When: 2.6.33
Why: Should be implemented in userspace, policy daemon.
Who: Johannes Berg <johannes@sipsolutions.net>
-
-----------------------------
-
-What: CONFIG_X86_OLD_MCE
-When: 2.6.32
-Why: Remove the old legacy 32bit machine check code. This has been
- superseded by the newer machine check code from the 64bit port,
- but the old version has been kept around for easier testing. Note this
- doesn't impact the old P5 and WinChip machine check handlers.
-Who: Andi Kleen <andi@firstfloor.org>
The action the kernel takes depends on the severity of the problem,
ranging from warning messages to halting the machine.
-config X86_OLD_MCE
- depends on X86_32 && X86_MCE
- bool "Use legacy machine check code (will go away)"
- default n
- select X86_ANCIENT_MCE
- ---help---
- Use the old i386 machine check code. This is merely intended for
- testing in a transition period. Try this if you run into any machine
- check related software problems, but report the problem to
- linux-kernel. When in doubt say no.
-
config X86_NEW_MCE
depends on X86_MCE
bool
- default y if (!X86_OLD_MCE && X86_32) || X86_64
+ default y
config X86_MCE_INTEL
def_bool y
If you don't know what a machine check is and you don't do kernel
QA it is safe to say n.
-config X86_MCE_NONFATAL
- tristate "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4"
- depends on X86_OLD_MCE
- ---help---
- Enabling this feature starts a timer that triggers every 5 seconds which
- will look at the machine check registers to see if anything happened.
- Non-fatal problems automatically get corrected (but still logged).
- Disable this if you don't want to see these messages.
- Seeing the messages this option prints out may be indicative of dying
- or out-of-spec (ie, overclocked) hardware.
- This option only does something on certain CPUs.
- (AMD Athlon/Duron and Intel Pentium 4)
-
-config X86_MCE_P4THERMAL
- bool "check for P4 thermal throttling interrupt."
- depends on X86_OLD_MCE && X86_MCE && (X86_UP_APIC || SMP)
- ---help---
- Enabling this feature will cause a message to be printed when the P4
- enters thermal throttling.
-
config X86_THERMAL_VECTOR
def_bool y
- depends on X86_MCE_P4THERMAL || X86_MCE_INTEL
+ depends on X86_MCE_INTEL
config VM86
bool "Enable VM86 support" if EMBEDDED
static inline void mcheck_init(struct cpuinfo_x86 *c) {}
#endif
-#ifdef CONFIG_X86_OLD_MCE
-extern int nr_mce_banks;
-void amd_mcheck_init(struct cpuinfo_x86 *c);
-void intel_p4_mcheck_init(struct cpuinfo_x86 *c);
-void intel_p6_mcheck_init(struct cpuinfo_x86 *c);
-#endif
-
#ifdef CONFIG_X86_ANCIENT_MCE
void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
void winchip_mcheck_init(struct cpuinfo_x86 *c);
void intel_init_thermal(struct cpuinfo_x86 *c);
-#ifdef CONFIG_X86_NEW_MCE
void mce_log_therm_throt_event(__u64 status);
-#else
-static inline void mce_log_therm_throt_event(__u64 status) {}
-#endif
#endif /* __KERNEL__ */
#endif /* _ASM_X86_MCE_H */
obj-y = mce.o
obj-$(CONFIG_X86_NEW_MCE) += mce-severity.o
-obj-$(CONFIG_X86_OLD_MCE) += k7.o p4.o p6.o
obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o
obj-$(CONFIG_X86_MCE_INTEL) += mce_intel.o
obj-$(CONFIG_X86_MCE_AMD) += mce_amd.o
-obj-$(CONFIG_X86_MCE_NONFATAL) += non-fatal.o
obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o
+++ /dev/null
-/*
- * Athlon specific Machine Check Exception Reporting
- * (C) Copyright 2002 Dave Jones <davej@redhat.com>
- */
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/mce.h>
-#include <asm/msr.h>
-
-/* Machine Check Handler For AMD Athlon/Duron: */
