and module 1 */
+	out |= (SOC_DTS_CPU_MODULE0_ENABLE_BIT |
+					SOC_DTS_CPU_MODULE1_ENABLE_BIT);
+	if (temp) {
+		if (thres_index)
+			out |= SOC_DTS_AUX1_ENABLE_BIT;
+		else
+			out |= SOC_DTS_AUX0_ENABLE_BIT;
+		te_out |= int_enable_bit;
+	} else {
+		if (thres_index)
+			out &= ~SOC_DTS_AUX1_ENABLE_BIT;
+		else
+			out &= ~SOC_DTS_AUX0_ENABLE_BIT;
+		te_out &= ~int_enable_bit;
+	}
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+				SOC_DTS_OFFSET_PTMC, out);
+	if (status)
+		goto err_restore_te_out;
+
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+				SOC_DTS_TE_AUX0 + thres_index,
+				te_out);
+	if (status)
+		goto err_restore_te_out;
+
+	dts->trip_types[thres_index] = trip_type;
+
+	return 0;
+err_restore_te_out:
+	iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+		       SOC_DTS_OFFSET_PTMC, store_te_out);
+err_restore_ptmc:
+	iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+		       SOC_DTS_OFFSET_PTMC, store_ptmc);
+err_restore_ptps:
+	iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+		       SOC_DTS_OFFSET_PTPS, store_ptps);
+	/* Nothing we can do if restore fails */
+
+	return status;
+}
+
+static int sys_set_trip_temp(struct thermal_zone_device *tzd, int trip,
+			     int temp)
+{
+	struct intel_soc_dts_sensor_entry *dts = tzd->devdata;
+	struct intel_soc_dts_sensors *sensors = dts->sensors;
+	int status;
+
+	if (temp > sensors->tj_max)
+		return -EINVAL;
+
+	mutex_lock(&sensors->dts_update_lock);
+	status = update_trip_temp(tzd->devdata, trip, temp,
+				  dts->trip_types[trip]);
+	mutex_unlock(&sensors->dts_update_lock);
+
+	return status;
+}
+
+static int sys_get_trip_type(struct thermal_zone_device *tzd,
+			     int trip, enum thermal_trip_type *type)
+{
+	struct intel_soc_dts_sensor_entry *dts;
+
+	dts = tzd->devdata;
+
+	*type = dts->trip_types[trip];
+
+	return 0;
+}
+
+static int sys_get_curr_temp(struct thermal_zone_device *tzd,
+			     int *temp)
+{
+	int status;
+	u32 out;
+	struct intel_soc_dts_sensor_entry *dts;
+	struct intel_soc_dts_sensors *sensors;
+
+	dts = tzd->devdata;
+	sensors = dts->sensors;
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_OFFSET_TEMP, &out);
+	if (status)
+		return status;
+
+	out = (out & dts->temp_mask) >> dts->temp_shift;
+	out -= SOC_DTS_TJMAX_ENCODING;
+	*temp = sensors->tj_max - out * 1000;
+
+	return 0;
+}
+
+static struct thermal_zone_device_ops tzone_ops = {
+	.get_temp = sys_get_curr_temp,
+	.get_trip_temp = sys_get_trip_temp,
+	.get_trip_type = sys_get_trip_type,
+	.set_trip_temp = sys_set_trip_temp,
+};
+
+static int soc_dts_enable(int id)
+{
+	u32 out;
+	int ret;
+
+	ret = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			    SOC_DTS_OFFSET_ENABLE, &out);
+	if (ret)
+		return ret;
+
+	if (!(out & BIT(id))) {
+		out |= BIT(id);
+		ret = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+				     SOC_DTS_OFFSET_ENABLE, out);
+		if (ret)
+			return ret;
+	}
+
+	return ret;
+}
+
+static void remove_dts_thermal_zone(struct intel_soc_dts_sensor_entry *dts)
+{
+	if (dts) {
+		iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+			       SOC_DTS_OFFSET_ENABLE, dts->store_status);
+		thermal_zone_device_unregister(dts->tzone);
+	}
+}
+
+static int add_dts_thermal_zone(int id, struct intel_soc_dts_sensor_entry *dts,
+				bool notification_support, int trip_cnt,
+				int read_only_trip_cnt)
+{
+	char name[10];
+	int trip_count = 0;
+	int trip_mask = 0;
+	u32 store_ptps;
+	int ret;
+	int i;
+
+	/* Store status to restor on exit */
+	ret = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			    SOC_DTS_OFFSET_ENABLE, &dts->store_status);
