Merge branch 'x86-hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-hwmon-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
  x86, hwmon: Package Level Thermal/Power: pkgtemp documentation
  x86, hwmon: Package Level Thermal/Power: power limit
  x86, hwmon: Package Level Thermal/Power: thermal throttling handler
  x86, hwmon: Package Level Thermal/Power: pkgtemp hwmon driver

7 files changed, 669 insertions, 39 deletions

diff --git a/Documentation/hwmon/pkgtemp b/Documentation/hwmon/pkgtemp
new file mode 100644
index 000000000000..c8e1fb0fadd3
--- /dev/null
+++ b/Documentation/hwmon/pkgtemp
@@ -0,0 +1,36 @@
+Kernel driver pkgtemp
+======================
+
+Supported chips:
+  * Intel family
+    Prefix: 'pkgtemp'
+    CPUID:
+    Datasheet: Intel 64 and IA-32 Architectures Software Developer's Manual
+               Volume 3A: System Programming Guide
+
+Author: Fenghua Yu
+
+Description
+-----------
+
+This driver permits reading package level temperature sensor embedded inside
+Intel CPU package. The sensors can be in core, uncore, memory controller, or
+other components in a package. The feature is first implemented in Intel Sandy
+Bridge platform.
+
+Temperature is measured in degrees Celsius and measurement resolution is
+1 degree C. Valid temperatures are from 0 to TjMax degrees C, because the actual
+value of temperature register is in fact a delta from TjMax.
+
+Temperature known as TjMax is the maximum junction temperature of package.
+We get this from MSR_IA32_TEMPERATURE_TARGET. If the MSR is not accessible,
+we define TjMax as 100 degrees Celsius. At this temperature, protection
+mechanism will perform actions to forcibly cool down the package. Alarm
+may be raised, if the temperature grows enough (more than TjMax) to trigger
+the Out-Of-Spec bit. Following table summarizes the exported sysfs files:
+
+temp1_input       - Package temperature (in millidegrees Celsius).
+temp1_max        - All cooling devices should be turned on.
+temp1_crit        - Maximum junction temperature (in millidegrees Celsius).
+temp1_crit_alarm - Set when Out-of-spec bit is set, never clears.
+                    Correct CPU operation is no longer guaranteed.
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index d28fad19654a..e3a32431ca1e 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1471,6 +1471,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_CORETEMP is not set
+# CONFIG_SENSORS_PKGTEMP is not set
 # CONFIG_SENSORS_IT87 is not set
 # CONFIG_SENSORS_LM63 is not set
 # CONFIG_SENSORS_LM75 is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 6c86acd847a4..4251f8372050 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -1456,6 +1456,7 @@ CONFIG_HWMON=y
 # CONFIG_SENSORS_GL518SM is not set
 # CONFIG_SENSORS_GL520SM is not set
 # CONFIG_SENSORS_CORETEMP is not set
+# CONFIG_SENSORS_PKGTEMP is not set
 # CONFIG_SENSORS_IT87 is not set
 # CONFIG_SENSORS_LM63 is not set
 # CONFIG_SENSORS_LM75 is not set
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index e1a0a3bf9716..c2a8b26d4fea 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -34,15 +34,25 @@
 /* How long to wait between reporting thermal events */
 #define CHECK_INTERVAL          (300 * HZ)
 
+#define THERMAL_THROTTLING_EVENT        0
+#define POWER_LIMIT_EVENT               1
+
 /*
- * Current thermal throttling state:
+ * Current thermal event state:
  */
-struct thermal_state {
-        bool                    is_throttled;
-
+struct _thermal_state {
+        bool                    new_event;
+        int                     event;
         u64                     next_check;
-        unsigned long           throttle_count;
-        unsigned long           last_throttle_count;
+        unsigned long           count;
+        unsigned long           last_count;
+};
+
+struct thermal_state {
+        struct _thermal_state core_throttle;
+        struct _thermal_state core_power_limit;
+        struct _thermal_state package_throttle;
+        struct _thermal_state package_power_limit;
 };
 