-static void k7_machine_check(struct pt_regs *regs, long error_code)
-{
- u32 alow, ahigh, high, low;
- u32 mcgstl, mcgsth;
- int recover = 1;
- int i;
-
- rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
- if (mcgstl & (1<<0)) /* Recoverable ? */
- recover = 0;
-
- printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
- smp_processor_id(), mcgsth, mcgstl);
-
- for (i = 1; i < nr_mce_banks; i++) {
- rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
- if (high & (1<<31)) {
- char misc[20];
- char addr[24];
-
- misc[0] = '\0';
- addr[0] = '\0';
-
- if (high & (1<<29))
- recover |= 1;
- if (high & (1<<25))
- recover |= 2;
- high &= ~(1<<31);
-
- if (high & (1<<27)) {
- rdmsr(MSR_IA32_MC0_MISC+i*4, alow, ahigh);
- snprintf(misc, 20, "[%08x%08x]", ahigh, alow);
- }
- if (high & (1<<26)) {
- rdmsr(MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
- snprintf(addr, 24, " at %08x%08x", ahigh, alow);
- }
-
- printk(KERN_EMERG "CPU %d: Bank %d: %08x%08x%s%s\n",
- smp_processor_id(), i, high, low, misc, addr);
-
- /* Clear it: */
- wrmsr(MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
- /* Serialize: */
- wmb();
- add_taint(TAINT_MACHINE_CHECK);
- }
- }
-
- if (recover & 2)
- panic("CPU context corrupt");
- if (recover & 1)
- panic("Unable to continue");
-
- printk(KERN_EMERG "Attempting to continue.\n");
-
- mcgstl &= ~(1<<2);
- wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
-}
-
-
-/* AMD K7 machine check is Intel like: */
-void amd_mcheck_init(struct cpuinfo_x86 *c)
-{
- u32 l, h;
- int i;
-
- if (!cpu_has(c, X86_FEATURE_MCE))
- return;
-
- machine_check_vector = k7_machine_check;
- /* Make sure the vector pointer is visible before we enable MCEs: */
- wmb();
-
- printk(KERN_INFO "Intel machine check architecture supported.\n");
-
- rdmsr(MSR_IA32_MCG_CAP, l, h);
- if (l & (1<<8)) /* Control register present ? */
- wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
- nr_mce_banks = l & 0xff;
-
- /*
- * Clear status for MC index 0 separately, we don't touch CTL,
- * as some K7 Athlons cause spurious MCEs when its enabled:
- */
- if (boot_cpu_data.x86 == 6) {
- wrmsr(MSR_IA32_MC0_STATUS, 0x0, 0x0);
- i = 1;
- } else
- i = 0;
-
- for (; i < nr_mce_banks; i++) {
- wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
- wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
- }
-
- set_in_cr4(X86_CR4_MCE);
- printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
- smp_processor_id());
-}
int mce_disabled __read_mostly;
-#ifdef CONFIG_X86_NEW_MCE
-
#define MISC_MCELOG_MINOR 227
#define SPINUNIT 100 /* 100ns */
device_initcall(mce_init_device);
-#else /* CONFIG_X86_OLD_MCE: */
-
-int nr_mce_banks;
-EXPORT_SYMBOL_GPL(nr_mce_banks); /* non-fatal.o */
-
-/* This has to be run for each processor */
-void mcheck_init(struct cpuinfo_x86 *c)
-{
- if (mce_disabled)
- return;
-
- switch (c->x86_vendor) {
- case X86_VENDOR_AMD:
- amd_mcheck_init(c);
- break;
-
- case X86_VENDOR_INTEL:
- if (c->x86 == 5)
- intel_p5_mcheck_init(c);
- if (c->x86 == 6)
- intel_p6_mcheck_init(c);
- if (c->x86 == 15)
- intel_p4_mcheck_init(c);
- break;
-
- case X86_VENDOR_CENTAUR:
- if (c->x86 == 5)
- winchip_mcheck_init(c);
- break;
-
- default:
- break;
- }
- printk(KERN_INFO "mce: CPU supports %d MCE banks\n", nr_mce_banks);
-}
-
-static int __init mcheck_enable(char *str)
-{
- mce_p5_enabled = 1;
- return 1;
-}
-__setup("mce", mcheck_enable);
-
-#endif /* CONFIG_X86_OLD_MCE */
-
/*
* Old style boot options parsing. Only for compatibility.