+	if (ret)
+		goto err_ret;
+
+	dts->id = id;
+	dts->temp_mask = 0x00FF << (id * 8);
+	dts->temp_shift = id * 8;
+	if (notification_support) {
+		trip_count = min(SOC_MAX_DTS_TRIPS, trip_cnt);
+		trip_mask = BIT(trip_count - read_only_trip_cnt) - 1;
+	}
+
+	/* Check if the writable trip we provide is not used by BIOS */
+	ret = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			    SOC_DTS_OFFSET_PTPS, &store_ptps);
+	if (ret)
+		trip_mask = 0;
+	else {
+		for (i = 0; i < trip_count; ++i) {
+			if (trip_mask & BIT(i))
+				if (store_ptps & (0xff << (i * 8)))
+					trip_mask &= ~BIT(i);
+		}
+	}
+	dts->trip_mask = trip_mask;
+	dts->trip_count = trip_count;
+	snprintf(name, sizeof(name), "soc_dts%d", id);
+	dts->tzone = thermal_zone_device_register(name,
+						  trip_count,
+						  trip_mask,
+						  dts, &tzone_ops,
+						  NULL, 0, 0);
+	if (IS_ERR(dts->tzone)) {
+		ret = PTR_ERR(dts->tzone);
+		goto err_ret;
+	}
+
+	ret = soc_dts_enable(id);
+	if (ret)
+		goto err_enable;
+
+	return 0;
+err_enable:
+	thermal_zone_device_unregister(dts->tzone);
+err_ret:
+	return ret;
+}
+
+int intel_soc_dts_iosf_add_read_only_critical_trip(
+	struct intel_soc_dts_sensors *sensors, int critical_offset)
+{
+	int i, j;
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+		for (j = 0; j < sensors->soc_dts[i].trip_count; ++j) {
+			if (!(sensors->soc_dts[i].trip_mask & BIT(j))) {
+				return update_trip_temp(&sensors->soc_dts[i], j,
+					sensors->tj_max - critical_offset,
+					THERMAL_TRIP_CRITICAL);
+			}
+		}
+	}
+
+	return -EINVAL;
+}
+EXPORT_SYMBOL_GPL(intel_soc_dts_iosf_add_read_only_critical_trip);
+
+void intel_soc_dts_iosf_interrupt_handler(struct intel_soc_dts_sensors *sensors)
+{
+	u32 sticky_out;
+	int status;
+	u32 ptmc_out;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sensors->intr_notify_lock, flags);
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_OFFSET_PTMC, &ptmc_out);
+	ptmc_out |= SOC_DTS_PTMC_APIC_DEASSERT_BIT;
+	status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+				SOC_DTS_OFFSET_PTMC, ptmc_out);
+
+	status = iosf_mbi_read(BT_MBI_UNIT_PMC, MBI_REG_READ,
+			       SOC_DTS_OFFSET_PTTSS, &sticky_out);
+	pr_debug("status %d PTTSS %x\n", status, sticky_out);
+	if (sticky_out & SOC_DTS_TRIP_MASK) {
+		int i;
+		/* reset sticky bit */
+		status = iosf_mbi_write(BT_MBI_UNIT_PMC, MBI_REG_WRITE,
+					SOC_DTS_OFFSET_PTTSS, sticky_out);
+		spin_unlock_irqrestore(&sensors->intr_notify_lock, flags);
+
+		for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+			pr_debug("TZD update for zone %d\n", i);
+			thermal_zone_device_update(sensors->soc_dts[i].tzone,
+						   THERMAL_EVENT_UNSPECIFIED);
+		}
+	} else
+		spin_unlock_irqrestore(&sensors->intr_notify_lock, flags);
+}
+EXPORT_SYMBOL_GPL(intel_soc_dts_iosf_interrupt_handler);
+
+struct intel_soc_dts_sensors *intel_soc_dts_iosf_init(
+	enum intel_soc_dts_interrupt_type intr_type, int trip_count,
+	int read_only_trip_count)
+{
+	struct intel_soc_dts_sensors *sensors;
+	bool notification;
+	u32 tj_max;
+	int ret;
+	int i;
+
+	if (!iosf_mbi_available())
+		return ERR_PTR(-ENODEV);
+
+	if (!trip_count || read_only_trip_count > trip_count)
+		return ERR_PTR(-EINVAL);
+
+	if (get_tj_max(&tj_max))
+		return ERR_PTR(-EINVAL);
+
+	sensors = kzalloc(sizeof(*sensors), GFP_KERNEL);
+	if (!sensors)
+		return ERR_PTR(-ENOMEM);
+
+	spin_lock_init(&sensors->intr_notify_lock);
+	mutex_init(&sensors->dts_update_lock);
+	sensors->intr_type = intr_type;
+	sensors->tj_max = tj_max;
+	if (intr_type == INTEL_SOC_DTS_INTERRUPT_NONE)
+		notification = false;
+	else
