diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mce')
| -rw-r--r-- | arch/x86/kernel/cpu/mce/Makefile | 14 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/amd.c | 1374 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/apei.c | 216 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 2871 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/dev-mcelog.c | 373 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/genpool.c | 147 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/inject.c | 800 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/intel.c | 538 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/internal.h | 281 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/p5.c | 66 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/severity.c | 479 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/threshold.c | 31 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/winchip.c | 41 |
13 files changed, 7231 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/mce/Makefile b/arch/x86/kernel/cpu/mce/Makefile new file mode 100644 index 0000000000..015856abdb --- /dev/null +++ b/arch/x86/kernel/cpu/mce/Makefile @@ -0,0 +1,14 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-y = core.o severity.o genpool.o + +obj-$(CONFIG_X86_ANCIENT_MCE) += winchip.o p5.o +obj-$(CONFIG_X86_MCE_INTEL) += intel.o +obj-$(CONFIG_X86_MCE_AMD) += amd.o +obj-$(CONFIG_X86_MCE_THRESHOLD) += threshold.o + +mce-inject-y := inject.o +obj-$(CONFIG_X86_MCE_INJECT) += mce-inject.o + +obj-$(CONFIG_ACPI_APEI) += apei.o + +obj-$(CONFIG_X86_MCELOG_LEGACY) += dev-mcelog.o diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c new file mode 100644 index 0000000000..c267f43de3 --- /dev/null +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -0,0 +1,1374 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * (c) 2005-2016 Advanced Micro Devices, Inc. + * + * Written by Jacob Shin - AMD, Inc. + * Maintained by: Borislav Petkov <bp@alien8.de> + * + * All MC4_MISCi registers are shared between cores on a node. + */ +#include <linux/interrupt.h> +#include <linux/notifier.h> +#include <linux/kobject.h> +#include <linux/percpu.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/sysfs.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/smp.h> +#include <linux/string.h> + +#include <asm/amd_nb.h> +#include <asm/traps.h> +#include <asm/apic.h> +#include <asm/mce.h> +#include <asm/msr.h> +#include <asm/trace/irq_vectors.h> + +#include "internal.h" + +#define NR_BLOCKS 5 +#define THRESHOLD_MAX 0xFFF +#define INT_TYPE_APIC 0x00020000 +#define MASK_VALID_HI 0x80000000 +#define MASK_CNTP_HI 0x40000000 +#define MASK_LOCKED_HI 0x20000000 +#define MASK_LVTOFF_HI 0x00F00000 +#define MASK_COUNT_EN_HI 0x00080000 +#define MASK_INT_TYPE_HI 0x00060000 +#define MASK_OVERFLOW_HI 0x00010000 +#define MASK_ERR_COUNT_HI 0x00000FFF +#define MASK_BLKPTR_LO 0xFF000000 +#define MCG_XBLK_ADDR 0xC0000400 + +/* Deferred error settings */ +#define MSR_CU_DEF_ERR 0xC0000410 +#define MASK_DEF_LVTOFF 0x000000F0 +#define MASK_DEF_INT_TYPE 0x00000006 +#define DEF_LVT_OFF 0x2 +#define DEF_INT_TYPE_APIC 0x2 + +/* Scalable MCA: */ + +/* Threshold LVT offset is at MSR0xC0000410[15:12] */ +#define SMCA_THR_LVT_OFF 0xF000 + +static bool thresholding_irq_en; + +static const char * const th_names[] = { + "load_store", + "insn_fetch", + "combined_unit", + "decode_unit", + "northbridge", + "execution_unit", +}; + +static const char * const smca_umc_block_names[] = { + "dram_ecc", + "misc_umc" +}; + +#define HWID_MCATYPE(hwid, mcatype) (((hwid) << 16) | (mcatype)) + +struct smca_hwid { + unsigned int bank_type; /* Use with smca_bank_types for easy indexing. */ + u32 hwid_mcatype; /* (hwid,mcatype) tuple */ +}; + +struct smca_bank { + const struct smca_hwid *hwid; + u32 id; /* Value of MCA_IPID[InstanceId]. */ + u8 sysfs_id; /* Value used for sysfs name. */ +}; + +static DEFINE_PER_CPU_READ_MOSTLY(struct smca_bank[MAX_NR_BANKS], smca_banks); +static DEFINE_PER_CPU_READ_MOSTLY(u8[N_SMCA_BANK_TYPES], smca_bank_counts); + +struct smca_bank_name { + const char *name; /* Short name for sysfs */ + const char *long_name; /* Long name for pretty-printing */ +}; + +static struct smca_bank_name smca_names[] = { + [SMCA_LS ... SMCA_LS_V2] = { "load_store", "Load Store Unit" }, + [SMCA_IF] = { "insn_fetch", "Instruction Fetch Unit" }, + [SMCA_L2_CACHE] = { "l2_cache", "L2 Cache" }, + [SMCA_DE] = { "decode_unit", "Decode Unit" }, + [SMCA_RESERVED] = { "reserved", "Reserved" }, + [SMCA_EX] = { "execution_unit", "Execution Unit" }, + [SMCA_FP] = { "floating_point", "Floating Point Unit" }, + [SMCA_L3_CACHE] = { "l3_cache", "L3 Cache" }, + [SMCA_CS ... SMCA_CS_V2] = { "coherent_slave", "Coherent Slave" }, + [SMCA_PIE] = { "pie", "Power, Interrupts, etc." }, + + /* UMC v2 is separate because both of them can exist in a single system. */ + [SMCA_UMC] = { "umc", "Unified Memory