x86, hwmon: Add core threshold notification to therm_throt.c

This patch adds code to therm_throt.c to notify core thermal threshold
events. These thresholds are supported by the IA32_THERM_INTERRUPT register.
The status/log for the same is monitored using the IA32_THERM_STATUS register.
The necessary #defines are in msr-index.h. A call back is added to mce.h, to
further notify the thermal stack, about the threshold events.

Signed-off-by: Durgadoss R <[email protected]>
LKML-Reference: <D6D887BA8C9DFF48B5233887EF04654105C1251710@bgsmsx502.gar.corp.intel.com>
Signed-off-by: H. Peter Anvin <[email protected]>

Author: durgadoss

arch/x86/include/asm/mce.h

@@ -223,6 +223,9 @@ void intel_init_thermal(struct cpuinfo_x86 *c);
 
 void mce_log_therm_throt_event(__u64 status);
 
+/* Interrupt Handler for core thermal thresholds */
+extern int (*platform_thermal_notify)(__u64 msr_val);
+
 #ifdef CONFIG_X86_THERMAL_VECTOR
 extern void mcheck_intel_therm_init(void);
 #else

arch/x86/include/asm/msr-index.h

@@ -253,6 +253,18 @@
 #define PACKAGE_THERM_INT_LOW_ENABLE		(1 << 1)
 #define PACKAGE_THERM_INT_PLN_ENABLE		(1 << 24)
 
+/* Thermal Thresholds Support */
+#define THERM_INT_THRESHOLD0_ENABLE    (1 << 15)
+#define THERM_SHIFT_THRESHOLD0        8
+#define THERM_MASK_THRESHOLD0          (0x7f << THERM_SHIFT_THRESHOLD0)
+#define THERM_INT_THRESHOLD1_ENABLE    (1 << 23)
+#define THERM_SHIFT_THRESHOLD1        16
+#define THERM_MASK_THRESHOLD1          (0x7f << THERM_SHIFT_THRESHOLD1)
+#define THERM_STATUS_THRESHOLD0        (1 << 6)
+#define THERM_LOG_THRESHOLD0           (1 << 7)
+#define THERM_STATUS_THRESHOLD1        (1 << 8)
+#define THERM_LOG_THRESHOLD1           (1 << 9)
+
 /* MISC_ENABLE bits: architectural */
 #define MSR_IA32_MISC_ENABLE_FAST_STRING	(1ULL << 0)
 #define MSR_IA32_MISC_ENABLE_TCC		(1ULL << 1)

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

@@ -53,8 +53,13 @@ struct thermal_state {
 	struct _thermal_state core_power_limit;
 	struct _thermal_state package_throttle;
 	struct _thermal_state package_power_limit;
+	struct _thermal_state core_thresh0;
+	struct _thermal_state core_thresh1;
 };
 
+/* Callback to handle core threshold interrupts */
+int (*platform_thermal_notify)(__u64 msr_val);
+
 static DEFINE_PER_CPU(struct thermal_state, thermal_state);
 
 static atomic_t therm_throt_en	= ATOMIC_INIT(0);
@@ -200,6 +205,22 @@ static int therm_throt_process(bool new_event, int event, int level)
 	return 0;
 }
 
+static int thresh_event_valid(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 (time_before64(now, state->next_check))
+		return 0;
+
+	state->next_check = now + CHECK_INTERVAL;
+	return 1;
+}
+
 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
 static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
@@ -313,6 +334,22 @@ device_initcall(thermal_throttle_init_device);
 #define PACKAGE_THROTTLED	((__u64)2 << 62)
 #define PACKAGE_POWER_LIMIT	((__u64)3 << 62)
 
+static void notify_thresholds(__u64 msr_val)
+{
+	/* check whether the interrupt handler is defined;
+	 * otherwise simply return
+	 */
+	if (!platform_thermal_notify)
+		return;
+
+	/* lower threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD0) &&	thresh_event_valid(0))
+		platform_thermal_notify(msr_val);
+	/* higher threshold reached */
+	if ((msr_val & THERM_LOG_THRESHOLD1) && thresh_event_valid(1))
+		platform_thermal_notify(msr_val);
+}
+
 /* Thermal transition interrupt handler */
 static void intel_thermal_interrupt(void)
 {
@@ -321,6 +358,9 @@ static void intel_thermal_interrupt(void)
 
 	rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
 
+	/* Check for violation of core thermal thresholds*/
+	notify_thresholds(msr_val);
+
 	if (therm_throt_process(msr_val & THERM_STATUS_PROCHOT,
 				THERMAL_THROTTLING_EVENT,
 				CORE_LEVEL) != 0)