Merge branch 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'x86-mce-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (80 commits)
  x86, mce: Add boot options for corrected errors
  x86, mce: Fix mce printing
  x86, mce: fix for mce counters
  x86, mce: support action-optional machine checks
  x86, mce: define MCE_VECTOR
  x86, mce: rename mce_notify_user to mce_notify_irq
  x86: fix panic with interrupts off (needed for MCE)
  x86, mce: export MCE severities coverage via debugfs
  x86, mce: implement new status bits
  x86, mce: print header/footer only once for multiple MCEs
  x86, mce: default to panic timeout for machine checks
  x86, mce: improve mce_get_rip
  x86, mce: make non Monarch panic message "Fatal machine check" too
  x86, mce: switch x86 machine check handler to Monarch election.
  x86, mce: implement panic synchronization
  x86, mce: implement bootstrapping for machine check wakeups
  x86, mce: check early in exception handler if panic is needed
  x86, mce: add table driven machine check grading
  x86, mce: remove TSC print heuristic
  x86, mce: log corrected errors when panicing
  ...

34 files changed, 2908 insertions, 1660 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 68f5578fe38..356d2ec8e2f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -789,10 +789,26 @@ config X86_MCE
 	  to disable it.  MCE support simply ignores non-MCE processors like
 	  the 386 and 486, so nearly everyone can say Y here.
 
+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
+
 config X86_MCE_INTEL
 	def_bool y
 	prompt "Intel MCE features"
-	depends on X86_64 && X86_MCE && X86_LOCAL_APIC
+	depends on X86_NEW_MCE && X86_LOCAL_APIC
 	---help---
 	   Additional support for intel specific MCE features such as
 	   the thermal monitor.
@@ -800,19 +816,36 @@ config X86_MCE_INTEL
 config X86_MCE_AMD
 	def_bool y
 	prompt "AMD MCE features"
-	depends on X86_64 && X86_MCE && X86_LOCAL_APIC
+	depends on X86_NEW_MCE && X86_LOCAL_APIC
 	---help---
 	   Additional support for AMD specific MCE features such as
 	   the DRAM Error Threshold.
 
+config X86_ANCIENT_MCE
+	def_bool n
+	depends on X86_32
+	prompt "Support for old Pentium 5 / WinChip machine checks"
+	---help---
+	  Include support for machine check handling on old Pentium 5 or WinChip
+	  systems. These typically need to be enabled explicitely on the command
+	  line.
+
 config X86_MCE_THRESHOLD
 	depends on X86_MCE_AMD || X86_MCE_INTEL
 	bool
 	default y
 
+config X86_MCE_INJECT
+	depends on X86_NEW_MCE
+	tristate "Machine check injector support"
+	---help---
+	  Provide support for injecting machine checks for testing purposes.
+	  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_32 && X86_MCE
+	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.
@@ -825,11 +858,15 @@ config X86_MCE_NONFATAL
 
 config X86_MCE_P4THERMAL
 	bool "check for P4 thermal throttling interrupt."
-	depends on X86_32 && X86_MCE && (X86_UP_APIC || SMP)
+	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
+
 config VM86
 	bool "Enable VM86 support" if EMBEDDED
 	default y
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h
index d750a10ccad..ff8cbfa0785 100644
--- a/arch/x86/include/asm/entry_arch.h
+++ b/arch/x86/include/asm/entry_arch.h
@@ -14,6 +14,7 @@ BUILD_INTERRUPT(reschedule_interrupt,RESCHEDULE_VECTOR)
 BUILD_INTERRUPT(call_function_interrupt,CALL_FUNCTION_VECTOR)
 BUILD_INTERRUPT(call_function_single_interrupt,CALL_FUNCTION_SINGLE_VECTOR)
 BUILD_INTERRUPT(irq_move_cleanup_interrupt,IRQ_MOVE_CLEANUP_VECTOR)
+BUILD_INTERRUPT(reboot_interrupt,REBOOT_VECTOR)
 
 BUILD_INTERRUPT3(invalidate_interrupt0,INVALIDATE_TLB_VECTOR_START+0,
 		 smp_invalidate_interrupt)
@@ -52,8 +53,16 @@ BUILD_INTERRUPT(spurious_interrupt,SPURIOUS_APIC_VECTOR)
 BUILD_INTERRUPT(perf_pending_interrupt, LOCAL_PENDING_VECTOR)
 #endif
 