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
@@ -53,11 +63,13 @@ static u32 lvtthmr_init __read_mostly;
 
 #ifdef CONFIG_SYSFS
 #define define_therm_throt_sysdev_one_ro(_name)                         \
-        static SYSDEV_ATTR(_name, 0444, therm_throt_sysdev_show_##_name, NULL)
+        static SYSDEV_ATTR(_name, 0444,                                 \
+                           therm_throt_sysdev_show_##_name,             \
+                                   NULL)                                \
 
-#define define_therm_throt_sysdev_show_func(name)                       \
+#define define_therm_throt_sysdev_show_func(event, name)                \
                                                                         \
-static ssize_t therm_throt_sysdev_show_##name(                          \
+static ssize_t therm_throt_sysdev_show_##event##_##name(                \
                         struct sys_device *dev,                         \
                         struct sysdev_attribute *attr,                  \
                         char *buf)                                      \
@@ -66,30 +78,42 @@ static ssize_t therm_throt_sysdev_show_##name(				\
         ssize_t ret;                                                    \
                                                                         \
         preempt_disable();      /* CPU hotplug */                       \
-        if (cpu_online(cpu))                                            \
+        if (cpu_online(cpu)) {                                          \
                 ret = sprintf(buf, "%lu\n",                             \
-                              per_cpu(thermal_state, cpu).name);        \
-        else                                                            \
+                              per_cpu(thermal_state, cpu).event.name);  \
+        } else                                                          \
                 ret = 0;                                                \
         preempt_enable();                                               \
                                                                         \
         return ret;                                                     \
 }
 
-define_therm_throt_sysdev_show_func(throttle_count);
-define_therm_throt_sysdev_one_ro(throttle_count);
+define_therm_throt_sysdev_show_func(core_throttle, count);
+define_therm_throt_sysdev_one_ro(core_throttle_count);
+
+define_therm_throt_sysdev_show_func(core_power_limit, count);
+define_therm_throt_sysdev_one_ro(core_power_limit_count);
+
+define_therm_throt_sysdev_show_func(package_throttle, count);
+define_therm_throt_sysdev_one_ro(package_throttle_count);
+
+define_therm_throt_sysdev_show_func(package_power_limit, count);
+define_therm_throt_sysdev_one_ro(package_power_limit_count);
 
 static struct attribute *thermal_throttle_attrs[] = {
-        &attr_throttle_count.attr,
+        &attr_core_throttle_count.attr,
         NULL
 };
 
-static struct attribute_group thermal_throttle_attr_group = {
+static struct attribute_group thermal_attr_group = {
         .attrs  = thermal_throttle_attrs,
         .name   = "thermal_throttle"
 };
 #endif /* CONFIG_SYSFS */
 
+#define CORE_LEVEL      0
+#define PACKAGE_LEVEL   1
+
 /***
  * therm_throt_process - Process thermal throttling event from interrupt
  * @curr: Whether the condition is current or not (boolean), since the
@@ -106,39 +130,70 @@ static struct attribute_group thermal_throttle_attr_group = {
  *          1 : Event should be logged further, and a message has been
  *              printed to the syslog.
  */
-static int therm_throt_process(bool is_throttled)
+static int therm_throt_process(bool new_event, int event, int level)
 {
-        struct thermal_state *state;
-        unsigned int this_cpu;
-        bool was_throttled;
+        struct _thermal_state *state;
+        unsigned int this_cpu = smp_processor_id();
+        bool old_event;
         u64 now;
+        struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
 
-        this_cpu = smp_processor_id();
         now = get_jiffies_64();
-        state = &per_cpu(thermal_state, this_cpu);
+        if (level == CORE_LEVEL) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        state = &pstate->core_throttle;
+                else if (event == POWER_LIMIT_EVENT)
+                        state = &pstate->core_power_limit;
+                else
+                         return 0;
+        } else if (level == PACKAGE_LEVEL) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        state = &pstate->package_throttle;
+                else if (event == POWER_LIMIT_EVENT)
+                        state = &pstate->package_power_limit;
+                else
+                        return 0;
+        } else
+                return 0;
 
