Merge branch 'cpu-package-thermal' of .git into next

Conflicts:
	drivers/thermal/Kconfig
	drivers/thermal/Makefile

Documentation/thermal/x86_pkg_temperature_thermal

@@ -0,0 +1,47 @@
+Kernel driver: x86_pkg_temp_thermal
+===================
+
+Supported chips:
+* x86: with package level thermal management
+(Verify using: CPUID.06H:EAX[bit 6] =1)
+
+Authors: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
+
+Reference
+---
+Intel® 64 and IA-32 Architectures Software Developer’s Manual (Jan, 2013):
+Chapter 14.6: PACKAGE LEVEL THERMAL MANAGEMENT
+
+Description
+---------
+
+This driver register CPU digital temperature package level sensor as a thermal
+zone with maximum two user mode configurable trip points. Number of trip points
+depends on the capability of the package. Once the trip point is violated,
+user mode can receive notification via thermal notification mechanism and can
+take any action to control temperature.
+
+
+Threshold management
+--------------------
+Each package will register as a thermal zone under /sys/class/thermal.
+Example:
+/sys/class/thermal/thermal_zone1
+
+This contains two trip points:
+- trip_point_0_temp
+- trip_point_1_temp
+
+User can set any temperature between 0 to TJ-Max temperature. Temperature units
+are in milli-degree Celsius. Refer to "Documentation/thermal/sysfs-api.txt" for
+thermal sys-fs details.
+
+Any value other than 0 in these trip points, can trigger thermal notifications.
+Setting 0, stops sending thermal notifications.
+
+Thermal notifications: To get kobject-uevent notifications, set the thermal zone
+policy to "user_space". For example: echo -n "user_space" > policy
+
+
+
+

arch/x86/include/asm/mce.h

@@ -214,6 +214,13 @@ void mce_log_therm_throt_event(__u64 status);
 /* Interrupt Handler for core thermal thresholds */
 extern int (*platform_thermal_notify)(__u64 msr_val);
 
+/* Interrupt Handler for package thermal thresholds */
+extern int (*platform_thermal_package_notify)(__u64 msr_val);
+
+/* Callback support of rate control, return true, if
+ * callback has rate control */
+extern bool (*platform_thermal_package_rate_control)(void);
+
 #ifdef CONFIG_X86_THERMAL_VECTOR
 extern void mcheck_intel_therm_init(void);
 #else

arch/x86/kernel/cpu/mcheck/therm_throt.c

@@ -54,12 +54,24 @@ struct thermal_state {
 	struct _thermal_state package_power_limit;
 	struct _thermal_state core_thresh0;
 	struct _thermal_state core_thresh1;
+	struct _thermal_state pkg_thresh0;
+	struct _thermal_state pkg_thresh1;
 };
 
 /* Callback to handle core threshold interrupts */
 int (*platform_thermal_notify)(__u64 msr_val);
 EXPORT_SYMBOL(platform_thermal_notify);
 
+/* Callback to handle core package threshold_interrupts */
+int (*platform_thermal_package_notify)(__u64 msr_val);
+EXPORT_SYMBOL_GPL(platform_thermal_package_notify);
+
+/* Callback support of rate control, return true, if
+ * callback has rate control */
+bool (*platform_thermal_package_rate_control)(void);
+EXPORT_SYMBOL_GPL(platform_thermal_package_rate_control);
+
+
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
@@ -203,19 +215,25 @@ static int therm_throt_process(bool new_event, int event, int level)
 	return 0;
 }
 
-static int thresh_event_valid(int event)
+static int thresh_event_valid(int level, int event)
 {
 	struct _thermal_state *state;
 	unsigned int this_cpu = smp_processor_id();
 	struct thermal_state *pstate = &per_cpu(thermal_state, this_cpu);
 	u64 now = get_jiffies_64();
 
