[PATCH] revamped machine check exception support.

- Split out from bluesmoke.c into per-vendor files (Me)
  (If we were that way inclined, we could even make the
   per-vendor bits CONFIG_ options, but thats probably overkill)
- Fixes Kconfig markup. (Roman Zippel)
- P4 can use non-fatal background checker too. (Venkatesh Pallipadi)
- Don't clear MCA status info in case of non-recoverable if
  OS has failed in logging those, BIOS can still ahve a look at
  that info. (Venkatesh)
- We can init bank 0 on P4 (Zwane Mwaikambo)
- Compile away to nothing if CONFIG_X86_MCE=n
- Various other cleaning (Me)

arch/i386/Kconfig

@@ -337,7 +337,6 @@ config PREEMPT
 
 config X86_UP_APIC
 	bool "Local APIC support on uniprocessors" if !SMP
-	default y if SMP
 	---help---
 	  A local APIC (Advanced Programmable Interrupt Controller) is an
 	  integrated interrupt controller in the CPU. If you have a single-CPU
@@ -447,7 +446,7 @@ config X86_MCE
 	  the 386 and 486, so nearly everyone can say Y here.
 
 config X86_MCE_NONFATAL
-	bool "Check for non-fatal errors on Athlon/Duron"
+	bool "Check for non-fatal errors on AMD Athlon/Duron / Intel Pentium 4"
 	depends on X86_MCE
 	help
 	  Enabling this feature starts a timer that triggers every 5 seconds which
@@ -456,12 +455,12 @@ config X86_MCE_NONFATAL
 	  Disable this if you don't want to see these messages.
 	  Seeing the messages this option prints out may be indicative of dying hardware,
 	  or out-of-spec (ie, overclocked) hardware.
-	  This option only does something on hardware with Intel P6 style MCE.
-	  (Pentium Pro and above, AMD Athlon/Duron)
+	  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_MCE && X86_UP_APIC
+	depends on X86_MCE && (X86_UP_APIC || SMP)
 	help
 	  Enabling this feature will cause a message to be printed when the P4
 	  enters thermal throttling.

arch/i386/kernel/Makefile

@@ -8,8 +8,7 @@ export-objs     := mca.o i386_ksyms.o time.o
 
 obj-y	:= process.o semaphore.o signal.o entry.o traps.o irq.o vm86.o \
 		ptrace.o i8259.o ioport.o ldt.o setup.o time.o sys_i386.o \
-		pci-dma.o i386_ksyms.o i387.o bluesmoke.o dmi_scan.o \
-		bootflag.o
+		pci-dma.o i386_ksyms.o i387.o dmi_scan.o bootflag.o
 
 obj-y				+= cpu/
 obj-y				+= timers/

arch/i386/kernel/cpu/Makefile

@@ -13,7 +13,10 @@ obj-y	+=	rise.o
 obj-y	+=	nexgen.o
 obj-y	+=	umc.o
 
+obj-$(CONFIG_X86_MCE)	+=	mcheck/
+
 obj-$(CONFIG_MTRR)	+= 	mtrr/
 obj-$(CONFIG_CPU_FREQ)	+=	cpufreq/
 
+
 include $(TOPDIR)/Rules.make

arch/i386/kernel/cpu/common.c

@@ -358,7 +358,9 @@ void __init identify_cpu(struct cpuinfo_x86 *c)
 	       boot_cpu_data.x86_capability[3]);
 
 	/* Init Machine Check Exception if available. */
+#ifdef CONFIG_X86_MCE
 	mcheck_init(c);
+#endif
 }
 /*
  *	Perform early boot up checks for a valid TSC. See arch/i386/kernel/time.c

arch/i386/kernel/cpu/mcheck/Makefile

+obj-y	=	mce.o k7.o p4.o p5.o p6.o winchip.o
+obj-$(CONFIG_X86_MCE_NONFATAL)	+=	non-fatal.o
+
+include $(TOPDIR)/Rules.make
+