-        was_throttled = state->is_throttled;
-        state->is_throttled = is_throttled;
+        old_event = state->new_event;
+        state->new_event = new_event;
 
-        if (is_throttled)
-                state->throttle_count++;
+        if (new_event)
+                state->count++;
 
         if (time_before64(now, state->next_check) &&
-                        state->throttle_count != state->last_throttle_count)
+                        state->count != state->last_count)
                 return 0;
 
         state->next_check = now + CHECK_INTERVAL;
-        state->last_throttle_count = state->throttle_count;
+        state->last_count = state->count;
 
         /* if we just entered the thermal event */
-        if (is_throttled) {
-                printk(KERN_CRIT "CPU%d: Temperature above threshold, cpu clock throttled (total events = %lu)\n", this_cpu, state->throttle_count);
+        if (new_event) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        printk(KERN_CRIT "CPU%d: %s temperature above threshold, cpu clock throttled (total events = %lu)\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package",
+                                state->count);
+                else
+                        printk(KERN_CRIT "CPU%d: %s power limit notification (total events = %lu)\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package",
+                                state->count);
 
                 add_taint(TAINT_MACHINE_CHECK);
                 return 1;
         }
-        if (was_throttled) {
-                printk(KERN_INFO "CPU%d: Temperature/speed normal\n", this_cpu);
+        if (old_event) {
+                if (event == THERMAL_THROTTLING_EVENT)
+                        printk(KERN_INFO "CPU%d: %s temperature/speed normal\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package");
+                else
+                        printk(KERN_INFO "CPU%d: %s power limit normal\n",
+                                this_cpu,
+                                level == CORE_LEVEL ? "Core" : "Package");
                 return 1;
         }
 
@@ -149,13 +204,32 @@ static int therm_throt_process(bool is_throttled)
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
 {
-        return sysfs_create_group(&sys_dev->kobj,
-                                  &thermal_throttle_attr_group);
+        int err;
+        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+
+        err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
+        if (err)
+                return err;
+
+        if (cpu_has(c, X86_FEATURE_PLN))
+                err = sysfs_add_file_to_group(&sys_dev->kobj,
+                                              &attr_core_power_limit_count.attr,
+                                              thermal_attr_group.name);
+        if (cpu_has(c, X86_FEATURE_PTS))
+                err = sysfs_add_file_to_group(&sys_dev->kobj,
+                                              &attr_package_throttle_count.attr,
+                                              thermal_attr_group.name);
+                if (cpu_has(c, X86_FEATURE_PLN))
+                        err = sysfs_add_file_to_group(&sys_dev->kobj,
+                                        &attr_package_power_limit_count.attr,
+                                        thermal_attr_group.name);
+
+        return err;
 }
 
 static __cpuinit void thermal_throttle_remove_dev(struct sys_device *sys_dev)
 {
-        sysfs_remove_group(&sys_dev->kobj, &thermal_throttle_attr_group);
+        sysfs_remove_group(&sys_dev->kobj, &thermal_attr_group);
 }
 
 /* Mutex protecting device creation against CPU hotplug: */
@@ -226,14 +300,50 @@ device_initcall(thermal_throttle_init_device);
 
 #endif /* CONFIG_SYSFS */
 
+/*
+ * Set up the most two significant bit to notify mce log that this thermal
+ * event type.
+ * This is a temp solution. May be changed in the future with mce log
+ * infrasture.
+ */
+#define CORE_THROTTLED          (0)
+#define CORE_POWER_LIMIT        ((__u64)1 << 62)
+#define PACKAGE_THROTTLED       ((__u64)2 << 62)
+#define PACKAGE_POWER_LIMIT     ((__u64)3 << 62)
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
         __u64 msr_val;
+        struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
 
         rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
-        if (therm_throt_process((msr_val & THERM_STATUS_PROCHOT) != 0))
-                mce_log_therm_throt_event(msr_val);
+
+        if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
+                                THERMAL_THROTTLING_EVENT,
+                                CORE_LEVEL) != 0)
+                mce_log_therm_throt_event(CORE_THROTTLED | msr_val);
+
+        if (cpu_has(c, X86_FEATURE_PLN))
+                if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT,
+                                        POWER_LIMIT_EVENT,
+                                        CORE_LEVEL) != 0)
+                        mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val);
+
+        if (cpu_has(c, X86_FEATURE_PTS)) {
+                rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
+                if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
+                                        THERMAL_THROTTLING_EVENT,
+                                        PACKAGE_LEVEL) != 0)
+                        mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val);
+                if (cpu_has(c, X86_FEATURE_PLN))
+                        if (therm_throt_process(msr_val &
+                                        PACKAGE_THERM_STATUS_POWER_LIMIT,
+                                        POWER_LIMIT_EVENT,
+                                        PACKAGE_LEVEL) != 0)
+                                mce_log_therm_throt_event(PACKAGE_POWER_LIMIT
+                                                          | msr_val);
+        }
 }
 
 static void unexpected_thermal_interrupt(void)
@@ -335,8 +445,26 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
         apic_write(APIC_LVTTHMR, h);
 
         rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
-        wrmsr(MSR_IA32_THERM_INTERRUPT,
-                l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h);
+        if (cpu_has(c, X86_FEATURE_PLN))
+                wrmsr(MSR_IA32_THERM_INTERRUPT,
+                      l | (THERM_INT_LOW_ENABLE
+                        | THERM_INT_HIGH_ENABLE | THERM_INT_PLN_ENABLE), h);
+        else
+                wrmsr(MSR_IA32_THERM_INTERRUPT,
+                      l | (THERM_INT_LOW_ENABLE | THERM_INT_HIGH_ENABLE), h);
+
+        if (cpu_has(c, X86_FEATURE_PTS)) {
+                rdmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT, l, h);
+                if (cpu_has(c, X86_FEATURE_PLN))
+                        wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
+                              l | (PACKAGE_THERM_INT_LOW_ENABLE
+                                | PACKAGE_THERM_INT_HIGH_ENABLE
+                                | PACKAGE_THERM_INT_PLN_ENABLE), h);
+                else
+                        wrmsr(MSR_IA32_PACKAGE_THERM_INTERRUPT,
+                              l | (PACKAGE_THERM_INT_LOW_ENABLE
+                                | PACKAGE_THERM_INT_HIGH_ENABLE), h);
+        }
 
         smp_thermal_vector = intel_thermal_interrupt;
 
diff --git a/drivers/hwmon/Kconfig b/drivers/hwmon/Kconfig
index c57e530d07c7..4d382ae53092 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -407,6 +407,13 @@ config SENSORS_CORETEMP
           sensor inside your CPU. Most of the family 6 CPUs
           are supported. Check documentation/driver for details.
 