*/
+++ /dev/null
-/*
- * Non Fatal Machine Check Exception Reporting
- *
- * (C) Copyright 2002 Dave Jones. <davej@redhat.com>
- *
- * This file contains routines to check for non-fatal MCEs every 15s
- *
- */
-#include <linux/interrupt.h>
-#include <linux/workqueue.h>
-#include <linux/jiffies.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/mce.h>
-#include <asm/msr.h>
-
-static int firstbank;
-
-#define MCE_RATE (15*HZ) /* timer rate is 15s */
-
-static void mce_checkregs(void *info)
-{
- u32 low, high;
- int i;
-
- for (i = firstbank; i < nr_mce_banks; i++) {
- rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
-
- if (!(high & (1<<31)))
- continue;
-
- printk(KERN_INFO "MCE: The hardware reports a non fatal, "
- "correctable incident occurred on CPU %d.\n",
- smp_processor_id());
-
- printk(KERN_INFO "Bank %d: %08x%08x\n", i, high, low);
-
- /*
- * Scrub the error so we don't pick it up in MCE_RATE
- * seconds time:
- */
- wrmsr(MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
-
- /* Serialize: */
- wmb();
- add_taint(TAINT_MACHINE_CHECK);
- }
-}
-
-static void mce_work_fn(struct work_struct *work);
-static DECLARE_DELAYED_WORK(mce_work, mce_work_fn);
-
-static void mce_work_fn(struct work_struct *work)
-{
- on_each_cpu(mce_checkregs, NULL, 1);
- schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE));
-}
-
-static int __init init_nonfatal_mce_checker(void)
-{
- struct cpuinfo_x86 *c = &boot_cpu_data;
-
- /* Check for MCE support */
- if (!cpu_has(c, X86_FEATURE_MCE))
- return -ENODEV;
-
- /* Check for PPro style MCA */
- if (!cpu_has(c, X86_FEATURE_MCA))
- return -ENODEV;
-
- /* Some Athlons misbehave when we frob bank 0 */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
- boot_cpu_data.x86 == 6)
- firstbank = 1;
- else
- firstbank = 0;
-
- /*
- * Check for non-fatal errors every MCE_RATE s
- */
- schedule_delayed_work(&mce_work, round_jiffies_relative(MCE_RATE));
- printk(KERN_INFO "Machine check exception polling timer started.\n");
-
- return 0;
-}
-module_init(init_nonfatal_mce_checker);
-
-MODULE_LICENSE("GPL");
+++ /dev/null
-/*
- * P4 specific Machine Check Exception Reporting
- */
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-
-#include <asm/processor.h>
-#include <asm/mce.h>
-#include <asm/msr.h>
-
-/* as supported by the P4/Xeon family */
-struct intel_mce_extended_msrs {
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u32 esi;
- u32 edi;
- u32 ebp;
- u32 esp;
- u32 eflags;
- u32 eip;
- /* u32 *reserved[]; */
-};
-
-static int mce_num_extended_msrs;
-
-/* P4/Xeon Extended MCE MSR retrieval, return 0 if unsupported */
-static void intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
-{
- u32 h;
-
- rdmsr(MSR_IA32_MCG_EAX, r->eax, h);
- rdmsr(MSR_IA32_MCG_EBX, r->ebx, h);
- rdmsr(MSR_IA32_MCG_ECX, r->ecx, h);
- rdmsr(MSR_IA32_MCG_EDX, r->edx, h);
- rdmsr(MSR_IA32_MCG_ESI, r->esi, h);
- rdmsr(MSR_IA32_MCG_EDI, r->edi, h);
- rdmsr(MSR_IA32_MCG_EBP, r->ebp, h);
- rdmsr(MSR_IA32_MCG_ESP, r->esp, h);
- rdmsr(MSR_IA32_MCG_EFLAGS, r->eflags, h);
- rdmsr(MSR_IA32_MCG_EIP, r->eip, h);
-}
-
-static void intel_machine_check(struct pt_regs *regs, long error_code)
-{
- u32 alow, ahigh, high, low;