arch/i386/kernel/cpu/mcheck/k7.c

+/*
+ * Athlon specific Machine Check Exception Reporting
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/config.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+
+#include <asm/processor.h> 
+#include <asm/system.h>
+#include <asm/msr.h>
+
+#include "mce.h"
+
+/* Machine Check Handler For AMD Athlon/Duron */
+static void k7_machine_check(struct pt_regs * regs, long error_code)
+{
+	int recover=1;
+	u32 alow, ahigh, high, low;
+	u32 mcgstl, mcgsth;
+	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)) {
+			if (high & (1<<29))
+				recover |= 1;
+			if (high & (1<<25))
+				recover |= 2;
+			printk (KERN_EMERG "Bank %d: %08x%08x", i, high, low);
+			high &= ~(1<<31);
+			if (high & (1<<27)) {
+				rdmsr (MSR_IA32_MC0_MISC+i*4, alow, ahigh);
+				printk ("[%08x%08x]", ahigh, alow);
+			}
+			if (high & (1<<26)) {
+				rdmsr (MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
+				printk (" at %08x%08x", ahigh, alow);
+			}
+			printk ("\n");
+			/* Clear it */
+			wrmsr (MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
+			/* Serialize */
+			wmb();
+		}
+	}
+
+	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 __init amd_mcheck_init(struct cpuinfo_x86 *c)
+{
+	u32 l, h;
+	int i;
+
+	machine_check_vector = k7_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());
+
+#ifdef CONFIG_X86_MCE_NONFATAL
+	init_nonfatal_mce_checker();
+#endif
+}

arch/i386/kernel/cpu/mcheck/mce.c

+/*
+ * mce.c - x86 Machine Check Exception Reporting
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/config.h>
+#include <linux/smp.h>
+#include <asm/processor.h> 
+#include <asm/system.h>
+#include <asm/thread_info.h>
+
+#include "mce.h"
+
+int mce_disabled __initdata = 0;
+int nr_mce_banks;
+
+/* Handle unconfigured int18 (should never happen) */
+static void unexpected_machine_check(struct pt_regs * regs, long error_code)
+{	
+	printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n", smp_processor_id());
+}
+
+/* Call the installed machine check handler for this CPU setup. */
+void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check;
+
+asmlinkage void do_machine_check(struct pt_regs * regs, long error_code)
+{
+	machine_check_vector(regs, error_code);
+}
+
+/* This has to be run for each processor */
+void __init mcheck_init(struct cpuinfo_x86 *c)
+{
+	if (mce_disabled==1)
+		return;
+
+	switch (c->x86_vendor) {
+		case X86_VENDOR_AMD:
+			if (c->x86==6 || c->x86==15)
+				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;
+	}
+}
+
+static int __init mcheck_disable(char *str)
+{
+	mce_disabled = 1;
+	return 0;
+}
+
+static int __init mcheck_enable(char *str)
+{
+	mce_disabled = -1;
+	return 0;
+}
+
+__setup("nomce", mcheck_disable);
+__setup("mce", mcheck_enable);

arch/i386/kernel/cpu/mcheck/mce.h

+#include <linux/init.h>
+
+void amd_mcheck_init(struct cpuinfo_x86 *c);
+void intel_p4_mcheck_init(struct cpuinfo_x86 *c);
+void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
+void intel_p6_mcheck_init(struct cpuinfo_x86 *c);
+void winchip_mcheck_init(struct cpuinfo_x86 *c);
+
+void init_nonfatal_mce_checker(void);
+
+/* Call the installed machine check handler for this CPU setup. */
+extern void (*machine_check_vector)(struct pt_regs *, long error_code);
+
+extern int mce_disabled __initdata;
+extern int nr_mce_banks;
+

