From 15d5f8398311f565682959daaca30e3ca7aea600 Mon Sep 17 00:00:00 2001
From: Dmitriy Zavin <dmitriyz@google.com>
Date: Tue, 26 Sep 2006 10:52:42 +0200
Subject: [PATCH] x86: Refactor thermal throttle processing
Refactor the event processing (syslog messaging and rate limiting)
into separate file therm_throt.c. This allows consistent reporting
of CPU thermal throttle events.
After ACK'ing the interrupt, if the event is current, the user
(p4.c/mce_intel.c) calls therm_throt_process to log (and rate limit)
the event. If that function returns 1, the user has the option to log
things further (such as to mce_log in x86_64).
AK: minor cleanup
Signed-off-by: Dmitriy Zavin <dmitriyz@google.com>
Signed-off-by: Andi Kleen <ak@suse.de>
---
arch/i386/kernel/cpu/mcheck/Makefile | 2 +-
arch/i386/kernel/cpu/mcheck/p4.c | 23 ++++--------
arch/i386/kernel/cpu/mcheck/therm_throt.c | 58 +++++++++++++++++++++++++++++++
3 files changed, 65 insertions(+), 18 deletions(-)
create mode 100644 arch/i386/kernel/cpu/mcheck/therm_throt.c
(limited to 'arch/i386')
diff --git a/arch/i386/kernel/cpu/mcheck/Makefile b/arch/i386/kernel/cpu/mcheck/Makefile
index 30808f3d6715..f1ebe1c1c17a 100644
--- a/arch/i386/kernel/cpu/mcheck/Makefile
+++ b/arch/i386/kernel/cpu/mcheck/Makefile
@@ -1,2 +1,2 @@
-obj-y = mce.o k7.o p4.o p5.o p6.o winchip.o
+obj-y = mce.o k7.o p4.o p5.o p6.o winchip.o therm_throt.o
obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o
diff --git a/arch/i386/kernel/cpu/mcheck/p4.c b/arch/i386/kernel/cpu/mcheck/p4.c
index b95f1b3d53aa..d83a669d376f 100644
--- a/arch/i386/kernel/cpu/mcheck/p4.c
+++ b/arch/i386/kernel/cpu/mcheck/p4.c
@@ -13,6 +13,8 @@
#include <asm/msr.h>
#include <asm/apic.h>
+#include <asm/therm_throt.h>
+
#include "mce.h"
/* as supported by the P4/Xeon family */
@@ -44,25 +46,12 @@ static void unexpected_thermal_interrupt(struct pt_regs *regs)
/* P4/Xeon Thermal transition interrupt handler */
static void intel_thermal_interrupt(struct pt_regs *regs)
{
- u32 l, h;
- unsigned int cpu = smp_processor_id();
- static unsigned long next[NR_CPUS];
+ __u64 msr_val;
ack_APIC_irq();
- if (time_after(next[cpu], jiffies))
- return;
-
- next[cpu] = jiffies + HZ*5;
- rdmsr(MSR_IA32_THERM_STATUS, l, h);
- if (l & 0x1) {
- printk(KERN_EMERG "CPU%d: Temperature above threshold\n", cpu);
- printk(KERN_EMERG "CPU%d: Running in modulated clock mode\n",
- cpu);
- add_taint(TAINT_MACHINE_CHECK);
- } else {
- printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
- }
+ rdmsrl(MSR_IA32_THERM_STATUS, msr_val);
+ therm_throt_process(msr_val & 0x1);
}
/* Thermal interrupt handler for this CPU setup */
@@ -122,7 +111,7 @@ static void intel_init_thermal(struct cpuinfo_x86 *c)
rdmsr (MSR_IA32_MISC_ENABLE, l, h);
wrmsr (MSR_IA32_MISC_ENABLE, l | (1<<3), h);
-
+
l = apic_read (APIC_LVTTHMR);
apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
printk (KERN_INFO "CPU%d: Thermal monitoring enabled\n", cpu);
diff --git a/arch/i386/kernel/cpu/mcheck/therm_throt.c b/arch/i386/kernel/cpu/mcheck/therm_throt.c
new file mode 100644
index 000000000000..85eba00d680e
--- /dev/null
+++ b/arch/i386/kernel/cpu/mcheck/therm_throt.c
@@ -0,0 +1,58 @@
+/*
+ * linux/arch/i386/kerne/cpu/mcheck/therm_throt.c
+ *
+ * Thermal throttle event support code.
+ *
+ * Author: Dmitriy Zavin (dmitriyz@google.com)
+ *
+ * Credits: Adapted from Zwane Mwaikambo's original code in mce_intel.c.
+ *
+ */
+
+#include <linux/percpu.h>
+#include <linux/cpu.h>
+#include <asm/cpu.h>
+#include <linux/notifier.h>
+#include <asm/therm_throt.h>
+
+/* How long to wait between reporting thermal events */
+#define CHECK_INTERVAL (300 * HZ)
+
+static DEFINE_PER_CPU(unsigned long, next_check);
+
+/***
+ * therm_throt_process - Process thermal throttling event
+ * @curr: Whether the condition is current or not (boolean), since the
+ * thermal interrupt normally gets called both when the thermal
+ * event begins and once the event has ended.
+ *
+ * This function is normally called by the thermal interrupt after the
+ * IRQ has been acknowledged.
+ *
+ * It will take care of rate limiting and printing messages to the syslog.
+ *
+ * Returns: 0 : Event should NOT be further logged, i.e. still in
+ * "timeout" from previous log message.
+ * 1 : Event should be logged further, and a message has been
+ * printed to the syslog.
+ */
+int therm_throt_process(int curr)
+{
+ unsigned int cpu = smp_processor_id();
+
+ if (time_before(jiffies, __get_cpu_var(next_check)))
+ return 0;
+
+ __get_cpu_var(next_check) = jiffies + CHECK_INTERVAL;
+
+ /* if we just entered the thermal event */
+ if (curr) {
+ printk(KERN_CRIT "CPU%d: Temperature above threshold, "
+ "cpu clock throttled\n", cpu);
+ add_taint(TAINT_MACHINE_CHECK);
+ } else {
+ printk(KERN_CRIT "CPU%d: Temperature/speed normal\n", cpu);
+ }
+
+ return 1;
+}
--
cgit v1.2.3