diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-13 13:14:51 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-06-13 13:14:51 -0700 |
commit | a2ee2981ae2a7046b10980feae9f4ab813877106 (patch) | |
tree | ed75db7830b9ef1342659d36d2775954ce96b79f /arch/x86/include | |
parent | 7603ef03a22a33d36d3c75d7c1aca1f957671ad3 (diff) | |
parent | 0d5959723e1db3fd7323c198a50c16cecf96c7a9 (diff) |
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
...
Diffstat (limited to 'arch/x86/include')
-rw-r--r-- | arch/x86/include/asm/entry_arch.h | 11 | ||||
-rw-r--r-- | arch/x86/include/asm/hardirq.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/hw_irq.h | 2 | ||||
-rw-r--r-- | arch/x86/include/asm/irq_vectors.h | 17 | ||||
-rw-r--r-- | arch/x86/include/asm/mce.h | 88 | ||||
-rw-r--r-- | arch/x86/include/asm/msr-index.h | 7 |
6 files changed, 85 insertions, 42 deletions
diff --git a/arch/x86/include/asm/entry_arch.h b/arch/x86/include/asm/entry_arch.h index d750a10ccad6..ff8cbfa07851 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 9ebc5c255032..82e3e8f01043 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 6df45f639666..ba180d93b08c 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 e997be98c9b9..5b21f0ec3df2 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 4f8c199584e7..540a466e50f5 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 4d58d04fca83..1692fb5050e3 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 */ |