arch/i386/kernel/cpu/mcheck/non-fatal.c

+/*
+ * P4 specific Machine Check Exception Reporting
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/config.h>
+#include <linux/irq.h>
+#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+
+#include <asm/processor.h> 
+#include <asm/system.h>
+#include <asm/msr.h>
+
+#include "mce.h"
+
+static struct timer_list mce_timer;
+static int timerset;
+
+#define MCE_RATE	15*HZ	/* timer rate is 15s */
+
+static void mce_checkregs (void *info)
+{
+	u32 low, high;
+	int i;
+
+	preempt_disable(); 
+	for (i=0; i<nr_mce_banks; i++) {
+		rdmsr (MSR_IA32_MC0_STATUS+i*4, low, high);
+
+		if (high & (1<<31)) {
+			printk (KERN_EMERG "MCE: The hardware reports a non fatal, correctable incident occured on CPU %d.\n",
+				smp_processor_id());
+			printk (KERN_EMERG "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();
+		}
+	}
+	preempt_enable();
+}
+
+static void do_mce_timer(void *data)
+{ 
+	mce_checkregs (NULL);
+	smp_call_function (mce_checkregs, NULL, 1, 1);
+} 
+
+static DECLARE_WORK(mce_work, do_mce_timer, NULL);
+
+static void mce_timerfunc (unsigned long data)
+{
+#ifdef CONFIG_SMP
+	if (num_online_cpus() > 1) 
+		schedule_work (&mce_work); 
+#else
+	mce_checkregs (NULL);
+#endif
+	mce_timer.expires = jiffies + MCE_RATE;
+	add_timer (&mce_timer);
+}	
+
+void init_nonfatal_mce_checker()
+{
+	if (timerset == 0) {
+		/* Set the timer to check for non-fatal
+		   errors every MCE_RATE seconds */
+		init_timer (&mce_timer);
+		mce_timer.expires = jiffies + MCE_RATE;
+		mce_timer.data = 0;
+		mce_timer.function = &mce_timerfunc;
+		add_timer (&mce_timer);
+		timerset = 1;
+		printk(KERN_INFO "Machine check exception polling timer started.\n");
+	}
+}

arch/i386/kernel/bluesmoke.c → arch/i386/kernel/cpu/mcheck/p4.c

 /*
- * arch/i386/kernel/bluesmoke.c - x86 Machine Check Exception Reporting
+ * P4 specific Machine Check Exception Reporting
  */
 
 #include <linux/init.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
-#include <linux/jiffies.h>
-#include <linux/smp.h>
 #include <linux/config.h>
 #include <linux/irq.h>
-#include <linux/workqueue.h>
 #include <linux/interrupt.h>
+#include <linux/smp.h>
 
 #include <asm/processor.h> 
 #include <asm/system.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
-#include <asm/pgtable.h>
-#include <asm/tlbflush.h>
-#include <asm/hardirq.h>
 
-#ifdef CONFIG_X86_MCE
+#include "mce.h"
 
 /* as supported by the P4/Xeon family */
 struct intel_mce_extended_msrs {
@@ -37,17 +32,16 @@ struct intel_mce_extended_msrs {
 	/* u32 *reserved[]; */
 };
 
-static int mce_disabled __initdata = 0;
-
 static int mce_num_extended_msrs = 0;
-static int banks;
 
 
 #ifdef CONFIG_X86_MCE_P4THERMAL
-/*
- *	P4/Xeon Thermal transition interrupt handler
- */
+static void unexpected_thermal_interrupt(struct pt_regs *regs)
+{	
+	printk(KERN_ERR "CPU#%d: Unexpected LVT TMR interrupt!\n", smp_processor_id());
+}
 
+/* P4/Xeon Thermal transition interrupt handler */
 static void intel_thermal_interrupt(struct pt_regs *regs)
 {
 	u32 l, h;
@@ -55,7 +49,7 @@ static void intel_thermal_interrupt(struct pt_regs *regs)
 
 	ack_APIC_irq();
 
-	rdmsr(MSR_IA32_THERM_STATUS, l, h);
+	rdmsr (MSR_IA32_THERM_STATUS, l, h);
 	if (l & 1) {
 		printk(KERN_EMERG "CPU#%d: Temperature above threshold\n", cpu);
 		printk(KERN_EMERG "CPU#%d: Running in modulated clock mode\n", cpu);
@@ -64,15 +58,7 @@ static void intel_thermal_interrupt(struct pt_regs *regs)
 	}
 }
 