+		notification = true;
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+		sensors->soc_dts[i].sensors = sensors;
+		ret = add_dts_thermal_zone(i, &sensors->soc_dts[i],
+					   notification, trip_count,
+					   read_only_trip_count);
+		if (ret)
+			goto err_free;
+	}
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+		ret = update_trip_temp(&sensors->soc_dts[i], 0, 0,
+				       THERMAL_TRIP_PASSIVE);
+		if (ret)
+			goto err_remove_zone;
+
+		ret = update_trip_temp(&sensors->soc_dts[i], 1, 0,
+				       THERMAL_TRIP_PASSIVE);
+		if (ret)
+			goto err_remove_zone;
+	}
+
+	return sensors;
+err_remove_zone:
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i)
+		remove_dts_thermal_zone(&sensors->soc_dts[i]);
+
+err_free:
+	kfree(sensors);
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_GPL(intel_soc_dts_iosf_init);
+
+void intel_soc_dts_iosf_exit(struct intel_soc_dts_sensors *sensors)
+{
+	int i;
+
+	for (i = 0; i < SOC_MAX_DTS_SENSORS; ++i) {
+		update_trip_temp(&sensors->soc_dts[i], 0, 0, 0);
+		update_trip_temp(&sensors->soc_dts[i], 1, 0, 0);
+		remove_dts_thermal_zone(&sensors->soc_dts[i]);
+	}
+	kfree(sensors);
+}
+EXPORT_SYMBOL_GPL(intel_soc_dts_iosf_exit);
+
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/intel_soc_dts_iosf.h b/drivers/thermal/intel/intel_soc_dts_iosf.h
new file mode 100644
index 000000000000..625e37bf93dc
--- /dev/null
+++ b/drivers/thermal/intel/intel_soc_dts_iosf.h
@@ -0,0 +1,62 @@
+/*
+ * intel_soc_dts_iosf.h
+ * Copyright (c) 2015, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+
+#ifndef _INTEL_SOC_DTS_IOSF_CORE_H
+#define _INTEL_SOC_DTS_IOSF_CORE_H
+
+#include <linux/thermal.h>
+
+/* DTS0 and DTS 1 */
+#define SOC_MAX_DTS_SENSORS	2
+
+enum intel_soc_dts_interrupt_type {
+	INTEL_SOC_DTS_INTERRUPT_NONE,
+	INTEL_SOC_DTS_INTERRUPT_APIC,
+	INTEL_SOC_DTS_INTERRUPT_MSI,
+	INTEL_SOC_DTS_INTERRUPT_SCI,
+	INTEL_SOC_DTS_INTERRUPT_SMI,
+};
+
+struct intel_soc_dts_sensors;
+
+struct intel_soc_dts_sensor_entry {
+	int id;
+	u32 temp_mask;
+	u32 temp_shift;
+	u32 store_status;
+	u32 trip_mask;
+	u32 trip_count;
+	enum thermal_trip_type trip_types[2];
+	struct thermal_zone_device *tzone;
+	struct intel_soc_dts_sensors *sensors;
+};
+
+struct intel_soc_dts_sensors {
+	u32 tj_max;
+	spinlock_t intr_notify_lock;
+	struct mutex dts_update_lock;
+	enum intel_soc_dts_interrupt_type intr_type;
+	struct intel_soc_dts_sensor_entry soc_dts[SOC_MAX_DTS_SENSORS];
+};
+
+struct intel_soc_dts_sensors *intel_soc_dts_iosf_init(
+	enum intel_soc_dts_interrupt_type intr_type, int trip_count,
+	int read_only_trip_count);
+void intel_soc_dts_iosf_exit(struct intel_soc_dts_sensors *sensors);
+void intel_soc_dts_iosf_interrupt_handler(
+				struct intel_soc_dts_sensors *sensors);
+int intel_soc_dts_iosf_add_read_only_critical_trip(
+	struct intel_soc_dts_sensors *sensors, int critical_offset);
+#endif
diff --git a/drivers/thermal/intel/intel_soc_dts_thermal.c b/drivers/thermal/intel/intel_soc_dts_thermal.c
new file mode 100644
index 000000000000..d748527d7a38
--- /dev/null
+++ b/drivers/thermal/intel/intel_soc_dts_thermal.c
@@ -0,0 +1,132 @@
+/*
+ * intel_soc_dts_thermal.c
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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/acpi.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <asm/cpu_device_id.h>
+#include <asm/intel-family.h>
+#include "intel_soc_dts_iosf.h"
+
+#define CRITICAL_OFFSET_FROM_TJ_MAX	5000
+
+static int crit_offset = CRITICAL_OFFSET_FROM_TJ_MAX;
+module_param(crit_offset, int, 0644);
+MODULE_PARM_DESC(crit_offset,