Controller" }, + [SMCA_UMC_V2] = { "umc_v2", "Unified Memory Controller v2" }, + [SMCA_PB] = { "param_block", "Parameter Block" }, + [SMCA_PSP ... SMCA_PSP_V2] = { "psp", "Platform Security Processor" }, + [SMCA_SMU ... SMCA_SMU_V2] = { "smu", "System Management Unit" }, + [SMCA_MP5] = { "mp5", "Microprocessor 5 Unit" }, + [SMCA_MPDMA] = { "mpdma", "MPDMA Unit" }, + [SMCA_NBIO] = { "nbio", "Northbridge IO Unit" }, + [SMCA_PCIE ... SMCA_PCIE_V2] = { "pcie", "PCI Express Unit" }, + [SMCA_XGMI_PCS] = { "xgmi_pcs", "Ext Global Memory Interconnect PCS Unit" }, + [SMCA_NBIF] = { "nbif", "NBIF Unit" }, + [SMCA_SHUB] = { "shub", "System Hub Unit" }, + [SMCA_SATA] = { "sata", "SATA Unit" }, + [SMCA_USB] = { "usb", "USB Unit" }, + [SMCA_GMI_PCS] = { "gmi_pcs", "Global Memory Interconnect PCS Unit" }, + [SMCA_XGMI_PHY] = { "xgmi_phy", "Ext Global Memory Interconnect PHY Unit" }, + [SMCA_WAFL_PHY] = { "wafl_phy", "WAFL PHY Unit" }, + [SMCA_GMI_PHY] = { "gmi_phy", "Global Memory Interconnect PHY Unit" }, +}; + +static const char *smca_get_name(enum smca_bank_types t) +{ + if (t >= N_SMCA_BANK_TYPES) + return NULL; + + return smca_names[t].name; +} + +const char *smca_get_long_name(enum smca_bank_types t) +{ + if (t >= N_SMCA_BANK_TYPES) + return NULL; + + return smca_names[t].long_name; +} +EXPORT_SYMBOL_GPL(smca_get_long_name); + +enum smca_bank_types smca_get_bank_type(unsigned int cpu, unsigned int bank) +{ + struct smca_bank *b; + + if (bank >= MAX_NR_BANKS) + return N_SMCA_BANK_TYPES; + + b = &per_cpu(smca_banks, cpu)[bank]; + if (!b->hwid) + return N_SMCA_BANK_TYPES; + + return b->hwid->bank_type; +} +EXPORT_SYMBOL_GPL(smca_get_bank_type); + +static const struct smca_hwid smca_hwid_mcatypes[] = { + /* { bank_type, hwid_mcatype } */ + + /* Reserved type */ + { SMCA_RESERVED, HWID_MCATYPE(0x00, 0x0) }, + + /* ZN Core (HWID=0xB0) MCA types */ + { SMCA_LS, HWID_MCATYPE(0xB0, 0x0) }, + { SMCA_LS_V2, HWID_MCATYPE(0xB0, 0x10) }, + { SMCA_IF, HWID_MCATYPE(0xB0, 0x1) }, + { SMCA_L2_CACHE, HWID_MCATYPE(0xB0, 0x2) }, + { SMCA_DE, HWID_MCATYPE(0xB0, 0x3) }, + /* HWID 0xB0 MCATYPE 0x4 is Reserved */ + { SMCA_EX, HWID_MCATYPE(0xB0, 0x5) }, + { SMCA_FP, HWID_MCATYPE(0xB0, 0x6) }, + { SMCA_L3_CACHE, HWID_MCATYPE(0xB0, 0x7) }, + + /* Data Fabric MCA types */ + { SMCA_CS, HWID_MCATYPE(0x2E, 0x0) }, + { SMCA_PIE, HWID_MCATYPE(0x2E, 0x1) }, + { SMCA_CS_V2, HWID_MCATYPE(0x2E, 0x2) }, + + /* Unified Memory Controller MCA type */ + { SMCA_UMC, HWID_MCATYPE(0x96, 0x0) }, + { SMCA_UMC_V2, HWID_MCATYPE(0x96, 0x1) }, + + /* Parameter Block MCA type */ + { SMCA_PB, HWID_MCATYPE(0x05, 0x0) }, + + /* Platform Security Processor MCA type */ + { SMCA_PSP, HWID_MCATYPE(0xFF, 0x0) }, + { SMCA_PSP_V2, HWID_MCATYPE(0xFF, 0x1) }, + + /* System Management Unit MCA type */ + { SMCA_SMU, HWID_MCATYPE(0x01, 0x0) }, + { SMCA_SMU_V2, HWID_MCATYPE(0x01, 0x1) }, + + /* Microprocessor 5 Unit MCA type */ + { SMCA_MP5, HWID_MCATYPE(0x01, 0x2) }, + + /* MPDMA MCA type */ + { SMCA_MPDMA, HWID_MCATYPE(0x01, 0x3) }, + + /* Northbridge IO Unit MCA type */ + { SMCA_NBIO, HWID_MCATYPE(0x18, 0x0) }, + + /* PCI Express Unit MCA type */ + { SMCA_PCIE, HWID_MCATYPE(0x46, 0x0) }, + { SMCA_PCIE_V2, HWID_MCATYPE(0x46, 0x1) }, + + { SMCA_XGMI_PCS, HWID_MCATYPE(0x50, 0x0) }, + { SMCA_NBIF, HWID_MCATYPE(0x6C, 0x0) }, + { SMCA_SHUB, HWID_MCATYPE(0x80, 0x0) }, + { SMCA_SATA, HWID_MCATYPE(0xA8, 0x0) }, + { SMCA_USB, HWID_MCATYPE(0xAA, 0x0) }, + { SMCA_GMI_PCS, HWID_MCATYPE(0x241, 0x0) }, + { SMCA_XGMI_PHY, HWID_MCATYPE(0x259, 0x0) }, + { SMCA_WAFL_PHY, HWID_MCATYPE(0x267, 0x0) }, + { SMCA_GMI_PHY, HWID_MCATYPE(0x269, 0x0) }, +}; + +/* + * In SMCA enabled processors, we can have multiple banks for a given IP type. + * So to define a unique name for each bank, we use a temp c-string to append + * the MCA_IPID[InstanceId] to type's name in get_name(). + * + * InstanceId is 32 bits which is 8 characters. Make sure MAX_MCATYPE_NAME_LEN + * is greater than 8 plus 1 (for underscore) plus length of longest type name. + */ +#define MAX_MCATYPE_NAME_LEN 30 +static char buf_mcatype[MAX_MCATYPE_NAME_LEN]; + +static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); + +/* + * A list of the banks enabled on each logical CPU. Controls which respective + * descriptors to initialize later in mce_threshold_create_device(). + */ +static DEFINE_PER_CPU(u64, bank_map); + +/* Map of banks that have more than MCA_MISC0 available. */ +static DEFINE_PER_CPU(u64, smca_misc_banks_map); + +static void amd_threshold_interrupt(void); +static void amd_deferred_error_interrupt(void); + +static void default_deferred_error_interrupt(void) +{ + pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR); +} +void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt; + +static void smca_set_misc_banks_map(unsigned int bank, unsigned int cpu) +{ + u32 low, high; + + /* + * For SMCA enabled processors, BLKPTR field of the first MISC register + * (MCx_MISC0) indicates presence of additional MISC regs set (MISC1-4). + */ + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_CONFIG(bank), &low, &high)) + return; + + if (!