-static void unexpected_thermal_interrupt(struct pt_regs *regs)
-{	
-	printk(KERN_ERR "CPU#%d: Unexpected LVT TMR interrupt!\n", smp_processor_id());
-}
-
-/*
- *	Thermal interrupt handler for this CPU setup
- */
-
+/* Thermal interrupt handler for this CPU setup */
 static void (*vendor_thermal_interrupt)(struct pt_regs *regs) = unexpected_thermal_interrupt;
 
 asmlinkage void smp_thermal_interrupt(struct pt_regs regs)
@@ -83,7 +69,6 @@ asmlinkage void smp_thermal_interrupt(struct pt_regs regs)
 }
 
 /* P4/Xeon Thermal regulation detect and init */
-
 static void __init intel_init_thermal(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
@@ -101,7 +86,7 @@ static void __init intel_init_thermal(struct cpuinfo_x86 *c)
 	 * be some SMM goo which handles it, so we can't even put a handler
 	 * since it might be delivered via SMI already -zwanem.
 	 */
-	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
+	rdmsr (MSR_IA32_MISC_ENABLE, l, h);
 	h = apic_read(APIC_LVTTHMR);
 	if ((l & (1<<3)) && (h & APIC_DM_SMI)) {
 		printk(KERN_DEBUG "CPU#%d: Thermal monitoring handled by SMI\n", cpu);
@@ -120,25 +105,24 @@ static void __init intel_init_thermal(struct cpuinfo_x86 *c)
 	h |= (APIC_DM_FIXED | APIC_LVT_MASKED);	/* we'll mask till we're ready */
 	apic_write_around(APIC_LVTTHMR, h);
 
-	rdmsr(MSR_IA32_THERM_INTERRUPT, l, h);
-	wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
+	rdmsr (MSR_IA32_THERM_INTERRUPT, l, h);
+	wrmsr (MSR_IA32_THERM_INTERRUPT, l | 0x03 , h);
 
 	/* ok we're good to go... */
 	vendor_thermal_interrupt = intel_thermal_interrupt;
 	
-	rdmsr(MSR_IA32_MISC_ENABLE, l, h);
-	wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+	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);
+	l = apic_read (APIC_LVTTHMR);
+	apic_write_around (APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
+	printk (KERN_INFO "CPU#%d: Thermal monitoring enabled\n", cpu);
 	return;
 }
 #endif /* CONFIG_X86_MCE_P4THERMAL */
 
 
 /* P4/Xeon Extended MCE MSR retrieval, return 0 if unsupported */
-
 static int inline intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 {
 	u32 h;
@@ -146,16 +130,16 @@ static int inline intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 	if (mce_num_extended_msrs == 0)
 		goto done;
 
-	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);
+	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);
 
 	/* can we rely on kmalloc to do a dynamic
 	 * allocation for the reserved registers?
@@ -164,10 +148,6 @@ static int inline intel_get_extended_msrs(struct intel_mce_extended_msrs *r)
 	return mce_num_extended_msrs;
 }
 
-/*
- *	Machine Check Handler For PII/PIII
- */
-
 static void intel_machine_check(struct pt_regs * regs, long error_code)
 {
 	int recover=1;
@@ -176,329 +156,106 @@ static void intel_machine_check(struct pt_regs * regs, long error_code)
 	int i;
 	struct intel_mce_extended_msrs dbg;
 
-	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
-	if(mcgstl&(1<<0))	/* Recoverable ? */
+	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);
+	printk (KERN_EMERG "CPU %d: Machine Check Exception: %08x%08x\n",
+		smp_processor_id(), mcgsth, mcgstl);
 
 	if (intel_get_extended_msrs(&dbg)) {
-		printk(KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n",
+		printk (KERN_DEBUG "CPU %d: EIP: %08x EFLAGS: %08x\n",
 			smp_processor_id(), dbg.eip, dbg.eflags);
-		printk(KERN_DEBUG "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n",
+		printk (KERN_DEBUG "\teax: %08x ebx: %08x ecx: %08x edx: %08x\n",
 			dbg.eax, dbg.ebx, dbg.ecx, dbg.edx);
-		printk(KERN_DEBUG "\tesi: %08x edi: %08x ebp: %08x esp: %08x\n",
+		printk (KERN_DEBUG "\tesi: %08x edi: %08x ebp: %08x esp: %08x\n",
 			dbg.esi, dbg.edi, dbg.ebp, dbg.esp);
 	}
 
