Merge branch 'x86-hwmon-for-linus' of...

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

Documentation/hwmon/pkgtemp

+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.

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

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

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)
@@ -335,9 +445,27 @@ void intel_init_thermal(struct cpuinfo_x86 *c)
 	apic_write(APIC_LVTTHMR, h);
 
 	rdmsr(MSR_IA32_THERM_INTERRUPT, l, 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;
 
 	rdmsr(MSR_IA32_MISC_ENABLE, l, h);

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

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