(low & MCI_CONFIG_MCAX)) + return; + + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_MISC(bank), &low, &high)) + return; + + if (low & MASK_BLKPTR_LO) + per_cpu(smca_misc_banks_map, cpu) |= BIT_ULL(bank); + +} + +static void smca_configure(unsigned int bank, unsigned int cpu) +{ + u8 *bank_counts = this_cpu_ptr(smca_bank_counts); + const struct smca_hwid *s_hwid; + unsigned int i, hwid_mcatype; + u32 high, low; + u32 smca_config = MSR_AMD64_SMCA_MCx_CONFIG(bank); + + /* Set appropriate bits in MCA_CONFIG */ + if (!rdmsr_safe(smca_config, &low, &high)) { + /* + * OS is required to set the MCAX bit to acknowledge that it is + * now using the new MSR ranges and new registers under each + * bank. It also means that the OS will configure deferred + * errors in the new MCx_CONFIG register. If the bit is not set, + * uncorrectable errors will cause a system panic. + * + * MCA_CONFIG[MCAX] is bit 32 (0 in the high portion of the MSR.) + */ + high |= BIT(0); + + /* + * SMCA sets the Deferred Error Interrupt type per bank. + * + * MCA_CONFIG[DeferredIntTypeSupported] is bit 5, and tells us + * if the DeferredIntType bit field is available. + * + * MCA_CONFIG[DeferredIntType] is bits [38:37] ([6:5] in the + * high portion of the MSR). OS should set this to 0x1 to enable + * APIC based interrupt. First, check that no interrupt has been + * set. + */ + if ((low & BIT(5)) && !((high >> 5) & 0x3)) + high |= BIT(5); + + this_cpu_ptr(mce_banks_array)[bank].lsb_in_status = !!(low & BIT(8)); + + wrmsr(smca_config, low, high); + } + + smca_set_misc_banks_map(bank, cpu); + + if (rdmsr_safe(MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) { + pr_warn("Failed to read MCA_IPID for bank %d\n", bank); + return; + } + + hwid_mcatype = HWID_MCATYPE(high & MCI_IPID_HWID, + (high & MCI_IPID_MCATYPE) >> 16); + + for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) { + s_hwid = &smca_hwid_mcatypes[i]; + + if (hwid_mcatype == s_hwid->hwid_mcatype) { + this_cpu_ptr(smca_banks)[bank].hwid = s_hwid; + this_cpu_ptr(smca_banks)[bank].id = low; + this_cpu_ptr(smca_banks)[bank].sysfs_id = bank_counts[s_hwid->bank_type]++; + break; + } + } +} + +struct thresh_restart { + struct threshold_block *b; + int reset; + int set_lvt_off; + int lvt_off; + u16 old_limit; +}; + +static inline bool is_shared_bank(int bank) +{ + /* + * Scalable MCA provides for only one core to have access to the MSRs of + * a shared bank. + */ + if (mce_flags.smca) + return false; + + /* Bank 4 is for northbridge reporting and is thus shared */ + return (bank == 4); +} + +static const char *bank4_names(const struct threshold_block *b) +{ + switch (b->address) { + /* MSR4_MISC0 */ + case 0x00000413: + return "dram"; + + case 0xc0000408: + return "ht_links"; + + case 0xc0000409: + return "l3_cache"; + + default: + WARN(1, "Funny MSR: 0x%08x\n", b->address); + return ""; + } +}; + + +static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits) +{ + /* + * bank 4 supports APIC LVT interrupts implicitly since forever. + */ + if (bank == 4) + return true; + + /* + * IntP: interrupt present; if this bit is set, the thresholding + * bank can generate APIC LVT interrupts + */ + return msr_high_bits & BIT(28); +} + +static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) +{ + int msr = (hi & MASK_LVTOFF_HI) >> 20; + + if (apic < 0) { + pr_err(FW_BUG "cpu %d, failed to setup threshold interrupt " + "for bank %d, block %d (MSR%08X=0x%x%08x)\n", b->cpu, + b->bank, b->block, b->address, hi, lo); + return 0; + } + + if (apic != msr) { + /* + * On SMCA CPUs, LVT offset is programmed at a different MSR, and + * the BIOS provides the value. The original field where LVT offset + * was set is reserved. Return early here: + */ + if (mce_flags.smca) + return 0; + + pr_err(FW_BUG "cpu %d, invalid threshold interrupt offset %d " + "for bank %d, block %d (MSR%08X=0x%x%08x)\n", + b->cpu, apic, b->bank, b->block, b->address, hi, lo); + return 0; + } + + return 1; +}; + +/* Reprogram MCx_MISC MSR behind this threshold bank. */ +static void threshold_restart_bank(void *_tr) +{ + struct thresh_restart *tr = _tr; + u32 hi, lo; + + /* sysfs write might race against an offline operation */ + if (!this_cpu_read(threshold_banks) && !tr->set_lvt_off) + return; + + rdmsr(tr->b->address, lo, hi); + + if (tr->b->threshold_limit < (hi & THRESHOLD_MAX)) + tr->reset = 1; /* limit cannot be lower than err count */ + + if (tr->reset) { /* reset err count and overflow bit */ + hi = + (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) | + (THRESHOLD_MAX - tr->b->threshold_limit); + } else if (tr->old_limit) { /* change limit w/o reset */ + int new_count = (hi & THRESHOLD_MAX) + + (tr->old_limit - tr->b->threshold_limit); + + hi = (hi & ~MASK_ERR_COUNT_HI) | + (new_count & THRESHOLD_MAX); + } + + /* clear IntType */ + hi &= ~MASK_INT_TYPE_HI; + + if (!tr->b->interrupt_capable) + goto done; + + if (tr->set_lvt_off) { + if (lvt_off_valid(tr->b, tr->lvt_off, lo, hi)) { + /* set new lvt offset */ + hi &= ~MASK_LVTOFF_HI; + hi |= tr->lvt_off << 20; + } + } + + if (tr->b->interrupt_enable) + hi |= INT_TYPE_APIC; + + done: + + hi |= MASK_COUNT_EN_HI; + wrmsr(tr->b->address, lo, hi); +} + +static void mce_threshold_block_init(struct threshold_block *b, int offset) +{ + struct thresh_restart tr = { + .b = b, + .set_lvt_off = 1, + .lvt_off = offset, + }; + + b->threshold_limit = THRESHOLD_MAX; + threshold_restart_bank(&tr); +}; + +static int setup_APIC_mce_threshold(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, THRESHOLD_APIC_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; +} + +static int setup_APIC_deferred_error(int reserved, int new) +{ + if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR, + APIC_EILVT_MSG_FIX, 0)) + return new; + + return reserved; +} + +static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c) +{ + u32 low = 0, high = 0; + int def_offset = -1, def_new; + + if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high)) + return; + + def_new = (low & MASK_DEF_LVTOFF) >> 4; + if (!(low & MASK_DEF_LVTOFF)) { + pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n"); + def_new = DEF_LVT_OFF; + low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4); + } + + def_offset = setup_APIC_deferred_error(def_offset, def_new); + if ((def_offset == def_new) && + (deferred_error_int_vector != amd_deferred_error_interrupt)) + deferred_error_int_vector = amd_deferred_error_interrupt; + + if (!mce_flags.smca) + low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC; + + wrmsr(MSR_CU_DEF_ERR, low, high); +} + +static u32 smca_get_block_address(unsigned int bank, unsigned int block, + unsigned int cpu) +{ + if (!block) + return MSR_AMD64_SMCA_MCx_MISC(bank); + + if (!(per_cpu(smca_misc_banks_map, cpu) & BIT_ULL(bank))) + return 0; + + return MSR_AMD64_SMCA_MCx_MISCy(bank, block - 1); +} + +static u32 get_block_address(u32 current_addr, u32 low, u32 high, + unsigned int bank, unsigned int block, + unsigned int cpu) +{ + u32 addr = 0, offset = 0; + + if ((bank >= per_cpu(mce_num_banks, cpu)) || (block >= NR_BLOCKS)) + return addr; + + if (mce_flags.smca) + return smca_get_block_address(bank, block, cpu); + + /* Fall back to method we used for older processors: */ + switch (block) { + case 0: + addr = mca_msr_reg(bank, MCA_MISC); + break; + case 1: + offset = ((low & MASK_BLKPTR_LO) >> 21); + if (offset) + addr = MCG_XBLK_ADDR + offset; + break; + default: + addr = ++current_addr; + } + return addr; +} + +static int +prepare_threshold_block(unsigned int bank, unsigned int block, u32 addr, + int offset, u32 misc_high) +{ + unsigned int cpu = smp_processor_id(); + u32 smca_low, smca_high; + struct threshold_block b; + int new; + + if (!block) + per_cpu(bank_map, cpu) |= BIT_ULL(bank); + + memset(&b, 0, sizeof(b)); + b.cpu = cpu; + b.bank = bank; + b.block = block; + b.address = addr; + b.interrupt_capable = lvt_interrupt_supported(bank, misc_high); + + if (!b.interrupt_capable) + goto done; + + b.interrupt_enable = 1; + + if (!mce_flags.smca) { + new = (misc_high & MASK_LVTOFF_HI) >> 20; + goto set_offset; + } + + /* Gather LVT offset for thresholding: */ + if (rdmsr_safe(MSR_CU_DEF_ERR, &smca_low, &smca_high)) + goto out; + + new = (smca_low & SMCA_THR_LVT_OFF) >> 12; + +set_offset: + offset = setup_APIC_mce_threshold(offset, new); + if (offset == new) + thresholding_irq_en = true; + +done: + mce_threshold_block_init(&b, offset); + +out: + return offset; +} + +bool amd_filter_mce(struct mce *m) +{ + enum smca_bank_types bank_type = smca_get_bank_type(m->extcpu, m->bank); + struct cpuinfo_x86 *c = &boot_cpu_data; + + /* See Family 17h Models 10h-2Fh Erratum #1114. */ + if (c->x86 == 0x17 && + c->x86_model >= 0x10 && c->x86_model <= 0x2F && + bank_type == SMCA_IF && XEC(m->status, 0x3f) == 10) + return true; + + /* NB GART TLB error reporting is disabled by default. */ + if (c->x86 < 0x17) { + if (m->bank == 4 && XEC(m->status, 0x1f) == 0x5) + return true; + } + + return false; +} + +/* + * Turn off thresholding banks for the following conditions: + * - MC4_MISC thresholding is not supported on Family 0x15. + * - Prevent possible spurious interrupts from the IF bank on Family 0x17 + * Models 0x10-0x2F due to Erratum #1114. + */ +static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank) +{ + int i, num_msrs; + u64 hwcr; + bool need_toggle; + u32 msrs[NR_BLOCKS]; + + if (c->x86 == 0x15 && bank == 4) { + msrs[0] = 0x00000413; /* MC4_MISC0 */ + msrs[1] = 0xc0000408; /* MC4_MISC1 */ + num_msrs = 2; + } else if (c->x86 == 0x17 && + (c->x86_model >= 0x10 && c->x86_model <= 0x2F)) { + + if (smca_get_bank_type(smp_processor_id(), bank) != SMCA_IF) + return; + + msrs[0] = MSR_AMD64_SMCA_MCx_MISC(bank); + num_msrs = 1; + } else { + return; + } + + rdmsrl(MSR_K7_HWCR, hwcr); + + /* McStatusWrEn has to be set */ + need_toggle = !