-	for (i=0;i<banks;i++) {
-		rdmsr(MSR_IA32_MC0_STATUS+i*4,low, high);
-		if(high&(1<<31)) {
-			if(high&(1<<29))
-				recover|=1;
-			if(high&(1<<25))
-				recover|=2;
-			printk(KERN_EMERG "Bank %d: %08x%08x", i, high, low);
-			high&=~(1<<31);
-			if(high&(1<<27)) {
-				rdmsr(MSR_IA32_MC0_MISC+i*4, alow, ahigh);
-				printk("[%08x%08x]", ahigh, alow);
+	for (i=0; i<nr_mce_banks; i++) {
+		rdmsr (MSR_IA32_MC0_STATUS+i*4,low, high);
+		if (high & (1<<31)) {
+			if (high & (1<<29))
+				recover |= 1;
+			if (high & (1<<25))
+				recover |= 2;
+			printk (KERN_EMERG "Bank %d: %08x%08x", i, high, low);
+			high &= ~(1<<31);
+			if (high & (1<<27)) {
+				rdmsr (MSR_IA32_MC0_MISC+i*4, alow, ahigh);
+				printk ("[%08x%08x]", ahigh, alow);
 			}
-			if(high&(1<<26)) {
-				rdmsr(MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
-				printk(" at %08x%08x", ahigh, alow);
+			if (high & (1<<26)) {
+				rdmsr (MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
+				printk (" at %08x%08x", ahigh, alow);
 			}
-			printk("\n");
-			/* Clear it */
-			wrmsr(MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
-			/* Serialize */
-			wmb();
+			printk ("\n");
 		}
 	}
 
-	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);
-}
+	if (recover & 2)
+		panic ("CPU context corrupt");
+	if (recover & 1)
+		panic ("Unable to continue");
 
-/*
- *	Machine check handler for Pentium class Intel
- */
-
-static void pentium_machine_check(struct pt_regs * regs, long error_code)
-{
-	u32 loaddr, hi, lotype;
-	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
-	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
-	printk(KERN_EMERG "CPU#%d: Machine Check Exception:  0x%8X (type 0x%8X).\n", smp_processor_id(), loaddr, lotype);
-	if(lotype&(1<<5))
-		printk(KERN_EMERG "CPU#%d: Possible thermal failure (CPU on fire ?).\n", smp_processor_id());
-}
-
-/*
- *	Machine check handler for WinChip C6
- */
-
-static void winchip_machine_check(struct pt_regs * regs, long error_code)
-{
-	printk(KERN_EMERG "CPU#%d: Machine Check Exception.\n", smp_processor_id());
-}
-
-/*
- *	Handle unconfigured int18 (should never happen)
- */
-
-static void unexpected_machine_check(struct pt_regs * regs, long error_code)
-{	
-	printk(KERN_ERR "CPU#%d: Unexpected int18 (Machine Check).\n", smp_processor_id());
-}
-
-/*
- *	Call the installed machine check handler for this CPU setup.
+	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.
 	 */
-
-static void (*machine_check_vector)(struct pt_regs *, long error_code) = unexpected_machine_check;
-
-asmlinkage void do_machine_check(struct pt_regs * regs, long error_code)
-{
-	machine_check_vector(regs, error_code);
-}
-
-
-#ifdef CONFIG_X86_MCE_NONFATAL
-static struct timer_list mce_timer;
-static int timerset = 0;
-
-#define MCE_RATE	15*HZ	/* timer rate is 15s */
-
-static void mce_checkregs (void *info)
-{
-	u32 low, high;
-	int i;
-
-	preempt_disable(); 
-	for (i=0; i<banks; i++) {
-		rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
-
-		if ((low | high) != 0) {
-			printk (KERN_EMERG "MCE: The hardware reports a non fatal, correctable incident occured on CPU %d.\n", smp_processor_id());
-			printk (KERN_EMERG "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);
-
+	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();
 		}
 	}
-	preempt_enable();
-}
-
-static void do_mce_timer(void *data)
-{ 
-	smp_call_function (mce_checkregs, NULL, 1, 1);
+	mcgstl &= ~(1<<2);
+	wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
 }
 