+	"Critical Temperature offset from tj max in millidegree Celsius.");
+
+/* IRQ 86 is a fixed APIC interrupt for BYT DTS Aux threshold notifications */
+#define BYT_SOC_DTS_APIC_IRQ	86
+
+static int soc_dts_thres_gsi;
+static int soc_dts_thres_irq;
+static struct intel_soc_dts_sensors *soc_dts;
+
+static irqreturn_t soc_irq_thread_fn(int irq, void *dev_data)
+{
+	pr_debug("proc_thermal_interrupt\n");
+	intel_soc_dts_iosf_interrupt_handler(soc_dts);
+
+	return IRQ_HANDLED;
+}
+
+static const struct x86_cpu_id soc_thermal_ids[] = {
+	{ X86_VENDOR_INTEL, 6, INTEL_FAM6_ATOM_SILVERMONT, 0,
+		BYT_SOC_DTS_APIC_IRQ},
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, soc_thermal_ids);
+
+static int __init intel_soc_thermal_init(void)
+{
+	int err = 0;
+	const struct x86_cpu_id *match_cpu;
+
+	match_cpu = x86_match_cpu(soc_thermal_ids);
+	if (!match_cpu)
+		return -ENODEV;
+
+	/* Create a zone with 2 trips with marked as read only */
+	soc_dts = intel_soc_dts_iosf_init(INTEL_SOC_DTS_INTERRUPT_APIC, 2, 1);
+	if (IS_ERR(soc_dts)) {
+		err = PTR_ERR(soc_dts);
+		return err;
+	}
+
+	soc_dts_thres_gsi = (int)match_cpu->driver_data;
+	if (soc_dts_thres_gsi) {
+		/*
+		 * Note the flags here MUST match the firmware defaults, rather
+		 * then the request_irq flags, otherwise we get an EBUSY error.
+		 */
+		soc_dts_thres_irq = acpi_register_gsi(NULL, soc_dts_thres_gsi,
+						      ACPI_LEVEL_SENSITIVE,
+						      ACPI_ACTIVE_LOW);
+		if (soc_dts_thres_irq < 0) {
+			pr_warn("intel_soc_dts: Could not get IRQ for GSI %d, err %d\n",
+				soc_dts_thres_gsi, soc_dts_thres_irq);
+			soc_dts_thres_irq = 0;
+		}
+	}
+
+	if (soc_dts_thres_irq) {
+		err = request_threaded_irq(soc_dts_thres_irq, NULL,
+					   soc_irq_thread_fn,
+					   IRQF_TRIGGER_RISING | IRQF_ONESHOT,
+					   "soc_dts", soc_dts);
+		if (err) {
+			/*
+			 * Do not just error out because the user space thermal
+			 * daemon such as DPTF may use polling instead of being
+			 * interrupt driven.
+			 */
+			pr_warn("request_threaded_irq ret %d\n", err);
+		}
+	}
+
+	err = intel_soc_dts_iosf_add_read_only_critical_trip(soc_dts,
+							     crit_offset);
+	if (err)
+		goto error_trips;
+
+	return 0;
+
+error_trips:
+	if (soc_dts_thres_irq) {
+		free_irq(soc_dts_thres_irq, soc_dts);
+		acpi_unregister_gsi(soc_dts_thres_gsi);
+	}
+	intel_soc_dts_iosf_exit(soc_dts);
+
+	return err;
+}
+
+static void __exit intel_soc_thermal_exit(void)
+{
+	if (soc_dts_thres_irq) {
+		free_irq(soc_dts_thres_irq, soc_dts);
+		acpi_unregister_gsi(soc_dts_thres_gsi);
+	}
+	intel_soc_dts_iosf_exit(soc_dts);
+}
+
+module_init(intel_soc_thermal_init)
+module_exit(intel_soc_thermal_exit)
+
+MODULE_DESCRIPTION("Intel SoC DTS Thermal Driver");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/thermal/intel/x86_pkg_temp_thermal.c b/drivers/thermal/intel/x86_pkg_temp_thermal.c
new file mode 100644
index 000000000000..1ef937d799e4
--- /dev/null
+++ b/drivers/thermal/intel/x86_pkg_temp_thermal.c
@@ -0,0 +1,558 @@
+/*
+ * x86_pkg_temp_thermal driver
+ * Copyright (c) 2013, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/param.h>
+#include <linux/device.h>
+#include <linux/platform_device.h>
+#include <linux/cpu.h>
+#include <linux/smp.h>
+#include <linux/slab.h>
+#include <linux/pm.h>
+#include <linux/thermal.h>
+#include <linux/debugfs.h>
+#include <asm/cpu_device_id.h>
+#include <asm/mce.h>
+
+/*
+* Rate control delay: Idea is to introduce denounce effect
+* This should be long enough to avoid reduce events, when
+* threshold is set to a temperature, which is constantly
+* violated, but at the short enough to take any action.
