AuxXxilium/linux_dsm_epyc7002
1
0
Fork 0
mirror of https://github.com/AuxXxilium/linux_dsm_epyc7002.git synced 2024-12-17 15:56:45 +07:00
Code Issues Actions Packages Projects Releases Wiki Activity
8dd1e17a55
linux_dsm_epyc7002/arch/x86/include/asm/mce.h
Aravind Gopalakrishnan 8dd1e17a55 x86/mce/AMD: Fix logic to obtain block address 
In upcoming processors, the BLKPTR field is no longer used to indicate
the MSR number of the additional register. Insted, it simply indicates
the prescence of additional MSRs.

Fix the logic here to gather MSR address from MSR_AMD64_SMCA_MCx_MISC()
for newer processors and fall back to existing logic for older
processors.

[ Drop nextaddr_out label; style cleanups. ]
Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1457021458-2522-4-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-03-08 11:48:14 +01:00

358 lines
11 KiB
C
Raw Blame History

#ifndef _ASM_X86_MCE_H
#define _ASM_X86_MCE_H
#include <uapi/asm/mce.h>
/*
* Machine Check support for x86
*/
/* MCG_CAP register defines */
#define MCG_BANKCNT_MASK 0xff /* Number of Banks */
#define MCG_CTL_P (1ULL<<8) /* MCG_CTL 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_ELOG_P (1ULL<<26) /* Extended error log supported */
#define MCG_LMCE_P (1ULL<<27) /* Local machine check supported */
/* MCG_STATUS register defines */
#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 MCG_STATUS_LMCES (1ULL<<3) /* LMCE signaled */
/* MCG_EXT_CTL register defines */
#define MCG_EXT_CTL_LMCE_EN (1ULL<<0) /* Enable LMCE */
/* MCi_STATUS register defines */
#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 */
/* AMD-specific bits */
#define MCI_STATUS_DEFERRED (1ULL<<44) /* declare an uncorrected error */
#define MCI_STATUS_POISON (1ULL<<43) /* access poisonous data */
#define MCI_STATUS_TCC (1ULL<<55) /* Task context corrupt */
/*
* McaX field if set indicates a given bank supports MCA extensions:
* - Deferred error interrupt type is specifiable by bank.
* - MCx_MISC0[BlkPtr] field indicates presence of extended MISC registers,
* But should not be used to determine MSR numbers.
* - TCC bit is present in MCx_STATUS.
*/
#define MCI_CONFIG_MCAX 0x1
#define MCI_IPID_MCATYPE 0xFFFF0000
#define MCI_IPID_HWID 0xFFF
/*
* Note that the full MCACOD field of IA32_MCi_STATUS MSR is
* bits 15:0. But bit 12 is the 'F' bit, defined for corrected
* errors to indicate that errors are being filtered by hardware.
* We should mask out bit 12 when looking for specific signatures
* of uncorrected errors - so the F bit is deliberately skipped
* in this #define.
*/
#define MCACOD 0xefff /* MCA Error Code */
/* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
#define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
#define MCACOD_SCRUBMSK 0xeff0 /* Skip bit 12 ('F' bit) */
#define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
#define MCACOD_DATA 0x0134 /* Data Load */
#define MCACOD_INSTR 0x0150 /* Instruction Fetch */
/* MCi_MISC register defines */
#define MCI_MISC_ADDR_LSB(m) ((m) & 0x3f)
#define MCI_MISC_ADDR_MODE(m) (((m) >> 6) & 7)
#define MCI_MISC_ADDR_SEGOFF 0 /* segment offset */
#define MCI_MISC_ADDR_LINEAR 1 /* linear address */
#define MCI_MISC_ADDR_PHYS 2 /* physical address */
#define MCI_MISC_ADDR_MEM 3 /* memory address */
#define MCI_MISC_ADDR_GENERIC 7 /* generic */
/* CTL2 register defines */
#define MCI_CTL2_CMCI_EN (1ULL << 30)
#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL
#define MCJ_CTX_MASK 3
#define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK)
#define MCJ_CTX_RANDOM 0 /* inject context: random */