-static DECLARE_WORK(mce_work, do_mce_timer, NULL);
 
-static void mce_timerfunc (unsigned long data)
-{
-#ifdef CONFIG_SMP
-	if (num_online_cpus() > 1) 
-		schedule_work(&mce_work); 
-#else
-	mce_checkregs(NULL);
-#endif
-	mce_timer.expires = jiffies + MCE_RATE;
-	add_timer (&mce_timer);
-}	
-#endif
-
-
-/*
- *	Set up machine check reporting for processors with Intel style MCE
- */
-
-static void __init intel_mcheck_init(struct cpuinfo_x86 *c)
+void __init intel_p4_mcheck_init(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 	int i;
-	static int done;
-	
-	/*
-	 *	Check for MCE support
-	 */
-
-	if( !cpu_has(c, X86_FEATURE_MCE) )
-		return;	
-
-	/*
-	 *	Pentium machine check
-	 */
-
-	if(c->x86 == 5)
-	{
-		/* Default P5 to off as its often misconnected */
-		if(mce_disabled != -1)
-			return;
-		machine_check_vector = pentium_machine_check;
-		wmb();
-		/* Read registers before enabling */
-		rdmsr(MSR_IA32_P5_MC_ADDR, l, h);
-		rdmsr(MSR_IA32_P5_MC_TYPE, l, h);
-		if(done==0)
-			printk(KERN_INFO "Intel old style machine check architecture supported.\n");
- 		/* Enable MCE */
-		set_in_cr4(X86_CR4_MCE);
-		printk(KERN_INFO "Intel old style machine check reporting enabled on CPU#%d.\n", smp_processor_id());
-		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;
 	wmb();
 
-	if(done==0)
-		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);
-	banks = l&0xff;
-
-	/* Don't enable bank 0 on intel P6 cores, it goes bang quickly. */
-	if (c->x86_vendor == X86_VENDOR_INTEL && c->x86 == 6) {
-		for(i=1; i<banks; i++)
-			wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
-	} else {
-		for(i=0; i<banks; i++)
-			wrmsr(MSR_IA32_MC0_CTL+4*i, 0xffffffff, 0xffffffff);
-	}
-
-	for(i=0; i<banks; i++)
-		wrmsr(MSR_IA32_MC0_STATUS+4*i, 0x0, 0x0);
+	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;
 
-	set_in_cr4(X86_CR4_MCE);
-	printk(KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n", smp_processor_id());
+	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);
+	}
 
-	/*
-	 *	Check for P4/Xeon specific MCE extensions
-	 */
+	set_in_cr4 (X86_CR4_MCE);
+	printk (KERN_INFO "Intel machine check reporting enabled on CPU#%d.\n",
+		smp_processor_id());
 