(hwcr & BIT(18)); + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr | BIT(18)); + + /* Clear CntP bit safely */ + for (i = 0; i < num_msrs; i++) + msr_clear_bit(msrs[i], 62); + + /* restore old settings */ + if (need_toggle) + wrmsrl(MSR_K7_HWCR, hwcr); +} + +/* cpu init entry point, called from mce.c with preempt off */ +void mce_amd_feature_init(struct cpuinfo_x86 *c) +{ + unsigned int bank, block, cpu = smp_processor_id(); + u32 low = 0, high = 0, address = 0; + int offset = -1; + + + for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) { + if (mce_flags.smca) + smca_configure(bank, cpu); + + disable_err_thresholding(c, bank); + + for (block = 0; block < NR_BLOCKS; ++block) { + address = get_block_address(address, low, high, bank, block, cpu); + if (!address) + break; + + if (rdmsr_safe(address, &low, &high)) + break; + + if (!(high & MASK_VALID_HI)) + continue; + + if (!(high & MASK_CNTP_HI) || + (high & MASK_LOCKED_HI)) + continue; + + offset = prepare_threshold_block(bank, block, address, offset, high); + } + } + + if (mce_flags.succor) + deferred_error_interrupt_enable(c); +} + +bool amd_mce_is_memory_error(struct mce *m) +{ + enum smca_bank_types bank_type; + /* ErrCodeExt[20:16] */ + u8 xec = (m->status >> 16) & 0x1f; + + bank_type = smca_get_bank_type(m->extcpu, m->bank); + if (mce_flags.smca) + return (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2) && xec == 0x0; + + return m->bank == 4 && xec == 0x8; +} + +static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) +{ + struct mce m; + + mce_setup(&m); + + m.status = status; + m.misc = misc; + m.bank = bank; + m.tsc = rdtsc(); + + if (m.status & MCI_STATUS_ADDRV) { + m.addr = addr; + + smca_extract_err_addr(&m); + } + + if (mce_flags.smca) { + rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid); + + if (m.status & MCI_STATUS_SYNDV) + rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd); + } + + mce_log(&m); +} + +DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error) +{ + trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR); + inc_irq_stat(irq_deferred_error_count); + deferred_error_int_vector(); + trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR); + apic_eoi(); +} + +/* + * Returns true if the logged error is deferred. False, otherwise. + */ +static inline bool +_log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc) +{ + u64 status, addr = 0; + + rdmsrl(msr_stat, status); + if (!(status & MCI_STATUS_VAL)) + return false; + + if (status & MCI_STATUS_ADDRV) + rdmsrl(msr_addr, addr); + + __log_error(bank, status, addr, misc); + + wrmsrl(msr_stat, 0); + + return status & MCI_STATUS_DEFERRED; +} + +static bool _log_error_deferred(unsigned int bank, u32 misc) +{ + if (!_log_error_bank(bank, mca_msr_reg(bank, MCA_STATUS), + mca_msr_reg(bank, MCA_ADDR), misc)) + return false; + + /* + * Non-SMCA systems don't have MCA_DESTAT/MCA_DEADDR registers. + * Return true here to avoid accessing these registers. + */ + if (!mce_flags.smca) + return true; + + /* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */ + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0); + return true; +} + +/* + * We have three scenarios for checking for Deferred errors: + * + * 1) Non-SMCA systems check MCA_STATUS and log error if found. + * 2) SMCA systems check MCA_STATUS. If error is found then log it and also + * clear MCA_DESTAT. + * 3) SMCA systems check MCA_DESTAT, if error was not found in MCA_STATUS, and + * log it. + */ +static void log_error_deferred(unsigned int bank) +{ + if (_log_error_deferred(bank, 0)) + return; + + /* + * Only deferred errors are logged in MCA_DE{STAT,ADDR} so just check + * for a valid error. + */ + _log_error_bank(bank, MSR_AMD64_SMCA_MCx_DESTAT(bank), + MSR_AMD64_SMCA_MCx_DEADDR(bank), 0); +} + +/* APIC interrupt handler for deferred errors */ +static void amd_deferred_error_interrupt(void) +{ + unsigned int bank; + + for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) + log_error_deferred(bank); +} + +static void log_error_thresholding(unsigned int bank, u64 misc) +{ + _log_error_deferred(bank, misc); +} + +static void log_and_reset_block(struct threshold_block *block) +{ + struct thresh_restart tr; + u32 low = 0, high = 0; + + if (!block) + return; + + if (rdmsr_safe(block->address, &low, &high)) + return; + + if (!