-#ifdef CONFIG_X86_MCE_P4THERMAL
+#ifdef CONFIG_X86_THERMAL_VECTOR
 BUILD_INTERRUPT(thermal_interrupt,THERMAL_APIC_VECTOR)
 #endif
 
+#ifdef CONFIG_X86_MCE_THRESHOLD
+BUILD_INTERRUPT(threshold_interrupt,THRESHOLD_APIC_VECTOR)
+#endif
+
+#ifdef CONFIG_X86_NEW_MCE
+BUILD_INTERRUPT(mce_self_interrupt,MCE_SELF_VECTOR)
+#endif
+
 #endif
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 9ebc5c25503..82e3e8f0104 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -22,7 +22,7 @@ typedef struct {
 #endif
 #ifdef CONFIG_X86_MCE
 	unsigned int irq_thermal_count;
-# ifdef CONFIG_X86_64
+# ifdef CONFIG_X86_MCE_THRESHOLD
 	unsigned int irq_threshold_count;
 # endif
 #endif
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 6df45f63966..ba180d93b08 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -34,6 +34,7 @@ extern void perf_pending_interrupt(void);
 extern void spurious_interrupt(void);
 extern void thermal_interrupt(void);
 extern void reschedule_interrupt(void);
+extern void mce_self_interrupt(void);
 
 extern void invalidate_interrupt(void);
 extern void invalidate_interrupt0(void);
@@ -46,6 +47,7 @@ extern void invalidate_interrupt6(void);
 extern void invalidate_interrupt7(void);
 
 extern void irq_move_cleanup_interrupt(void);
+extern void reboot_interrupt(void);
 extern void threshold_interrupt(void);
 
 extern void call_function_interrupt(void);
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index e997be98c9b..5b21f0ec3df 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -25,6 +25,7 @@
  */
 
 #define NMI_VECTOR			0x02
+#define MCE_VECTOR			0x12
 
 /*
  * IDT vectors usable for external interrupt sources start
@@ -87,13 +88,8 @@
 #define CALL_FUNCTION_VECTOR		0xfc
 #define CALL_FUNCTION_SINGLE_VECTOR	0xfb
 #define THERMAL_APIC_VECTOR		0xfa
-
-#ifdef CONFIG_X86_32
-/* 0xf8 - 0xf9 : free */
-#else
-# define THRESHOLD_APIC_VECTOR		0xf9
-# define UV_BAU_MESSAGE			0xf8
-#endif
+#define THRESHOLD_APIC_VECTOR		0xf9
+#define REBOOT_VECTOR			0xf8
 
 /* f0-f7 used for spreading out TLB flushes: */
 #define INVALIDATE_TLB_VECTOR_END	0xf7
@@ -117,6 +113,13 @@
  */
 #define LOCAL_PENDING_VECTOR		0xec
 
+#define UV_BAU_MESSAGE			0xec
+
+/*
+ * Self IPI vector for machine checks
+ */
+#define MCE_SELF_VECTOR			0xeb
+
 /*
  * First APIC vector available to drivers: (vectors 0x30-0xee) we
  * start at 0x31(0x41) to spread out vectors evenly between priority
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4f8c199584e..540a466e50f 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -1,8 +1,6 @@
 #ifndef _ASM_X86_MCE_H
 #define _ASM_X86_MCE_H
 