#define MCJ_CTX_PROCESS 0x1 /* inject context: process */
#define MCJ_CTX_IRQ 0x2 /* inject context: IRQ */
#define MCJ_NMI_BROADCAST 0x4 /* do NMI broadcasting */
#define MCJ_EXCEPTION 0x8 /* raise as exception */
#define MCJ_IRQ_BROADCAST 0x10 /* do IRQ broadcasting */
#define MCE_OVERFLOW 0 /* bit 0 in flags means overflow */
/* Software defined banks */
#define MCE_EXTENDED_BANK 128
#define MCE_THERMAL_BANK (MCE_EXTENDED_BANK + 0)
#define MCE_LOG_LEN 32
#define MCE_LOG_SIGNATURE "MACHINECHECK"
/* AMD Scalable MCA */
#define MSR_AMD64_SMCA_MC0_MISC0 0xc0002003
#define MSR_AMD64_SMCA_MC0_CONFIG 0xc0002004
#define MSR_AMD64_SMCA_MC0_IPID 0xc0002005
#define MSR_AMD64_SMCA_MC0_MISC1 0xc000200a
#define MSR_AMD64_SMCA_MCx_MISC(x) (MSR_AMD64_SMCA_MC0_MISC0 + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_CONFIG(x) (MSR_AMD64_SMCA_MC0_CONFIG + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_IPID(x) (MSR_AMD64_SMCA_MC0_IPID + 0x10*(x))
#define MSR_AMD64_SMCA_MCx_MISCy(x, y) ((MSR_AMD64_SMCA_MC0_MISC1 + y) + (0x10*(x)))
/*
* This structure contains all data related to the MCE log. Also
* carries a signature to make it easier to find from external
* debugging tools. Each entry is only valid when its finished flag
* is set.
*/
struct mce_log {
char signature[12]; /* "MACHINECHECK" */
unsigned len; /* = MCE_LOG_LEN */
unsigned next;
unsigned flags;
unsigned recordlen; /* length of struct mce */
struct mce entry[MCE_LOG_LEN];
};
struct mca_config {
bool dont_log_ce;
bool cmci_disabled;
bool lmce_disabled;
bool ignore_ce;
bool disabled;
bool ser;
bool bios_cmci_threshold;
u8 banks;
s8 bootlog;
int tolerant;
int monarch_timeout;
int panic_timeout;
u32 rip_msr;
};
struct mce_vendor_flags {
/*
* Indicates that overflow conditions are not fatal, when set.
*/
__u64 overflow_recov : 1,
/*
* (AMD) SUCCOR stands for S/W UnCorrectable error COntainment and
* Recovery. It indicates support for data poisoning in HW and deferred
* error interrupts.
*/
succor : 1,
/*
* (AMD) SMCA: This bit indicates support for Scalable MCA which expands
* the register space for each MCA bank and also increases number of
* banks. Also, to accommodate the new banks and registers, the MCA
* register space is moved to a new MSR range.
*/
smca : 1,
__reserved_0 : 61;
};
extern struct mce_vendor_flags mce_flags;
extern struct mca_config mca_cfg;
extern void mce_register_decode_chain(struct notifier_block *nb);
extern void mce_unregister_decode_chain(struct notifier_block *nb);
#include <linux/percpu.h>
#include <linux/atomic.h>
extern int mce_p5_enabled;
#ifdef CONFIG_X86_MCE
int mcheck_init(void);
void mcheck_cpu_init(struct cpuinfo_x86 *c);
void mcheck_cpu_clear(struct cpuinfo_x86 *c);
void mcheck_vendor_init_severity(void);
#else
static inline int mcheck_init(void) { return 0; }
static inline void mcheck_cpu_init(struct cpuinfo_x86 *c) {}
static inline void mcheck_cpu_clear(struct cpuinfo_x86 *c) {}
static inline void mcheck_vendor_init_severity(void) {}
#endif
#ifdef CONFIG_X86_ANCIENT_MCE
void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
void winchip_mcheck_init(struct cpuinfo_x86 *c);
static inline void enable_p5_mce(void) { mce_p5_enabled = 1; }
#else
static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {}
static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
static inline void enable_p5_mce(void) {}
#endif
void mce_setup(struct mce *m);
void mce_log(struct mce *m);
DECLARE_PER_CPU(struct device *, mce_device);
/*
* Maximum banks number.
* This is the limit of the current register layout on
* Intel CPUs.