+* The action can be remove threshold or change it to next
+* interesting setting. Based on experiments, in around
+* every 5 seconds under load will give us a significant
+* temperature change.
+*/
+#define PKG_TEMP_THERMAL_NOTIFY_DELAY	5000
+static int notify_delay_ms = PKG_TEMP_THERMAL_NOTIFY_DELAY;
+module_param(notify_delay_ms, int, 0644);
+MODULE_PARM_DESC(notify_delay_ms,
+	"User space notification delay in milli seconds.");
+
+/* Number of trip points in thermal zone. Currently it can't
+* be more than 2. MSR can allow setting and getting notifications
+* for only 2 thresholds. This define enforces this, if there
+* is some wrong values returned by cpuid for number of thresholds.
+*/
+#define MAX_NUMBER_OF_TRIPS	2
+
+struct pkg_device {
+	int				cpu;
+	bool				work_scheduled;
+	u32				tj_max;
+	u32				msr_pkg_therm_low;
+	u32				msr_pkg_therm_high;
+	struct delayed_work		work;
+	struct thermal_zone_device	*tzone;
+	struct cpumask			cpumask;
+};
+
+static struct thermal_zone_params pkg_temp_tz_params = {
+	.no_hwmon	= true,
+};
+
+/* Keep track of how many package pointers we allocated in init() */
+static int max_packages __read_mostly;
+/* Array of package pointers */
+static struct pkg_device **packages;
+/* Serializes interrupt notification, work and hotplug */
+static DEFINE_SPINLOCK(pkg_temp_lock);
+/* Protects zone operation in the work function against hotplug removal */
+static DEFINE_MUTEX(thermal_zone_mutex);
+
+/* The dynamically assigned cpu hotplug state for module_exit() */
+static enum cpuhp_state pkg_thermal_hp_state __read_mostly;
+
+/* Debug counters to show using debugfs */
+static struct dentry *debugfs;
+static unsigned int pkg_interrupt_cnt;
+static unsigned int pkg_work_cnt;
+
+static int pkg_temp_debugfs_init(void)
+{
+	struct dentry *d;
+
+	debugfs = debugfs_create_dir("pkg_temp_thermal", NULL);
+	if (!debugfs)
+		return -ENOENT;
+
+	d = debugfs_create_u32("pkg_thres_interrupt", S_IRUGO, debugfs,
+			       &pkg_interrupt_cnt);
+	if (!d)
+		goto err_out;
+
+	d = debugfs_create_u32("pkg_thres_work", S_IRUGO, debugfs,
+			       &pkg_work_cnt);
+	if (!d)
+		goto err_out;
+
+	return 0;
+
+err_out:
+	debugfs_remove_recursive(debugfs);
+	return -ENOENT;
+}
+
+/*
+ * Protection:
+ *
+ * - cpu hotplug: Read serialized by cpu hotplug lock
+ *		  Write must hold pkg_temp_lock
+ *
+ * - Other callsites: Must hold pkg_temp_lock
+ */
+static struct pkg_device *pkg_temp_thermal_get_dev(unsigned int cpu)
+{
+	int pkgid = topology_logical_package_id(cpu);
+
+	if (pkgid >= 0 && pkgid < max_packages)
+		return packages[pkgid];
+	return NULL;
+}
+
+/*
+* tj-max is is interesting because threshold is set relative to this
+* temperature.