-#ifdef __x86_64__
-
 #include <linux/types.h>
 #include <asm/ioctls.h>
 
@@ -10,21 +8,35 @@
  * Machine Check support for x86
  */
 
-#define MCG_CTL_P	 (1UL<<8)   /* MCG_CAP register available */
-#define MCG_EXT_P	 (1ULL<<9)   /* Extended registers available */
-#define MCG_CMCI_P	 (1ULL<<10)  /* CMCI supported */
-
-#define MCG_STATUS_RIPV  (1UL<<0)   /* restart ip valid */
-#define MCG_STATUS_EIPV  (1UL<<1)   /* ip points to correct instruction */
-#define MCG_STATUS_MCIP  (1UL<<2)   /* machine check in progress */
-
-#define MCI_STATUS_VAL   (1UL<<63)  /* valid error */
-#define MCI_STATUS_OVER  (1UL<<62)  /* previous errors lost */
-#define MCI_STATUS_UC    (1UL<<61)  /* uncorrected error */
-#define MCI_STATUS_EN    (1UL<<60)  /* error enabled */
-#define MCI_STATUS_MISCV (1UL<<59)  /* misc error reg. valid */
-#define MCI_STATUS_ADDRV (1UL<<58)  /* addr reg. valid */
-#define MCI_STATUS_PCC   (1UL<<57)  /* processor context corrupt */
+#define MCG_BANKCNT_MASK	0xff         /* Number of Banks */
+#define MCG_CTL_P		(1ULL<<8)    /* MCG_CAP register available */
+#define MCG_EXT_P		(1ULL<<9)    /* Extended registers available */
+#define MCG_CMCI_P		(1ULL<<10)   /* CMCI supported */
+#define MCG_EXT_CNT_MASK	0xff0000     /* Number of Extended registers */
+#define MCG_EXT_CNT_SHIFT	16
+#define MCG_EXT_CNT(c)		(((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT)
+#define MCG_SER_P	 	(1ULL<<24)   /* MCA recovery/new status bits */
+
+#define MCG_STATUS_RIPV  (1ULL<<0)   /* restart ip valid */
+#define MCG_STATUS_EIPV  (1ULL<<1)   /* ip points to correct instruction */
+#define MCG_STATUS_MCIP  (1ULL<<2)   /* machine check in progress */
+
+#define MCI_STATUS_VAL   (1ULL<<63)  /* valid error */
+#define MCI_STATUS_OVER  (1ULL<<62)  /* previous errors lost */
+#define MCI_STATUS_UC    (1ULL<<61)  /* uncorrected error */
+#define MCI_STATUS_EN    (1ULL<<60)  /* error enabled */
+#define MCI_STATUS_MISCV (1ULL<<59)  /* misc error reg. valid */
+#define MCI_STATUS_ADDRV (1ULL<<58)  /* addr reg. valid */
+#define MCI_STATUS_PCC   (1ULL<<57)  /* processor context corrupt */
+#define MCI_STATUS_S	 (1ULL<<56)  /* Signaled machine check */
+#define MCI_STATUS_AR	 (1ULL<<55)  /* Action required */
+
+/* MISC register defines */
+#define MCM_ADDR_SEGOFF  0	/* segment offset */
+#define MCM_ADDR_LINEAR  1	/* linear address */
+#define MCM_ADDR_PHYS	 2	/* physical address */
+#define MCM_ADDR_MEM	 3	/* memory address */
+#define MCM_ADDR_GENERIC 7	/* generic */
 
 /* Fields are zero when not available */
 struct mce {
@@ -34,13 +46,19 @@ struct mce {
 	__u64 mcgstatus;
 	__u64 ip;
 	__u64 tsc;	/* cpu time stamp counter */
-	__u64 res1;	/* for future extension */
-	__u64 res2;	/* dito. */
+	__u64 time;	/* wall time_t when error was detected */
+	__u8  cpuvendor;	/* cpu vendor as encoded in system.h */
+	__u8  pad1;
+	__u16 pad2;
+	__u32 cpuid;	/* CPUID 1 EAX */
 	__u8  cs;		/* code segment */
 	__u8  bank;	/* machine check bank */
-	__u8  cpu;	/* cpu that raised the error */
+	__u8  cpu;	/* cpu number; obsolete; use extcpu now */
 	__u8  finished;   /* entry is valid */
-	__u32 pad;
+	__u32 extcpu;	/* linux cpu number that detected the error */
+	__u32 socketid;	/* CPU socket ID */
+	__u32 apicid;	/* CPU initial apic ID */
+	__u64 mcgcap;	/* MCGCAP MSR: machine check capabilities of CPU */
 };
 
 /*
@@ -57,7 +75,7 @@ struct mce_log {
 	unsigned len;	    /* = MCE_LOG_LEN */
 	unsigned next;
 	unsigned flags;
-	unsigned pad0;
+	unsigned recordlen;	/* length of struct mce */
 	struct mce entry[MCE_LOG_LEN];
 };
 
@@ -82,19 +100,16 @@ struct mce_log {
 #define K8_MCE_THRESHOLD_BANK_5    (MCE_THRESHOLD_BASE + 5 * 9)
 #define K8_MCE_THRESHOLD_DRAM_ECC  (MCE_THRESHOLD_BANK_4 + 0)
 