+config SENSORS_PKGTEMP
+        tristate "Intel processor package temperature sensor"
+        depends on X86 && PCI && EXPERIMENTAL
+        help
+          If you say yes here you get support for the package level temperature
+          sensor inside your CPU. Check documentation/driver for details.
+
 config SENSORS_IBMAEM
         tristate "IBM Active Energy Manager temperature/power sensors and control"
         select IPMI_SI
diff --git a/drivers/hwmon/Makefile b/drivers/hwmon/Makefile
index c5057745b068..9103bd6ea73a 100644
--- a/drivers/hwmon/Makefile
+++ b/drivers/hwmon/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_SENSORS_AMS)	+= ams/
 obj-$(CONFIG_SENSORS_ASC7621)   += asc7621.o
 obj-$(CONFIG_SENSORS_ATXP1)     += atxp1.o
 obj-$(CONFIG_SENSORS_CORETEMP)  += coretemp.o
+obj-$(CONFIG_SENSORS_PKGTEMP)   += pkgtemp.o
 obj-$(CONFIG_SENSORS_DME1737)   += dme1737.o
 obj-$(CONFIG_SENSORS_DS1621)    += ds1621.o
 obj-$(CONFIG_SENSORS_EMC1403)   += emc1403.o
diff --git a/drivers/hwmon/pkgtemp.c b/drivers/hwmon/pkgtemp.c
new file mode 100644
index 000000000000..74157fcda6ed
--- /dev/null
+++ b/drivers/hwmon/pkgtemp.c
@@ -0,0 +1,456 @@
+/*
+ * pkgtemp.c - Linux kernel module for processor package hardware monitoring
+ *
+ * Copyright (C) 2010 Fenghua Yu <fenghua.yu@intel.com>
+ *
+ * Inspired from many hwmon drivers especially coretemp.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
+ * 02110-1301 USA.
+ */
+
+#include <linux/module.h>
+#include <linux/delay.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/jiffies.h>
+#include <linux/hwmon.h>
+#include <linux/sysfs.h>
+#include <linux/hwmon-sysfs.h>
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/list.h>
+#include <linux/platform_device.h>
+#include <linux/cpu.h>
+#include <linux/pci.h>
+#include <asm/msr.h>
+#include <asm/processor.h>
+
+#define DRVNAME "pkgtemp"
+
+enum { SHOW_TEMP, SHOW_TJMAX, SHOW_TTARGET, SHOW_LABEL, SHOW_NAME };
+
+/*
+ * Functions declaration
+ */
+
+static struct pkgtemp_data *pkgtemp_update_device(struct device *dev);
+
+struct pkgtemp_data {
+        struct device *hwmon_dev;
+        struct mutex update_lock;
+        const char *name;
+        u32 id;
+        u16 phys_proc_id;
+        char valid;             /* zero until following fields are valid */
+        unsigned long last_updated;     /* in jiffies */
+        int temp;
+        int tjmax;
+        int ttarget;
+        u8 alarm;
+};
+
+/*
+ * Sysfs stuff
+ */
+
+static ssize_t show_name(struct device *dev, struct device_attribute
+                          *devattr, char *buf)
+{
+        int ret;
+        struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+        struct pkgtemp_data *data = dev_get_drvdata(dev);
+
+        if (attr->index == SHOW_NAME)
+                ret = sprintf(buf, "%s\n", data->name);
+        else    /* show label */
+                ret = sprintf(buf, "physical id %d\n",
+                              data->phys_proc_id);
+        return ret;
+}
+
+static ssize_t show_alarm(struct device *dev, struct device_attribute
+                          *devattr, char *buf)
+{
+        struct pkgtemp_data *data = pkgtemp_update_device(dev);
+        /* read the Out-of-spec log, never clear */
+        return sprintf(buf, "%d\n", data->alarm);
+}
+
+static ssize_t show_temp(struct device *dev,
+                         struct device_attribute *devattr, char *buf)
+{
+        struct sensor_device_attribute *attr = to_sensor_dev_attr(devattr);
+        struct pkgtemp_data *data = pkgtemp_update_device(dev);
+        int err = 0;
+
+        if (attr->index == SHOW_TEMP)
+                err = data->valid ? sprintf(buf, "%d\n", data->temp) : -EAGAIN;