- u32 mcgstl, mcgsth;
- int recover = 1;
- int i;
-
- rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
- if (mcgstl & (1<<0)) /* Recoverable ? */
- recover = 0;
-
- printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
- smp_processor_id(), mcgsth, mcgstl);
-
- if (mce_num_extended_msrs > 0) {
- struct intel_mce_extended_msrs dbg;
-
- intel_get_extended_msrs(&dbg);
-
- printk(KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n"
- "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n"
- "\tesi: %08x edi: %08x ebp: %08x esp: %08x\n",
- smp_processor_id(), dbg.eip, dbg.eflags,
- dbg.eax, dbg.ebx, dbg.ecx, dbg.edx,
- dbg.esi, dbg.edi, dbg.ebp, dbg.esp);
- }
-
- for (i = 0; i < nr_mce_banks; i++) {
- rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
- if (high & (1<<31)) {
- char misc[20];
- char addr[24];
-
- misc[0] = addr[0] = '\0';
- if (high & (1<<29))
- recover |= 1;
- if (high & (1<<25))
- recover |= 2;
- high &= ~(1<<31);
- if (high & (1<<27)) {
- rdmsr(MSR_IA32_MC0_MISC+i*4, alow, ahigh);
- snprintf(misc, 20, "[%08x%08x]", ahigh, alow);
- }
- if (high & (1<<26)) {
- rdmsr(MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
- snprintf(addr, 24, " at %08x%08x", ahigh, alow);
- }
- printk(KERN_EMERG "CPU %d: Bank %d: %08x%08x%s%s\n",
- smp_processor_id(), i, high, low, misc, addr);
- }
- }
-
- if (recover & 2)
- panic("CPU context corrupt");
- if (recover & 1)
- panic("Unable to continue");
-
- printk(KERN_EMERG "Attempting to continue.\n");
-
- /*
- * Do not clear the MSR_IA32_MCi_STATUS if the error is not
- * recoverable/continuable.This will allow BIOS to look at the MSRs
- * for errors if the OS could not log the error.
- */
- for (i = 0; i < nr_mce_banks; i++) {
- u32 msr;
- msr = MSR_IA32_MC0_STATUS+i*4;
- rdmsr(msr, low, high);
- if (high&(1<<31)) {
- /* Clear it */
- wrmsr(msr, 0UL, 0UL);
- /* Serialize */
- wmb();
- add_taint(TAINT_MACHINE_CHECK);
- }
- }
- mcgstl &= ~(1<<2);
- wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
-}
-
-void intel_p4_mcheck_init(struct cpuinfo_x86 *c)
-{
- u32 l, h;
- int i;
-
- machine_check_vector = intel_machine_check;
- wmb();
-
- printk(KERN_INFO "Intel machine check architecture supported.\n");
- rdmsr(MSR_IA32_MCG_CAP, l, h);
- if (l & (1<<8)) /* Control register present ? */
- wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
- nr_mce_banks = l & 0xff;
-
- for (i = 0; i < nr_mce_banks; i++) {
- wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
- wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
- }
-
- set_in_cr4(X86_CR4_MCE);
- printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
- smp_processor_id());
-
- /* Check for P4/Xeon extended MCE MSRs */
- rdmsr(MSR_IA32_MCG_CAP, l, h);
- if (l & (1<<9)) {/* MCG_EXT_P */
- mce_num_extended_msrs = (l >> 16) & 0xff;
- printk(KERN_INFO "CPU%d: Intel P4/Xeon Extended MCE MSRs (%d)"
- " available\n",
- smp_processor_id(), mce_num_extended_msrs);
-
-#ifdef CONFIG_X86_MCE_P4THERMAL
- /* Check for P4/Xeon Thermal monitor */
- intel_init_thermal(c);
-#endif
- }
-}
+++ /dev/null
-/*
- * P6 specific Machine Check Exception Reporting
- * (C) Copyright 2002 Alan Cox <alan@lxorguk.ukuu.org.uk>
- */
-#include <linux/interrupt.h>