-#endif /* __x86_64__ */
-
 #ifdef __KERNEL__
 
-#ifdef CONFIG_X86_32
 extern int mce_disabled;
-#else /* CONFIG_X86_32 */
 
 #include <asm/atomic.h>
+#include <linux/percpu.h>
 
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
-DECLARE_PER_CPU(struct sys_device, device_mce);
+DECLARE_PER_CPU(struct sys_device, mce_dev);
 extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
 /*
@@ -104,6 +119,8 @@ extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 #define MAX_NR_BANKS (MCE_EXTENDED_BANK - 1)
 
 #ifdef CONFIG_X86_MCE_INTEL
+extern int mce_cmci_disabled;
+extern int mce_ignore_ce;
 void mce_intel_feature_init(struct cpuinfo_x86 *c);
 void cmci_clear(void);
 void cmci_reenable(void);
@@ -123,13 +140,16 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c);
 static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
 #endif
 
-extern int mce_available(struct cpuinfo_x86 *c);
+int mce_available(struct cpuinfo_x86 *c);
+
+DECLARE_PER_CPU(unsigned, mce_exception_count);
+DECLARE_PER_CPU(unsigned, mce_poll_count);
 
 void mce_log_therm_throt_event(__u64 status);
 
 extern atomic_t mce_entry;
 
-extern void do_machine_check(struct pt_regs *, long);
+void do_machine_check(struct pt_regs *, long);
 
 typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
 DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
@@ -139,14 +159,16 @@ enum mcp_flags {
 	MCP_UC = (1 << 1),		/* log uncorrected errors */
 	MCP_DONTLOG = (1 << 2),		/* only clear, don't log */
 };
-extern void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
+void machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
-extern int mce_notify_user(void);
+int mce_notify_irq(void);
+void mce_notify_process(void);
 
-#endif /* !CONFIG_X86_32 */
+DECLARE_PER_CPU(struct mce, injectm);
+extern struct file_operations mce_chrdev_ops;
 
 #ifdef CONFIG_X86_MCE
-extern void mcheck_init(struct cpuinfo_x86 *c);
+void mcheck_init(struct cpuinfo_x86 *c);
 #else
 #define mcheck_init(c) do { } while (0)
 #endif
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 4d58d04fca8..1692fb5050e 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -207,7 +207,14 @@
 
 #define MSR_IA32_THERM_CONTROL		0x0000019a
 #define MSR_IA32_THERM_INTERRUPT	0x0000019b
+
+#define THERM_INT_LOW_ENABLE		(1 << 0)
+#define THERM_INT_HIGH_ENABLE		(1 << 1)
+
 #define MSR_IA32_THERM_STATUS		0x0000019c
+
+#define THERM_STATUS_PROCHOT		(1 << 0)
+
 #define MSR_IA32_MISC_ENABLE		0x000001a0
 
 /* MISC_ENABLE bits: architectural */
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 076d3881f3d..8c7c042ecad 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -899,7 +899,7 @@ void clear_local_APIC(void)
 	}
 
 	/* lets not touch this if we didn't frob it */
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	if (maxlvt >= 5) {
 		v = apic_read(APIC_LVTTHMR);
 		apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
@@ -2017,7 +2017,7 @@ static int lapic_suspend(struct sys_device *dev, pm_message_t state)
 	apic_pm_state.apic_lvterr = apic_read(APIC_LVTERR);
 	apic_pm_state.apic_tmict = apic_read(APIC_TMICT);
 	apic_pm_state.apic_tdcr = apic_read(APIC_TDCR);
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
+#ifdef CONFIG_X86_THERMAL_VECTOR
 	if (maxlvt >= 5)
 		apic_pm_state.apic_thmr = apic_read(APIC_LVTTHMR);
 #endif
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index a691302dc3f..b3025b43b63 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -66,7 +66,7 @@ static inline unsigned int get_nmi_count(int cpu)
 
 static inline int mce_in_progress(void)
 {
-#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+#if defined(CONFIG_X86_NEW_MCE)
 	return atomic_read(&mce_entry) > 0;
 #endif
 	return 0;
diff --git a/arch/x86/kernel/cpu/mcheck/Makefile b/arch/x86/kernel/cpu/mcheck/Makefile
index b2f89829bbe..45004faf67e 100644
--- a/arch/x86/kernel/cpu/mcheck/Makefile
+++ b/arch/x86/kernel/cpu/mcheck/Makefile
@@ -1,7 +1,11 @@
-obj-y				=  mce_$(BITS).o therm_throt.o
+obj-y				=  mce.o therm_throt.o
 