-	if (c->x86_vendor == X86_VENDOR_INTEL && c->x86 == 15) {
 	/* Check for P4/Xeon extended MCE MSRs */
-		rdmsr(MSR_IA32_MCG_CAP, l, h);
+	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",
+		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
 	}
-
-	done=1;
-}
-
-/*
- *	Set up machine check reporting on the Winchip C6 series
- */
-
-static void __init winchip_mcheck_init(struct cpuinfo_x86 *c)
-{
-	u32 lo, hi;
-	/* Not supported on C3 */
-	if(c->x86 != 5)
-		return;
-	/* Winchip C6 */
-	machine_check_vector = winchip_machine_check;
-	wmb();
-	rdmsr(MSR_IDT_FCR1, lo, hi);
-	lo|= (1<<2);	/* Enable EIERRINT (int 18 MCE) */
-	lo&= ~(1<<4);	/* Enable MCE */
-	wrmsr(MSR_IDT_FCR1, lo, hi);
-	set_in_cr4(X86_CR4_MCE);
-	printk(KERN_INFO "Winchip machine check reporting enabled on CPU#%d.\n", smp_processor_id());
-}
-
-
-/*
- *	This has to be run for each processor
- */
-
-void __init mcheck_init(struct cpuinfo_x86 *c)
-{
-
-	if(mce_disabled==1)
-		return;
-
-	switch(c->x86_vendor)
-	{
-		case X86_VENDOR_AMD:
-			/* AMD K7 machine check is Intel like */
-			if(c->x86 == 6 || c->x86 == 15) {
-				intel_mcheck_init(c);
 #ifdef CONFIG_X86_MCE_NONFATAL
-				if (timerset == 0) {
-					/* Set the timer to check for non-fatal
-					   errors every MCE_RATE seconds */
-					init_timer (&mce_timer);
-					mce_timer.expires = jiffies + MCE_RATE;
-					mce_timer.data = 0;
-					mce_timer.function = &mce_timerfunc;
-					add_timer (&mce_timer);
-					timerset = 1;
-					printk(KERN_INFO "Machine check exception polling timer started.\n");
-				}
+	init_nonfatal_mce_checker();
 #endif
-			}
-			break;
-
-		case X86_VENDOR_INTEL:
-			intel_mcheck_init(c);
-			break;
-
-		case X86_VENDOR_CENTAUR:
-			winchip_mcheck_init(c);
-			break;
-
-		default:
-			break;
-	}
 }
-
-static int __init mcheck_disable(char *str)
-{
-	mce_disabled = 1;
-	return 0;
-}
-
-static int __init mcheck_enable(char *str)
-{
-	mce_disabled = -1;
-	return 0;
-}
-
-__setup("nomce", mcheck_disable);
-__setup("mce", mcheck_enable);
-
-#else
-asmlinkage void do_machine_check(struct pt_regs * regs, long error_code) {}
-asmlinkage void smp_thermal_interrupt(struct pt_regs regs) {}
-void __init mcheck_init(struct cpuinfo_x86 *c) {}
-#endif

arch/i386/kernel/cpu/mcheck/p5.c

+/*
+ * P5 specific Machine Check Exception Reporting
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+
+#include <asm/processor.h> 
+#include <asm/system.h>
+#include <asm/msr.h>
+
+#include "mce.h"
+
+/* Machine check handler for Pentium class Intel */
+static void pentium_machine_check(struct pt_regs * regs, long error_code)
+{
+	u32 loaddr, hi, lotype;
+	rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi);
+	rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi);
+	printk(KERN_EMERG "CPU#%d: Machine Check Exception:  0x%8X (type 0x%8X).\n", smp_processor_id(), loaddr, lotype);
+	if(lotype&(1<<5))
+		printk(KERN_EMERG "CPU#%d: Possible thermal failure (CPU on fire ?).\n", smp_processor_id());
+}
+
+/* Set up machine check reporting for processors with Intel style MCE */
+void __init intel_p5_mcheck_init(struct cpuinfo_x86 *c)
+{
+	u32 l, h;
+	
+	/*Check for MCE support */
+	if( !cpu_has(c, X86_FEATURE_MCE) )
+		return;	
+
+	/* Default P5 to off as its often misconnected */
+	if(mce_disabled != -1)
+		return;
+	machine_check_vector = pentium_machine_check;
+	wmb();
+
+	/* Read registers before enabling */
+	rdmsr(MSR_IA32_P5_MC_ADDR, l, h);
+	rdmsr(MSR_IA32_P5_MC_TYPE, l, h);
+	printk(KERN_INFO "Intel old style machine check architecture supported.\n");
+
+ 	/* Enable MCE */
+	set_in_cr4(X86_CR4_MCE);
+	printk(KERN_INFO "Intel old style machine check reporting enabled on CPU#%d.\n", smp_processor_id());
+}