-	state = (event == 0) ? &pstate->core_thresh0 : &pstate->core_thresh1;
+	if (level == PACKAGE_LEVEL)
+		state = (event == 0) ? &pstate->pkg_thresh0 :
+						&pstate->pkg_thresh1;
+	else
+		state = (event == 0) ? &pstate->core_thresh0 :
+						&pstate->core_thresh1;
 
 	if (time_before64(now, state->next_check))
 		return 0;
 
 	state->next_check = now + CHECK_INTERVAL;
+
 	return 1;
 }
 
@@ -321,6 +339,39 @@ device_initcall(thermal_throttle_init_device);
 
 #endif /* CONFIG_SYSFS */
 
+static void notify_package_thresholds(__u64 msr_val)
+{
+	bool notify_thres_0 = false;
+	bool notify_thres_1 = false;
+
+	if (!platform_thermal_package_notify)
+		return;
+
+	/* lower threshold check */
+	if (msr_val & THERM_LOG_THRESHOLD0)
+		notify_thres_0 = true;
+	/* higher threshold check */
+	if (msr_val & THERM_LOG_THRESHOLD1)
+		notify_thres_1 = true;
+
+	if (!notify_thres_0 && !notify_thres_1)
+		return;
+
+	if (platform_thermal_package_rate_control &&
+		platform_thermal_package_rate_control()) {
+		/* Rate control is implemented in callback */
+		platform_thermal_package_notify(msr_val);
+		return;
+	}
+
+	/* lower threshold reached */
+	if (notify_thres_0 && thresh_event_valid(PACKAGE_LEVEL, 0))
+		platform_thermal_package_notify(msr_val);
+	/* higher threshold reached */
+	if (notify_thres_1 && thresh_event_valid(PACKAGE_LEVEL, 1))
+		platform_thermal_package_notify(msr_val);
+}
+
 static void notify_thresholds(__u64 msr_val)
 {
 	/* check whether the interrupt handler is defined;
@@ -330,10 +381,12 @@ static void notify_thresholds(__u64 msr_val)
 		return;
 
 	/* lower threshold reached */
-	if ((msr_val & THERM_LOG_THRESHOLD0) &&	thresh_event_valid(0))
+	if ((msr_val & THERM_LOG_THRESHOLD0) &&
+			thresh_event_valid(CORE_LEVEL, 0))
 		platform_thermal_notify(msr_val);
 	/* higher threshold reached */
-	if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+	if ((msr_val & THERM_LOG_THRESHOLD1) &&
+			thresh_event_valid(CORE_LEVEL, 1))
 		platform_thermal_notify(msr_val);
 }
 
@@ -359,6 +412,8 @@ static void intel_thermal_interrupt(void)
 
 	if (this_cpu_has(X86_FEATURE_PTS)) {
 		rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val);
+		/* check violations of package thermal thresholds */
+		notify_package_thresholds(msr_val);
 		therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT,
 					THERMAL_THROTTLING_EVENT,
 					PACKAGE_LEVEL);

drivers/thermal/Kconfig

@@ -169,7 +169,20 @@ config INTEL_POWERCLAMP
 	  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 THERMAL
+	depends on X86
+	select THERMAL_GOV_USER_SPACE
+	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.
+
 menu "Texas Instruments thermal drivers"
 source "drivers/thermal/ti-soc-thermal/Kconfig"
 endmenu
+
 endif

drivers/thermal/Makefile

@@ -23,4 +23,5 @@ obj-$(CONFIG_DB8500_THERMAL)	+= db8500_thermal.o
 obj-$(CONFIG_ARMADA_THERMAL)	+= armada_thermal.o
 obj-$(CONFIG_DB8500_CPUFREQ_COOLING)	+= db8500_cpufreq_cooling.o
 obj-$(CONFIG_INTEL_POWERCLAMP)	+= intel_powerclamp.o
+obj-$(CONFIG_X86_PKG_TEMP_THERMAL)	+= x86_pkg_temp_thermal.o
 obj-$(CONFIG_TI_SOC_THERMAL)	+= ti-soc-thermal/