-obj-$(CONFIG_X86_32)		+= k7.o p4.o p5.o p6.o winchip.o
-obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel_64.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_P4THERMAL)	+= mce_intel.o
+obj-$(CONFIG_X86_MCE_INTEL)	+= mce_intel_64.o mce_intel.o
 obj-$(CONFIG_X86_MCE_AMD)	+= mce_amd_64.o
 obj-$(CONFIG_X86_MCE_NONFATAL)	+= non-fatal.o
 obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o
+obj-$(CONFIG_X86_MCE_INJECT)	+= mce-inject.o
diff --git a/arch/x86/kernel/cpu/mcheck/k7.c b/arch/x86/kernel/cpu/mcheck/k7.c
index dd3af6e7b39..89e51042415 100644
--- a/arch/x86/kernel/cpu/mcheck/k7.c
+++ b/arch/x86/kernel/cpu/mcheck/k7.c
@@ -2,11 +2,10 @@
  * Athlon specific Machine Check Exception Reporting
  * (C) Copyright 2002 Dave Jones <davej@redhat.com>
  */
-
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/init.h>
 #include <linux/smp.h>
 
 #include <asm/processor.h>
@@ -15,12 +14,12 @@
 
 #include "mce.h"
 
-/* Machine Check Handler For AMD Athlon/Duron */
+/* 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 recover = 1;
 	int i;
 
 	rdmsr(MSR_IA32_MCG_STATUS, mcgstl, mcgsth);
@@ -32,15 +31,19 @@ static void k7_machine_check(struct pt_regs *regs, long error_code)
 
 	for (i = 1; i < nr_mce_banks; i++) {
 		rdmsr(MSR_IA32_MC0_STATUS+i*4, low, high);
-		if (high&(1<<31)) {
+		if (high & (1<<31)) {
 			char misc[20];
 			char addr[24];
-			misc[0] = addr[0] = '\0';
+
+			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);
@@ -49,27 +52,31 @@ static void k7_machine_check(struct pt_regs *regs, long error_code)
 				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 */
+
+			/* Clear it: */
 			wrmsr(MSR_IA32_MC0_STATUS+i*4, 0UL, 0UL);
-			/* Serialize */
+			/* Serialize: */
 			wmb();
 			add_taint(TAINT_MACHINE_CHECK);
 		}
 	}
 