arch/i386/kernel/cpu/mcheck/p6.c

+/*
+ * P6 specific Machine Check Exception Reporting
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+#include <linux/smp.h>
+
+#include <asm/processor.h> 
+#include <asm/system.h>
+#include <asm/msr.h>
+
+#include "mce.h"
+
+/* Machine Check Handler For PII/PIII */
+static void intel_machine_check(struct pt_regs * regs, long error_code)
+{
+	int recover=1;
+	u32 alow, ahigh, high, low;
+	u32 mcgstl, mcgsth;
+	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)) {
+			if (high & (1<<29))
+				recover |= 1;
+			if (high & (1<<25))
+				recover |= 2;
+			printk (KERN_EMERG "Bank %d: %08x%08x", i, high, low);
+			high &= ~(1<<31);
+			if (high & (1<<27)) {
+				rdmsr (MSR_IA32_MC0_MISC+i*4, alow, ahigh);
+				printk ("[%08x%08x]", ahigh, alow);
+			}
+			if (high & (1<<26)) {
+				rdmsr (MSR_IA32_MC0_ADDR+i*4, alow, ahigh);
+				printk (" at %08x%08x", ahigh, alow);
+			}
+			printk ("\n");
+		}
+	}
+
+	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();
+		}
+	}
+	mcgstl &= ~(1<<2);
+	wrmsr (MSR_IA32_MCG_STATUS,mcgstl, mcgsth);
+}
+
+/* Set up machine check reporting for processors with Intel style MCE */
+void __init 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;
+	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;
+
+	/* Don't enable bank 0 on intel P6 cores, it goes bang quickly. */
+	for (i=1; 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());
+}

arch/i386/kernel/cpu/mcheck/winchip.c

+/*
+ * IDT Winchip specific Machine Check Exception Reporting
+ */
+
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/irq.h>
+#include <linux/interrupt.h>
+
+#include <asm/processor.h> 
+#include <asm/system.h>
+#include <asm/msr.h>
+
+#include "mce.h"
+
+/* Machine check handler for WinChip C6 */
+static void winchip_machine_check(struct pt_regs * regs, long error_code)
+{
+	printk(KERN_EMERG "CPU0: Machine Check Exception.\n");
+}
+
+/* Set up machine check reporting on the Winchip C6 series */
+void __init winchip_mcheck_init(struct cpuinfo_x86 *c)
+{
+	u32 lo, hi;
+	machine_check_vector = winchip_machine_check;
+	wmb();
+	rdmsr(MSR_IDT_FCR1, lo, hi);
+	lo|= (1<<2);	/* Enable EIERRINT (int 18 MCE) */
+	lo&= ~(1<<4);	/* Enable MCE */
+	wrmsr(MSR_IDT_FCR1, lo, hi);
+	set_in_cr4(X86_CR4_MCE);
+	printk(KERN_INFO "Winchip machine check reporting enabled on CPU#0.\n");
+}

arch/i386/kernel/entry.S

@@ -471,10 +471,12 @@ ENTRY(page_fault)
 	pushl $do_page_fault
 	jmp error_code
 
+#ifdef CONFIG_X86_MCE
 ENTRY(machine_check)
 	pushl $0
 	pushl $do_machine_check
 	jmp error_code
+#endif
 
 ENTRY(spurious_interrupt_bug)
 	pushl $0

arch/i386/kernel/traps.c

@@ -906,7 +906,9 @@ void __init trap_init(void)
 	set_trap_gate(15,&spurious_interrupt_bug);
 	set_trap_gate(16,&coprocessor_error);
 	set_trap_gate(17,&alignment_check);
+#ifdef CONFIG_X86_MCE
 	set_trap_gate(18,&machine_check);
+#endif
 	set_trap_gate(19,&simd_coprocessor_error);
 
 	set_system_gate(SYSCALL_VECTOR,&system_call);