(high & MASK_OVERFLOW_HI)) + return; + + /* Log the MCE which caused the threshold event. */ + log_error_thresholding(block->bank, ((u64)high << 32) | low); + + /* Reset threshold block after logging error. */ + memset(&tr, 0, sizeof(tr)); + tr.b = block; + threshold_restart_bank(&tr); +} + +/* + * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt + * goes off when error_count reaches threshold_limit. + */ +static void amd_threshold_interrupt(void) +{ + struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL; + struct threshold_bank **bp = this_cpu_read(threshold_banks); + unsigned int bank, cpu = smp_processor_id(); + + /* + * Validate that the threshold bank has been initialized already. The + * handler is installed at boot time, but on a hotplug event the + * interrupt might fire before the data has been initialized. + */ + if (!bp) + return; + + for (bank = 0; bank < this_cpu_read(mce_num_banks); ++bank) { + if (!(per_cpu(bank_map, cpu) & BIT_ULL(bank))) + continue; + + first_block = bp[bank]->blocks; + if (!first_block) + continue; + + /* + * The first block is also the head of the list. Check it first + * before iterating over the rest. + */ + log_and_reset_block(first_block); + list_for_each_entry_safe(block, tmp, &first_block->miscj, miscj) + log_and_reset_block(block); + } +} + +/* + * Sysfs Interface + */ + +struct threshold_attr { + struct attribute attr; + ssize_t (*show) (struct threshold_block *, char *); + ssize_t (*store) (struct threshold_block *, const char *, size_t count); +}; + +#define SHOW_FIELDS(name) \ +static ssize_t show_ ## name(struct threshold_block *b, char *buf) \ +{ \ + return sprintf(buf, "%lu\n", (unsigned long) b->name); \ +} +SHOW_FIELDS(interrupt_enable) +SHOW_FIELDS(threshold_limit) + +static ssize_t +store_interrupt_enable(struct threshold_block *b, const char *buf, size_t size) +{ + struct thresh_restart tr; + unsigned long new; + + if (!b->interrupt_capable) + return -EINVAL; + + if (kstrtoul(buf, 0, &new) < 0) + return -EINVAL; + + b->interrupt_enable = !!new; + + memset(&tr, 0, sizeof(tr)); + tr.b = b; + + if (smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1)) + return -ENODEV; + + return size; +} + +static ssize_t +store_threshold_limit(struct threshold_block *b, const char *buf, size_t size) +{ + struct thresh_restart tr; + unsigned long new; + + if (kstrtoul(buf, 0, &new) < 0) + return -EINVAL; + + if (new > THRESHOLD_MAX) + new = THRESHOLD_MAX; + if (new < 1) + new = 1; + + memset(&tr, 0, sizeof(tr)); + tr.old_limit = b->threshold_limit; + b->threshold_limit = new; + tr.b = b; + + if (smp_call_function_single(b->cpu, threshold_restart_bank, &tr, 1)) + return -ENODEV; + + return size; +} + +static ssize_t show_error_count(struct threshold_block *b, char *buf) +{ + u32 lo, hi; + + /* CPU might be offline by now */ + if (rdmsr_on_cpu(b->cpu, b->address, &lo, &hi)) + return -ENODEV; + + return sprintf(buf, "%u\n", ((hi & THRESHOLD_MAX) - + (THRESHOLD_MAX - b->threshold_limit))); +} + +static struct threshold_attr error_count = { + .attr = {.name = __stringify(error_count), .mode = 0444 }, + .show = show_error_count, +}; + +#define RW_ATTR(val) \ +static struct threshold_attr val = { \ + .attr = {.name = __stringify(val), .mode = 0644 }, \ + .show = show_## val, \ + .store = store_## val, \ +}; + +RW_ATTR(interrupt_enable); +RW_ATTR(threshold_limit); + +static struct attribute *default_attrs[] = { + &threshold_limit.attr, + &error_count.attr, + NULL, /* possibly interrupt_enable if supported, see below */ + NULL, +}; +ATTRIBUTE_GROUPS(default); + +#define to_block(k) container_of(k, struct threshold_block, kobj) +#define to_attr(a) container_of(a, struct threshold_attr, attr) + +static ssize_t show(struct kobject *kobj, struct attribute *attr, char *buf) +{ + struct threshold_block *b = to_block(kobj); + struct threshold_attr *a = to_attr(attr); + ssize_t ret; + + ret = a->show ? a->show(b, buf) : -EIO; + + return ret; +} + +static ssize_t store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + struct threshold_block *b = to_block(kobj); + struct threshold_attr *a = to_attr(attr); + ssize_t ret; + + ret = a->store ? a->store(b, buf, count) : -EIO; + + return ret; +} + +static const struct sysfs_ops threshold_ops = { + .show = show, + .store = store, +}; + +static void threshold_block_release(struct kobject *kobj); + +static const struct kobj_type threshold_ktype = { + .sysfs_ops = &threshold_ops, + .default_groups = default_groups, + .release = threshold_block_release, +}; + +static const char *get_name(unsigned int cpu, unsigned int bank, struct threshold_block *b) +{ + enum smca_bank_types bank_type; + + if (!mce_flags.smca) { + if (b && bank == 4) + return bank4_names(b); + + return th_names[bank]; + } + + bank_type = smca_get_bank_type(cpu, bank); + if (bank_type >= N_SMCA_BANK_TYPES) + return NULL; + + if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) { + if (b->block < ARRAY_SIZE(smca_umc_block_names)) + return smca_umc_block_names[b->block]; + return NULL; + } + + if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1) + return smca_get_name(bank_type); + + snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, + "%s_%u", smca_get_name(bank_type), + per_cpu(smca_banks, cpu)[bank].sysfs_id); + return buf_mcatype; +} + +static int allocate_threshold_blocks(unsigned int cpu, struct threshold_bank *tb, + unsigned int bank, unsigned int block, + u32 address) +{ + struct threshold_block *b = NULL; + u32 low, high; + int err; + + if ((bank >= this_cpu_read(mce_num_banks)) || (block >= NR_BLOCKS)) + return 0; + + if (rdmsr_safe(address, &low, &high)) + return 0; + + if (!