-	if (recover&2)
+	if (recover & 2)
 		panic("CPU context corrupt");
-	if (recover&1)
+	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 */
+/* AMD K7 machine check is Intel like: */
 void amd_mcheck_init(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
@@ -79,21 +86,26 @@ void amd_mcheck_init(struct cpuinfo_x86 *c)
 		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. */
+	/*
+	 * 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);
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
new file mode 100644
index 00000000000..a3a235a53f0
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -0,0 +1,127 @@
+/*
+ * Machine check injection support.
+ * Copyright 2008 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Authors:
+ * Andi Kleen
+ * Ying Huang
+ */
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/timer.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/fs.h>
+#include <linux/smp.h>
+#include <asm/mce.h>
+
+/* Update fake mce registers on current CPU. */
+static void inject_mce(struct mce *m)
+{
+	struct mce *i = &per_cpu(injectm, m->extcpu);
+
+	/* Make sure noone reads partially written injectm */
+	i->finished = 0;
+	mb();
+	m->finished = 0;
+	/* First set the fields after finished */
+	i->extcpu = m->extcpu;
+	mb();
+	/* Now write record in order, finished last (except above) */
+	memcpy(i, m, sizeof(struct mce));
+	/* Finally activate it */
+	mb();
+	i->finished = 1;
+}
+
+struct delayed_mce {
+	struct timer_list timer;
+	struct mce m;
+};
+
+/* Inject mce on current CPU */
+static void raise_mce(unsigned long data)
+{
+	struct delayed_mce *dm = (struct delayed_mce *)data;
+	struct mce *m = &dm->m;
+	int cpu = m->extcpu;
+
+	inject_mce(m);
+	if (m->status & MCI_STATUS_UC) {
+		struct pt_regs regs;
+		memset(&regs, 0, sizeof(struct pt_regs));
+		regs.ip = m->ip;
+		regs.cs = m->cs;
+		printk(KERN_INFO "Triggering MCE exception on CPU %d\n", cpu);
+		do_machine_check(&regs, 0);
+		printk(KERN_INFO "MCE exception done on CPU %d\n", cpu);
+	} else {
+		mce_banks_t b;
+		memset(&b, 0xff, sizeof(mce_banks_t));
+		printk(KERN_INFO "Starting machine check poll CPU %d\n", cpu);
+		machine_check_poll(0, &b);
+		mce_notify_irq();
+		printk(KERN_INFO "Finished machine check poll on CPU %d\n",
+		       cpu);
+	}
+	kfree(dm);
+}
+
+/* Error injection interface */
+static ssize_t mce_write(struct file *filp, const char __user *ubuf,
+			 size_t usize, loff_t *off)
+{
+	struct delayed_mce *dm;
+	struct mce m;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	/*
+	 * There are some cases where real MSR reads could slip
+	 * through.
+	 */
+	if (!boot_cpu_has(X86_FEATURE_MCE) || !boot_cpu_has(X86_FEATURE_MCA))
+		return -EIO;
+
+	if ((unsigned long)usize > sizeof(struct mce))
+		usize = sizeof(struct mce);
+	if (copy_from_user(&m, ubuf, usize))
+		return -EFAULT;
+
+	if (m.extcpu >= num_possible_cpus() || !cpu_online(m.extcpu))
+		return -EINVAL;
+
+	dm = kmalloc(sizeof(struct delayed_mce), GFP_KERNEL);
+	if (!dm)
+		return -ENOMEM;
+
+	/*
+	 * Need to give user space some time to set everything up,
+	 * so do it a jiffie or two later everywhere.
+	 * Should we use a hrtimer here for better synchronization?
+	 */
+	memcpy(&dm->m, &m, sizeof(struct mce));
+	setup_timer(&dm->timer, raise_mce, (unsigned long)dm);
+	dm->timer.expires = jiffies + 2;
+	add_timer_on(&dm->timer, m.extcpu);
+	return usize;
+}
+
+static int inject_init(void)
+{
+	printk(KERN_INFO "Machine check injector initialized\n");
+	mce_chrdev_ops.write = mce_write;
+	return 0;
+}
+
+module_init(inject_init);
+/*
+ * Cannot tolerate unloading currently because we cannot
+ * guarantee all openers of mce_chrdev will get a reference to us.
+ */
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/mcheck/mce-internal.h b/arch/x86/kernel/cpu/mcheck/mce-internal.h
new file mode 100644
index 00000000000..54dcb8ff12e
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-internal.h
@@ -0,0 +1,15 @@
+#include <asm/mce.h>
+
+enum severity_level {
+	MCE_NO_SEVERITY,
+	MCE_KEEP_SEVERITY,
+	MCE_SOME_SEVERITY,
+	MCE_AO_SEVERITY,
+	MCE_UC_SEVERITY,
+	MCE_AR_SEVERITY,
+	MCE_PANIC_SEVERITY,
+};
+
+int mce_severity(struct mce *a, int tolerant, char **msg);
+
+extern int mce_ser;
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
new file mode 100644
index 00000000000..ff0807f9705
--- /dev/null
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -0,0 +1,218 @@
+/*
+ * MCE grading rules.
+ * Copyright 2008, 2009 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ *
+ * Author: Andi Kleen
+ */
+#include <linux/kernel.h>
+#include <linux/seq_file.h>
+#include <linux/init.h>
+#include <linux/debugfs.h>
+#include <asm/mce.h>
+
+#include "mce-internal.h"
+
+/*
+ * Grade an mce by severity. In general the most severe ones are processed
+ * first. Since there are quite a lot of combinations test the bits in a
+ * table-driven way. The rules are simply processed in order, first
+ * match wins.
+ *
+ * Note this is only used for machine check exceptions, the corrected
+ * errors use much simpler rules. The exceptions still check for the corrected
+ * errors, but only to leave them alone for the CMCI handler (except for
+ * panic situations)
+ */
+
+enum context { IN_KERNEL = 1, IN_USER = 2 };
+enum ser { SER_REQUIRED = 1, NO_SER = 2 };
+
+static struct severity {
+	u64 mask;
+	u64 result;
+	unsigned char sev;
+	unsigned char mcgmask;
+