+        else if (attr->index == SHOW_TJMAX)
+                err = sprintf(buf, "%d\n", data->tjmax);
+        else
+                err = sprintf(buf, "%d\n", data->ttarget);
+        return err;
+}
+
+static SENSOR_DEVICE_ATTR(temp1_input, S_IRUGO, show_temp, NULL, SHOW_TEMP);
+static SENSOR_DEVICE_ATTR(temp1_crit, S_IRUGO, show_temp, NULL, SHOW_TJMAX);
+static SENSOR_DEVICE_ATTR(temp1_max, S_IRUGO, show_temp, NULL, SHOW_TTARGET);
+static DEVICE_ATTR(temp1_crit_alarm, S_IRUGO, show_alarm, NULL);
+static SENSOR_DEVICE_ATTR(temp1_label, S_IRUGO, show_name, NULL, SHOW_LABEL);
+static SENSOR_DEVICE_ATTR(name, S_IRUGO, show_name, NULL, SHOW_NAME);
+
+static struct attribute *pkgtemp_attributes[] = {
+        &sensor_dev_attr_name.dev_attr.attr,
+        &sensor_dev_attr_temp1_label.dev_attr.attr,
+        &dev_attr_temp1_crit_alarm.attr,
+        &sensor_dev_attr_temp1_input.dev_attr.attr,
+        &sensor_dev_attr_temp1_crit.dev_attr.attr,
+        NULL
+};
+
+static const struct attribute_group pkgtemp_group = {
+        .attrs = pkgtemp_attributes,
+};
+
+static struct pkgtemp_data *pkgtemp_update_device(struct device *dev)
+{
+        struct pkgtemp_data *data = dev_get_drvdata(dev);
+        unsigned int cpu;
+        int err;
+
+        mutex_lock(&data->update_lock);
+
+        if (!data->valid || time_after(jiffies, data->last_updated + HZ)) {
+                u32 eax, edx;
+
+                data->valid = 0;
+                cpu = data->id;
+                err = rdmsr_on_cpu(cpu, MSR_IA32_PACKAGE_THERM_STATUS,
+                                   &eax, &edx);
+                if (!err) {
+                        data->alarm = (eax >> 5) & 1;
+                        data->temp = data->tjmax - (((eax >> 16)
+                                                        & 0x7f) * 1000);
+                        data->valid = 1;
+                } else
+                        dev_dbg(dev, "Temperature data invalid (0x%x)\n", eax);
+
+                data->last_updated = jiffies;
+        }
+
+        mutex_unlock(&data->update_lock);
+        return data;
+}
+
+static int get_tjmax(int cpu, struct device *dev)
+{
+        int default_tjmax = 100000;
+        int err;
+        u32 eax, edx;
+        u32 val;
+
+        /* IA32_TEMPERATURE_TARGET contains the TjMax value */
+        err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
+        if (!err) {
+                val = (eax >> 16) & 0xff;
+                if ((val > 80) && (val < 120)) {
+                        dev_info(dev, "TjMax is %d C.\n", val);
+                        return val * 1000;
+                }
+        }
+        dev_warn(dev, "Unable to read TjMax from CPU.\n");
+        return default_tjmax;
+}
+
+static int __devinit pkgtemp_probe(struct platform_device *pdev)
+{
+        struct pkgtemp_data *data;
+        int err;
+        u32 eax, edx;
+#ifdef CONFIG_SMP
+        struct cpuinfo_x86 *c = &cpu_data(pdev->id);
+#endif
+
+        data = kzalloc(sizeof(struct pkgtemp_data), GFP_KERNEL);
+        if (!data) {
+                err = -ENOMEM;
+                dev_err(&pdev->dev, "Out of memory\n");
+                goto exit;
+        }
+
+        data->id = pdev->id;
+#ifdef CONFIG_SMP
+        data->phys_proc_id = c->phys_proc_id;
+#endif
+        data->name = "pkgtemp";
+        mutex_init(&data->update_lock);
+
+        /* test if we can access the THERM_STATUS MSR */
+        err = rdmsr_safe_on_cpu(data->id, MSR_IA32_PACKAGE_THERM_STATUS,
+                                &eax, &edx);
+        if (err) {
+                dev_err(&pdev->dev,
+                        "Unable to access THERM_STATUS MSR, giving up\n");