+*/
+static int get_tj_max(int cpu, u32 *tj_max)
+{
+	u32 eax, edx, val;
+	int err;
+
+	err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+	if (err)
+		return err;
+
+	val = (eax >> 16) & 0xff;
+	*tj_max = val * 1000;
+
+	return val ? 0 : -EINVAL;
+}
+
+static int sys_get_curr_temp(struct thermal_zone_device *tzd, int *temp)
+{
+	struct pkg_device *pkgdev = tzd->devdata;
+	u32 eax, edx;
+
+	rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_STATUS, &eax, &edx);
+	if (eax & 0x80000000) {
+		*temp = pkgdev->tj_max - ((eax >> 16) & 0x7f) * 1000;
+		pr_debug("sys_get_curr_temp %d\n", *temp);
+		return 0;
+	}
+	return -EINVAL;
+}
+
+static int sys_get_trip_temp(struct thermal_zone_device *tzd,
+			     int trip, int *temp)
+{
+	struct pkg_device *pkgdev = tzd->devdata;
+	unsigned long thres_reg_value;
+	u32 mask, shift, eax, edx;
+	int ret;
+
+	if (trip >= MAX_NUMBER_OF_TRIPS)
+		return -EINVAL;
+
+	if (trip) {
+		mask = THERM_MASK_THRESHOLD1;
+		shift = THERM_SHIFT_THRESHOLD1;
+	} else {
+		mask = THERM_MASK_THRESHOLD0;
+		shift = THERM_SHIFT_THRESHOLD0;
+	}
+
+	ret = rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
+			   &eax, &edx);
+	if (ret < 0)
+		return ret;
+
+	thres_reg_value = (eax & mask) >> shift;
+	if (thres_reg_value)
+		*temp = pkgdev->tj_max - thres_reg_value * 1000;
+	else
+		*temp = 0;
+	pr_debug("sys_get_trip_temp %d\n", *temp);
+
+	return 0;
+}
+
+static int
+sys_set_trip_temp(struct thermal_zone_device *tzd, int trip, int temp)
+{
+	struct pkg_device *pkgdev = tzd->devdata;
+	u32 l, h, mask, shift, intr;
+	int ret;
+
+	if (trip >= MAX_NUMBER_OF_TRIPS || temp >= pkgdev->tj_max)
+		return -EINVAL;
+
+	ret = rdmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT,
+			   &l, &h);
+	if (ret < 0)
+		return ret;
+
+	if (trip) {
+		mask = THERM_MASK_THRESHOLD1;
+		shift = THERM_SHIFT_THRESHOLD1;
+		intr = THERM_INT_THRESHOLD1_ENABLE;
+	} else {
+		mask = THERM_MASK_THRESHOLD0;
+		shift = THERM_SHIFT_THRESHOLD0;
+		intr = THERM_INT_THRESHOLD0_ENABLE;
+	}
+	l &= ~mask;
+	/*
+	* When users space sets a trip temperature == 0, which is indication
+	* that, it is no longer interested in receiving notifications.
+	*/
+	if (!temp) {
+		l &= ~intr;
+	} else {
+		l |= (pkgdev->tj_max - temp)/1000 << shift;
+		l |= intr;
+	}
+
+	return wrmsr_on_cpu(pkgdev->cpu, MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+}
+
+static int sys_get_trip_type(struct thermal_zone_device *thermal, int trip,
+			     enum thermal_trip_type *type)
+{
+	*type = THERMAL_TRIP_PASSIVE;
+	return 0;
+}
+
+/* Thermal zone callback registry */
+static struct thermal_zone_device_ops tzone_ops = {
+	.get_temp = sys_get_curr_temp,
+	.get_trip_temp = sys_get_trip_temp,
+	.get_trip_type = sys_get_trip_type,
+	.set_trip_temp = sys_set_trip_temp,
+};
+
+static bool pkg_thermal_rate_control(void)
+{
+	return true;
+}
+
+/* Enable threshold interrupt on local package/cpu */
+static inline void enable_pkg_thres_interrupt(void)
+{
+	u8 thres_0, thres_1;
+	u32 l, h;
+
+	rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+	/* only enable/disable if it had valid threshold value */
+	thres_0 = (l & THERM_MASK_THRESHOLD0) >> THERM_SHIFT_THRESHOLD0;
+	thres_1 = (l & THERM_MASK_THRESHOLD1) >> THERM_SHIFT_THRESHOLD1;
+	if (thres_0)
+		l |= THERM_INT_THRESHOLD0_ENABLE;
+	if (thres_1)
+		l |= THERM_INT_THRESHOLD1_ENABLE;
+	wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+}
+
+/* Disable threshold interrupt on local package/cpu */
+static inline void disable_pkg_thres_interrupt(void)
+{
+	u32 l, h;
+
+	rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+
+	l &= ~(THERM_INT_THRESHOLD0_ENABLE | THERM_INT_THRESHOLD1_ENABLE);
+	wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+}
+
+static void pkg_temp_thermal_threshold_work_fn(struct work_struct *work)
+{
+	struct thermal_zone_device *tzone = NULL;
+	int cpu = smp_processor_id();
+	struct pkg_device *pkgdev;
+	u64 msr_val, wr_val;
+
+	mutex_lock(&thermal_zone_mutex);
+	spin_lock_irq(&pkg_temp_lock);
+	++pkg_work_cnt;
+
+	pkgdev = pkg_temp_thermal_get_dev(cpu);
+	if (!pkgdev) {
+		spin_unlock_irq(&pkg_temp_lock);
+		mutex_unlock(&thermal_zone_mutex);
+		return;
+	}
+	pkgdev->work_scheduled = false;
+
+	rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
+	wr_val = msr_val & ~(THERM_LOG_THRESHOLD0 | THERM_LOG_THRESHOLD1);
+	if (wr_val != msr_val) {
+		wrmsrl(MSR_IA32_PACKAGE_THERM_STATUS, wr_val);
+		tzone = pkgdev->tzone;
+	}
+
+	enable_pkg_thres_interrupt();
+	spin_unlock_irq(&pkg_temp_lock);
+
+	/*
+	 * If tzone is not NULL, then thermal_zone_mutex will prevent the
+	 * concurrent removal in the cpu offline callback.