-#include <linux/kernel.h>
-#include <linux/types.h>
-#include <linux/init.h>
-#include <linux/smp.h>
-
-#include <asm/processor.h>
-#include <asm/system.h>
-#include <asm/mce.h>
-#include <asm/msr.h>
-
-/* Machine Check Handler For PII/PIII */
-static void intel_machine_check(struct pt_regs *regs, long error_code)
-{
- u32 alow, ahigh, high, low;
- u32 mcgstl, mcgsth;
- int recover = 1;
- int i;
-
- rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
- if (mcgstl & (1<<0)) /* Recoverable ? */
- recover = 0;
-
- printk(KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
- smp_processor_id(), mcgsth, mcgstl);
-
- for (i = 0; i < nr_mce_banks; i++) {
- rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
- if (high & (1<<31)) {
- char misc[20];
- char addr[24];
-
- misc[0] = '\0';
- addr[0] = '\0';
-
- if (high & (1<<29))
- recover |= 1;
- if (high & (1<<25))
- recover |= 2;
- high &= ~(1<<31);
-
- if (high & (1<<27)) {
- rdmsr(MSR_IA32_MC0_MISC+i*4, alow, ahigh);
- snprintf(misc, 20, "[%08x%08x]", ahigh, alow);
- }
- if (high & (1<<26)) {
- rdmsr(MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
- snprintf(addr, 24, " at %08x%08x", ahigh, alow);
- }
-
- printk(KERN_EMERG "CPU %d: Bank %d: %08x%08x%s%s\n",
- smp_processor_id(), i, high, low, misc, addr);
- }
- }
-
- if (recover & 2)
- panic("CPU context corrupt");
- if (recover & 1)
- panic("Unable to continue");
-
- printk(KERN_EMERG "Attempting to continue.\n");
- /*
- * Do not clear the MSR_IA32_MCi_STATUS if the error is not
- * recoverable/continuable.This will allow BIOS to look at the MSRs
- * for errors if the OS could not log the error:
- */
- for (i = 0; i < nr_mce_banks; i++) {
- unsigned int msr;
-
- msr = MSR_IA32_MC0_STATUS+i*4;
- rdmsr(msr, low, high);
- if (high & (1<<31)) {
- /* Clear it: */
- wrmsr(msr, 0UL, 0UL);
- /* Serialize: */
- wmb();
- add_taint(TAINT_MACHINE_CHECK);
- }
- }
- mcgstl &= ~(1<<2);
- wrmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
-}
-
-/* Set up machine check reporting for processors with Intel style MCE: */
-void intel_p6_mcheck_init(struct cpuinfo_x86 *c)
-{
- u32 l, h;
- int i;
-
- /* Check for MCE support */
- if (!cpu_has(c, X86_FEATURE_MCE))
- return;
-
- /* Check for PPro style MCA */
- if (!cpu_has(c, X86_FEATURE_MCA))
- return;
-
- /* Ok machine check is available */
- machine_check_vector = intel_machine_check;
- /* Make sure the vector pointer is visible before we enable MCEs: */
- wmb();
-
- printk(KERN_INFO "Intel machine check architecture supported.\n");
- rdmsr(MSR_IA32_MCG_CAP, l, h);
- if (l & (1<<8)) /* Control register present ? */
- wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
- nr_mce_banks = l & 0xff;
-
- /*
- * Following the example in IA-32 SDM Vol 3:
- * - MC0_CTL should not be written
- * - Status registers on all banks should be cleared on reset
- */
- for (i = 1; i < nr_mce_banks; i++)
- wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
-
- for (i = 0; i < nr_mce_banks; i++)
- wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
-
- set_in_cr4(X86_CR4_MCE);
- printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
- smp_processor_id());
-}
git.openpandora.org / pandora-kernel.git / commitdiff