+                goto exit_free;
+        }
+
+        data->tjmax = get_tjmax(data->id, &pdev->dev);
+        platform_set_drvdata(pdev, data);
+
+        err = rdmsr_safe_on_cpu(data->id, MSR_IA32_TEMPERATURE_TARGET,
+                                &eax, &edx);
+        if (err) {
+                dev_warn(&pdev->dev, "Unable to read"
+                                " IA32_TEMPERATURE_TARGET MSR\n");
+        } else {
+                data->ttarget = data->tjmax - (((eax >> 8) & 0xff) * 1000);
+                err = device_create_file(&pdev->dev,
+                                &sensor_dev_attr_temp1_max.dev_attr);
+                if (err)
+                        goto exit_free;
+        }
+
+        err = sysfs_create_group(&pdev->dev.kobj, &pkgtemp_group);
+        if (err)
+                goto exit_free;
+
+        data->hwmon_dev = hwmon_device_register(&pdev->dev);
+        if (IS_ERR(data->hwmon_dev)) {
+                err = PTR_ERR(data->hwmon_dev);
+                dev_err(&pdev->dev, "Class registration failed (%d)\n",
+                        err);
+                goto exit_class;
+        }
+
+        return 0;
+
+exit_class:
+        sysfs_remove_group(&pdev->dev.kobj, &pkgtemp_group);
+exit_free:
+        kfree(data);
+exit:
+        return err;
+}
+
+static int __devexit pkgtemp_remove(struct platform_device *pdev)
+{
+        struct pkgtemp_data *data = platform_get_drvdata(pdev);
+
+        hwmon_device_unregister(data->hwmon_dev);
+        sysfs_remove_group(&pdev->dev.kobj, &pkgtemp_group);
+        platform_set_drvdata(pdev, NULL);
+        kfree(data);
+        return 0;
+}
+
+static struct platform_driver pkgtemp_driver = {
+        .driver = {
+                .owner = THIS_MODULE,
+                .name = DRVNAME,
+        },
+        .probe = pkgtemp_probe,
+        .remove = __devexit_p(pkgtemp_remove),
+};
+
+struct pdev_entry {
+        struct list_head list;
+        struct platform_device *pdev;
+        unsigned int cpu;
+#ifdef CONFIG_SMP
+        u16 phys_proc_id;
+#endif
+};
+
+static LIST_HEAD(pdev_list);
+static DEFINE_MUTEX(pdev_list_mutex);
+
+static int __cpuinit pkgtemp_device_add(unsigned int cpu)
+{
+        int err;
+        struct platform_device *pdev;
+        struct pdev_entry *pdev_entry;
+#ifdef CONFIG_SMP
+        struct cpuinfo_x86 *c = &cpu_data(cpu);
+#endif
+
+        mutex_lock(&pdev_list_mutex);
+
+#ifdef CONFIG_SMP
+        /* Only keep the first entry in each package */
+        list_for_each_entry(pdev_entry, &pdev_list, list) {
+                if (c->phys_proc_id == pdev_entry->phys_proc_id) {
+                        err = 0;        /* Not an error */
+                        goto exit;
+                }
+        }
+#endif
+
+        pdev = platform_device_alloc(DRVNAME, cpu);
+        if (!pdev) {
+                err = -ENOMEM;
+                printk(KERN_ERR DRVNAME ": Device allocation failed\n");
+                goto exit;
+        }
+
+        pdev_entry = kzalloc(sizeof(struct pdev_entry), GFP_KERNEL);
+        if (!pdev_entry) {
+                err = -ENOMEM;
+                goto exit_device_put;
+        }
+
+        err = platform_device_add(pdev);
+        if (err) {
+                printk(KERN_ERR DRVNAME ": Device addition failed (%d)\n",
+                       err);
+                goto exit_device_free;
+        }
+
+#ifdef CONFIG_SMP
+        pdev_entry->phys_proc_id = c->phys_proc_id;
+#endif
+        pdev_entry->pdev = pdev;
+        pdev_entry->cpu = cpu;
+        list_add_tail(&pdev_entry->list, &pdev_list);
+        mutex_unlock(&pdev_list_mutex);
+
+        return 0;
+