+	 */
+	if (tzone)
+		thermal_zone_device_update(tzone, THERMAL_EVENT_UNSPECIFIED);
+
+	mutex_unlock(&thermal_zone_mutex);
+}
+
+static void pkg_thermal_schedule_work(int cpu, struct delayed_work *work)
+{
+	unsigned long ms = msecs_to_jiffies(notify_delay_ms);
+
+	schedule_delayed_work_on(cpu, work, ms);
+}
+
+static int pkg_thermal_notify(u64 msr_val)
+{
+	int cpu = smp_processor_id();
+	struct pkg_device *pkgdev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pkg_temp_lock, flags);
+	++pkg_interrupt_cnt;
+
+	disable_pkg_thres_interrupt();
+
+	/* Work is per package, so scheduling it once is enough. */
+	pkgdev = pkg_temp_thermal_get_dev(cpu);
+	if (pkgdev && !pkgdev->work_scheduled) {
+		pkgdev->work_scheduled = true;
+		pkg_thermal_schedule_work(pkgdev->cpu, &pkgdev->work);
+	}
+
+	spin_unlock_irqrestore(&pkg_temp_lock, flags);
+	return 0;
+}
+
+static int pkg_temp_thermal_device_add(unsigned int cpu)
+{
+	int pkgid = topology_logical_package_id(cpu);
+	u32 tj_max, eax, ebx, ecx, edx;
+	struct pkg_device *pkgdev;
+	int thres_count, err;
+
+	if (pkgid >= max_packages)
+		return -ENOMEM;
+
+	cpuid(6, &eax, &ebx, &ecx, &edx);
+	thres_count = ebx & 0x07;
+	if (!thres_count)
+		return -ENODEV;
+
+	thres_count = clamp_val(thres_count, 0, MAX_NUMBER_OF_TRIPS);
+
+	err = get_tj_max(cpu, &tj_max);
+	if (err)
+		return err;
+
+	pkgdev = kzalloc(sizeof(*pkgdev), GFP_KERNEL);
+	if (!pkgdev)
+		return -ENOMEM;
+
+	INIT_DELAYED_WORK(&pkgdev->work, pkg_temp_thermal_threshold_work_fn);
+	pkgdev->cpu = cpu;
+	pkgdev->tj_max = tj_max;
+	pkgdev->tzone = thermal_zone_device_register("x86_pkg_temp",
+			thres_count,
+			(thres_count == MAX_NUMBER_OF_TRIPS) ? 0x03 : 0x01,
+			pkgdev, &tzone_ops, &pkg_temp_tz_params, 0, 0);
+	if (IS_ERR(pkgdev->tzone)) {
+		err = PTR_ERR(pkgdev->tzone);
+		kfree(pkgdev);
+		return err;
+	}
+	/* Store MSR value for package thermal interrupt, to restore at exit */
+	rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, pkgdev->msr_pkg_therm_low,
+	      pkgdev->msr_pkg_therm_high);
+
+	cpumask_set_cpu(cpu, &pkgdev->cpumask);
+	spin_lock_irq(&pkg_temp_lock);
+	packages[pkgid] = pkgdev;
+	spin_unlock_irq(&pkg_temp_lock);
+	return 0;
+}
+
+static int pkg_thermal_cpu_offline(unsigned int cpu)
+{
+	struct pkg_device *pkgdev = pkg_temp_thermal_get_dev(cpu);
+	bool lastcpu, was_target;
+	int target;
+
+	if (!pkgdev)
+		return 0;
+
+	target = cpumask_any_but(&pkgdev->cpumask, cpu);
+	cpumask_clear_cpu(cpu, &pkgdev->cpumask);
+	lastcpu = target >= nr_cpu_ids;
+	/*
+	 * Remove the sysfs files, if this is the last cpu in the package
+	 * before doing further cleanups.
+	 */
+	if (lastcpu) {
+		struct thermal_zone_device *tzone = pkgdev->tzone;
+
+		/*
+		 * We must protect against a work function calling
+		 * thermal_zone_update, after/while unregister. We null out
+		 * the pointer under the zone mutex, so the worker function
+		 * won't try to call.