*/
#define MAX_NR_BANKS 32
#ifdef CONFIG_X86_MCE_INTEL
void mce_intel_feature_init(struct cpuinfo_x86 *c);
void mce_intel_feature_clear(struct cpuinfo_x86 *c);
void cmci_clear(void);
void cmci_reenable(void);
void cmci_rediscover(void);
void cmci_recheck(void);
#else
static inline void mce_intel_feature_init(struct cpuinfo_x86 *c) { }
static inline void mce_intel_feature_clear(struct cpuinfo_x86 *c) { }
static inline void cmci_clear(void) {}
static inline void cmci_reenable(void) {}
static inline void cmci_rediscover(void) {}
static inline void cmci_recheck(void) {}
#endif
#ifdef CONFIG_X86_MCE_AMD
void mce_amd_feature_init(struct cpuinfo_x86 *c);
#else
static inline void mce_amd_feature_init(struct cpuinfo_x86 *c) { }
#endif
int mce_available(struct cpuinfo_x86 *c);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
enum mcp_flags {
MCP_TIMESTAMP = BIT(0), /* log time stamp */
MCP_UC = BIT(1), /* log uncorrected errors */
MCP_DONTLOG = BIT(2), /* only clear, don't log */
};
bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
int mce_notify_irq(void);
DECLARE_PER_CPU(struct mce, injectm);
extern void register_mce_write_callback(ssize_t (*)(struct file *filp,
const char __user *ubuf,
size_t usize, loff_t *off));
/* Disable CMCI/polling for MCA bank claimed by firmware */
extern void mce_disable_bank(int bank);
/*
* Exception handler
*/
/* Call the installed machine check handler for this CPU setup. */
extern void (*machine_check_vector)(struct pt_regs *, long error_code);
void do_machine_check(struct pt_regs *, long);
/*
* Threshold handler
*/
extern void (*mce_threshold_vector)(void);
extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
/* Deferred error interrupt handler */
extern void (*deferred_error_int_vector)(void);
/*
* Thermal handler
*/
void intel_init_thermal(struct cpuinfo_x86 *c);
void mce_log_therm_throt_event(__u64 status);
/* Interrupt Handler for core thermal thresholds */
extern int (*platform_thermal_notify)(__u64 msr_val);
/* Interrupt Handler for package thermal thresholds */
extern int (*platform_thermal_package_notify)(__u64 msr_val);
/* Callback support of rate control, return true, if
* callback has rate control */
extern bool (*platform_thermal_package_rate_control)(void);
#ifdef CONFIG_X86_THERMAL_VECTOR
extern void mcheck_intel_therm_init(void);
#else
static inline void mcheck_intel_therm_init(void) { }
#endif
/*
* Used by APEI to report memory error via /dev/mcelog
*/
struct cper_sec_mem_err;
extern void apei_mce_report_mem_error(int corrected,
struct cper_sec_mem_err *mem_err);
/*
* Enumerate new IP types and HWID values in AMD processors which support
* Scalable MCA.
*/
#ifdef CONFIG_X86_MCE_AMD
enum amd_ip_types {
SMCA_F17H_CORE = 0, /* Core errors */
SMCA_DF, /* Data Fabric */
SMCA_UMC, /* Unified Memory Controller */
SMCA_PB, /* Parameter Block */
SMCA_PSP, /* Platform Security Processor */
SMCA_SMU, /* System Management Unit */
N_AMD_IP_TYPES
};
struct amd_hwid {
const char *name;
unsigned int hwid;
};
extern struct amd_hwid amd_hwids[N_AMD_IP_TYPES];
enum amd_core_mca_blocks {
SMCA_LS = 0, /* Load Store */
SMCA_IF, /* Instruction Fetch */
SMCA_L2_CACHE, /* L2 cache */
SMCA_DE, /* Decoder unit */
RES, /* Reserved */
SMCA_EX, /* Execution unit */
SMCA_FP, /* Floating Point */
SMCA_L3_CACHE, /* L3 cache */
N_CORE_MCA_BLOCKS
};
extern const char * const amd_core_mcablock_names[N_CORE_MCA_BLOCKS];
enum amd_df_mca_blocks {
SMCA_CS = 0, /* Coherent Slave */
SMCA_PIE, /* Power management, Interrupts, etc */
N_DF_BLOCKS
};
extern const char * const amd_df_mcablock_names[N_DF_BLOCKS];
#endif
#endif /* _ASM_X86_MCE_H */
Reference in New Issue View Git Blame Copy Permalink