+exit_device_free:
+        kfree(pdev_entry);
+exit_device_put:
+        platform_device_put(pdev);
+exit:
+        mutex_unlock(&pdev_list_mutex);
+        return err;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void pkgtemp_device_remove(unsigned int cpu)
+{
+        struct pdev_entry *p, *n;
+        unsigned int i;
+        int err;
+
+        mutex_lock(&pdev_list_mutex);
+        list_for_each_entry_safe(p, n, &pdev_list, list) {
+                if (p->cpu != cpu)
+                        continue;
+
+                platform_device_unregister(p->pdev);
+                list_del(&p->list);
+                kfree(p);
+                for_each_cpu(i, cpu_core_mask(cpu)) {
+                        if (i != cpu) {
+                                err = pkgtemp_device_add(i);
+                                if (!err)
+                                        break;
+                        }
+                }
+                break;
+        }
+        mutex_unlock(&pdev_list_mutex);
+}
+
+static int __cpuinit pkgtemp_cpu_callback(struct notifier_block *nfb,
+                                 unsigned long action, void *hcpu)
+{
+        unsigned int cpu = (unsigned long) hcpu;
+
+        switch (action) {
+        case CPU_ONLINE:
+        case CPU_DOWN_FAILED:
+                pkgtemp_device_add(cpu);
+                break;
+        case CPU_DOWN_PREPARE:
+                pkgtemp_device_remove(cpu);
+                break;
+        }
+        return NOTIFY_OK;
+}
+
+static struct notifier_block pkgtemp_cpu_notifier __refdata = {
+        .notifier_call = pkgtemp_cpu_callback,
+};
+#endif                          /* !CONFIG_HOTPLUG_CPU */
+
+static int __init pkgtemp_init(void)
+{
+        int i, err = -ENODEV;
+        struct pdev_entry *p, *n;
+
+        /* quick check if we run Intel */
+        if (cpu_data(0).x86_vendor != X86_VENDOR_INTEL)
+                goto exit;
+
+        err = platform_driver_register(&pkgtemp_driver);
+        if (err)
+                goto exit;
+
+        for_each_online_cpu(i) {
+                struct cpuinfo_x86 *c = &cpu_data(i);
+
+                if (!cpu_has(c, X86_FEATURE_PTS))
+                        continue;
+
+                err = pkgtemp_device_add(i);
+                if (err)
+                        goto exit_devices_unreg;
+        }
+        if (list_empty(&pdev_list)) {
+                err = -ENODEV;
+                goto exit_driver_unreg;
+        }
+
+#ifdef CONFIG_HOTPLUG_CPU
+        register_hotcpu_notifier(&pkgtemp_cpu_notifier);
+#endif
+        return 0;
+
+exit_devices_unreg:
+        mutex_lock(&pdev_list_mutex);
+        list_for_each_entry_safe(p, n, &pdev_list, list) {
+                platform_device_unregister(p->pdev);
+                list_del(&p->list);
+                kfree(p);
+        }
+        mutex_unlock(&pdev_list_mutex);
+exit_driver_unreg:
+        platform_driver_unregister(&pkgtemp_driver);
+exit:
+        return err;
+}
+
+static void __exit pkgtemp_exit(void)
+{
+        struct pdev_entry *p, *n;
+#ifdef CONFIG_HOTPLUG_CPU
+        unregister_hotcpu_notifier(&pkgtemp_cpu_notifier);
+#endif
+        mutex_lock(&pdev_list_mutex);
+        list_for_each_entry_safe(p, n, &pdev_list, list) {
+                platform_device_unregister(p->pdev);
+                list_del(&p->list);
+                kfree(p);
+        }
+        mutex_unlock(&pdev_list_mutex);
+        platform_driver_unregister(&pkgtemp_driver);
+}
+
+MODULE_AUTHOR("Fenghua Yu <fenghua.yu@intel.com>");
+MODULE_DESCRIPTION("Intel processor package temperature monitor");
+MODULE_LICENSE("GPL");
+
+module_init(pkgtemp_init)
+module_exit(pkgtemp_exit)