+		 */
+		mutex_lock(&thermal_zone_mutex);
+		pkgdev->tzone = NULL;
+		mutex_unlock(&thermal_zone_mutex);
+
+		thermal_zone_device_unregister(tzone);
+	}
+
+	/* Protect against work and interrupts */
+	spin_lock_irq(&pkg_temp_lock);
+
+	/*
+	 * Check whether this cpu was the current target and store the new
+	 * one. When we drop the lock, then the interrupt notify function
+	 * will see the new target.
+	 */
+	was_target = pkgdev->cpu == cpu;
+	pkgdev->cpu = target;
+
+	/*
+	 * If this is the last CPU in the package remove the package
+	 * reference from the array and restore the interrupt MSR. When we
+	 * drop the lock neither the interrupt notify function nor the
+	 * worker will see the package anymore.
+	 */
+	if (lastcpu) {
+		packages[topology_logical_package_id(cpu)] = NULL;
+		/* After this point nothing touches the MSR anymore. */
+		wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
+		      pkgdev->msr_pkg_therm_low, pkgdev->msr_pkg_therm_high);
+	}
+
+	/*
+	 * Check whether there is work scheduled and whether the work is
+	 * targeted at the outgoing CPU.
+	 */
+	if (pkgdev->work_scheduled && was_target) {
+		/*
+		 * To cancel the work we need to drop the lock, otherwise
+		 * we might deadlock if the work needs to be flushed.
+		 */
+		spin_unlock_irq(&pkg_temp_lock);
+		cancel_delayed_work_sync(&pkgdev->work);
+		spin_lock_irq(&pkg_temp_lock);
+		/*
+		 * If this is not the last cpu in the package and the work
+		 * did not run after we dropped the lock above, then we
+		 * need to reschedule the work, otherwise the interrupt
+		 * stays disabled forever.
+		 */
+		if (!lastcpu && pkgdev->work_scheduled)
+			pkg_thermal_schedule_work(target, &pkgdev->work);
+	}
+
+	spin_unlock_irq(&pkg_temp_lock);
+
+	/* Final cleanup if this is the last cpu */
+	if (lastcpu)
+		kfree(pkgdev);
+	return 0;
+}
+
+static int pkg_thermal_cpu_online(unsigned int cpu)
+{
+	struct pkg_device *pkgdev = pkg_temp_thermal_get_dev(cpu);
+	struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+	/* Paranoia check */
+	if (!cpu_has(c, X86_FEATURE_DTHERM) || !cpu_has(c, X86_FEATURE_PTS))
+		return -ENODEV;
+
+	/* If the package exists, nothing to do */
+	if (pkgdev) {
+		cpumask_set_cpu(cpu, &pkgdev->cpumask);
+		return 0;
+	}
+	return pkg_temp_thermal_device_add(cpu);
+}
+
+static const struct x86_cpu_id __initconst pkg_temp_thermal_ids[] = {
+	{ X86_VENDOR_INTEL, X86_FAMILY_ANY, X86_MODEL_ANY, X86_FEATURE_PTS },
+	{}
+};
+MODULE_DEVICE_TABLE(x86cpu, pkg_temp_thermal_ids);
+
+static int __init pkg_temp_thermal_init(void)
+{
+	int ret;
+
+	if (!x86_match_cpu(pkg_temp_thermal_ids))
+		return -ENODEV;
+
+	max_packages = topology_max_packages();
+	packages = kcalloc(max_packages, sizeof(struct pkg_device *),
+			   GFP_KERNEL);
+	if (!packages)
+		return -ENOMEM;
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "thermal/x86_pkg:online",
+				pkg_thermal_cpu_online,	pkg_thermal_cpu_offline);
+	if (ret < 0)
+		goto err;
+
+	/* Store the state for module exit */
+	pkg_thermal_hp_state = ret;
+
+	platform_thermal_package_notify = pkg_thermal_notify;
+	platform_thermal_package_rate_control = pkg_thermal_rate_control;
+
+	 /* Don't care if it fails */
+	pkg_temp_debugfs_init();
+	return 0;
+
+err:
+	kfree(packages);
+	return ret;
+}
+module_init(pkg_temp_thermal_init)
+
+static void __exit pkg_temp_thermal_exit(void)
+{
+	platform_thermal_package_notify = NULL;
+	platform_thermal_package_rate_control = NULL;
+
+	cpuhp_remove_state(pkg_thermal_hp_state);
+	debugfs_remove_recursive(debugfs);
+	kfree(packages);
+}
+module_exit(pkg_temp_thermal_exit)
+
+MODULE_DESCRIPTION("X86 PKG TEMP Thermal Driver");
+MODULE_AUTHOR("Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>");
+MODULE_LICENSE("GPL v2");