(high & MASK_VALID_HI)) { + if (block) + goto recurse; + else + return 0; + } + + if (!(high & MASK_CNTP_HI) || + (high & MASK_LOCKED_HI)) + goto recurse; + + b = kzalloc(sizeof(struct threshold_block), GFP_KERNEL); + if (!b) + return -ENOMEM; + + b->block = block; + b->bank = bank; + b->cpu = cpu; + b->address = address; + b->interrupt_enable = 0; + b->interrupt_capable = lvt_interrupt_supported(bank, high); + b->threshold_limit = THRESHOLD_MAX; + + if (b->interrupt_capable) { + default_attrs[2] = &interrupt_enable.attr; + b->interrupt_enable = 1; + } else { + default_attrs[2] = NULL; + } + + INIT_LIST_HEAD(&b->miscj); + + /* This is safe as @tb is not visible yet */ + if (tb->blocks) + list_add(&b->miscj, &tb->blocks->miscj); + else + tb->blocks = b; + + err = kobject_init_and_add(&b->kobj, &threshold_ktype, tb->kobj, get_name(cpu, bank, b)); + if (err) + goto out_free; +recurse: + address = get_block_address(address, low, high, bank, ++block, cpu); + if (!address) + return 0; + + err = allocate_threshold_blocks(cpu, tb, bank, block, address); + if (err) + goto out_free; + + if (b) + kobject_uevent(&b->kobj, KOBJ_ADD); + + return 0; + +out_free: + if (b) { + list_del(&b->miscj); + kobject_put(&b->kobj); + } + return err; +} + +static int __threshold_add_blocks(struct threshold_bank *b) +{ + struct list_head *head = &b->blocks->miscj; + struct threshold_block *pos = NULL; + struct threshold_block *tmp = NULL; + int err = 0; + + err = kobject_add(&b->blocks->kobj, b->kobj, b->blocks->kobj.name); + if (err) + return err; + + list_for_each_entry_safe(pos, tmp, head, miscj) { + + err = kobject_add(&pos->kobj, b->kobj, pos->kobj.name); + if (err) { + list_for_each_entry_safe_reverse(pos, tmp, head, miscj) + kobject_del(&pos->kobj); + + return err; + } + } + return err; +} + +static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, + unsigned int bank) +{ + struct device *dev = this_cpu_read(mce_device); + struct amd_northbridge *nb = NULL; + struct threshold_bank *b = NULL; + const char *name = get_name(cpu, bank, NULL); + int err = 0; + + if (!dev) + return -ENODEV; + + if (is_shared_bank(bank)) { + nb = node_to_amd_nb(topology_die_id(cpu)); + + /* threshold descriptor already initialized on this node? */ + if (nb && nb->bank4) { + /* yes, use it */ + b = nb->bank4; + err = kobject_add(b->kobj, &dev->kobj, name); + if (err) + goto out; + + bp[bank] = b; + refcount_inc(&b->cpus); + + err = __threshold_add_blocks(b); + + goto out; + } + } + + b = kzalloc(sizeof(struct threshold_bank), GFP_KERNEL); + if (!b) { + err = -ENOMEM; + goto out; + } + + /* Associate the bank with the per-CPU MCE device */ + b->kobj = kobject_create_and_add(name, &dev->kobj); + if (!b->kobj) { + err = -EINVAL; + goto out_free; + } + + if (is_shared_bank(bank)) { + b->shared = 1; + refcount_set(&b->cpus, 1); + + /* nb is already initialized, see above */ + if (nb) { + WARN_ON(nb->bank4); + nb->bank4 = b; + } + } + + err = allocate_threshold_blocks(cpu, b, bank, 0, mca_msr_reg(bank, MCA_MISC)); + if (err) + goto out_kobj; + + bp[bank] = b; + return 0; + +out_kobj: + kobject_put(b->kobj); +out_free: + kfree(b); +out: + return err; +} + +static void threshold_block_release(struct kobject *kobj) +{ + kfree(to_block(kobj)); +} + +static void deallocate_threshold_blocks(struct threshold_bank *bank) +{ + struct threshold_block *pos, *tmp; + + list_for_each_entry_safe(pos, tmp, &bank->blocks->miscj, miscj) { + list_del(&pos->miscj); + kobject_put(&pos->kobj); + } + + kobject_put(&bank->blocks->kobj); +} + +static void __threshold_remove_blocks(struct threshold_bank *b) +{ + struct threshold_block *pos = NULL; + struct threshold_block *tmp = NULL; + + kobject_put(b->kobj); + + list_for_each_entry_safe(pos, tmp, &b->blocks->miscj, miscj) + kobject_put(b->kobj); +} + +static void threshold_remove_bank(struct threshold_bank *bank) +{ + struct amd_northbridge *nb; + + if (!bank->blocks) + goto out_free; + + if (!bank->shared) + goto out_dealloc; + + if (!refcount_dec_and_test(&bank->cpus)) { + __threshold_remove_blocks(bank); + return; + } else { + /* + * The last CPU on this node using the shared bank is going + * away, remove that bank now. + */ + nb = node_to_amd_nb(topology_die_id(smp_processor_id())); + nb->bank4 = NULL; + } + +out_dealloc: + deallocate_threshold_blocks(bank); + +out_free: + kobject_put(bank->kobj); + kfree(bank); +} + +static void __threshold_remove_device(struct threshold_bank **bp) +{ + unsigned int bank, numbanks = this_cpu_read(mce_num_banks); + + for (bank = 0; bank < numbanks; bank++) { + if (!bp[bank]) + continue; + + threshold_remove_bank(bp[bank]); + bp[bank] = NULL; + } + kfree(bp); +} + +int mce_threshold_remove_device(unsigned int cpu) +{ + struct threshold_bank **bp = this_cpu_read(threshold_banks); + + if (!bp) + return 0; + + /* + * Clear the pointer before cleaning up, so that the interrupt won't + * touch anything of this. + */ + this_cpu_write(threshold_banks, NULL); + + __threshold_remove_device(bp); + return 0; +} + +/** + * mce_threshold_create_device - Create the per-CPU MCE threshold device + * @cpu: The plugged in CPU + * + * Create directories and files for all valid threshold banks. + * + * This is invoked from the CPU hotplug callback which was installed in + * mcheck_init_device(). The invocation happens in context of the hotplug + * thread running on @cpu. The callback is invoked on all CPUs which are + * online when the callback is installed or during a real hotplug event. + */ +int mce_threshold_create_device(unsigned int cpu) +{ + unsigned int numbanks, bank; + struct threshold_bank **bp; + int err; + + if (!mce_flags.amd_threshold) + return 0; + + bp = this_cpu_read(threshold_banks); + if (bp) + return 0; + + numbanks = this_cpu_read(mce_num_banks); + bp = kcalloc(numbanks, sizeof(*bp), GFP_KERNEL); + if (!bp) + return -ENOMEM; + + for (bank = 0; bank < numbanks; ++bank) { + if (!(this_cpu_read(bank_map) & BIT_ULL(bank))) + continue; + err = threshold_create_bank(bp, cpu, bank); + if (err) { + __threshold_remove_device(bp); + return err; + } + } + this_cpu_write(threshold_banks, bp); + + if (thresholding_irq_en) + mce_threshold_vector = amd_threshold_interrupt; + return 0; +} diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c new file mode 100644 index 0000000000..8ed3417146 --- /dev/null +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -0,0 +1,216 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Bridge between MCE and APEI + * + * On some machine, corrected memory errors are reported via APEI + * generic hardware error source (GHES) instead of corrected Machine + * Check. These corrected memory errors can be reported to user space + * through /dev/mcelog via faking a corrected Machine Check, so that + * the error memory page can be offlined by /sbin/mcelog if the error + * count for one page is beyond the threshold. + * + * For fatal MCE, save MCE record into persistent storage via ERST, so + * that the MCE record can be logged after reboot via ERST. + * + * Copyright 2010 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + */ + +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/acpi.h> +#include <linux/cper.h> +#include <acpi/apei.h> +#include <acpi/ghes.h> +#include <asm/mce.h> + +#include "internal.h" + +void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) +{ + struct mce m; + int lsb; + + if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) + return; + + /* + * Even if the ->validation_bits are set for address mask, + * to be extra safe, check and reject an error radius '0', + * and fall back to the default page size. + */ + if (mem_err->validation_bits & CPER_MEM_VALID_PA_MASK) + lsb = find_first_bit((void *)&mem_err->physical_addr_mask, PAGE_SHIFT); + else + lsb = PAGE_SHIFT; + + mce_setup(&m); + m.bank = -1; + /* Fake a memory read error with unknown channel */ + m.status = MCI_STATUS_VAL | MCI_STATUS_EN | MCI_STATUS_ADDRV | MCI_STATUS_MISCV | 0x9f; + m.misc = (MCI_MISC_ADDR_PHYS << 6) | lsb; + + if (severity >= GHES_SEV_RECOVERABLE) + m.status |= MCI_STATUS_UC; + + if (severity >= GHES_SEV_PANIC) { + m.status |= MCI_STATUS_PCC; + m.tsc = rdtsc(); + } + + m.addr = mem_err->physical_addr; + mce_log(&m); +} +EXPORT_SYMBOL_GPL(apei_mce_report_mem_error); + +int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) +{ + const u64 *i_mce = ((const u64 *) (ctx_info + 1)); + unsigned int cpu; + struct mce m; + + if (!boot_cpu_has(X86_FEATURE_SMCA)) + return -EINVAL; + + /* + * The starting address of the register array extracted from BERT must + * match with the first expected register in the register layout of + * SMCA address space. This address corresponds to banks's MCA_STATUS + * register. + * + * Match any MCi_STATUS register by turning off bank numbers. + */ + if ((ctx_info->msr_addr & MSR_AMD64_SMCA_MC0_STATUS) != + MSR_AMD64_SMCA_MC0_STATUS) + return -EINVAL; + + /* + * The register array size must be large enough to include all the + * SMCA registers which need to be extracted. + * + * The number of registers in the register array is determined by + * Register Array Size/8 as defined in UEFI spec v2.8, sec N.2.4.2.2. + * The register layout is fixed and currently the raw data in the + * register array includes 6 SMCA registers which the kernel can + * extract. + */ + if (ctx_info->reg_arr_size < 48) + return -EINVAL; + + mce_setup(&m); + + m.extcpu = -1; + m.socketid = -1; + + for_each_possible_cpu(cpu) { + if (cpu_data(cpu).initial_apicid == lapic_id) { + m.extcpu = cpu; + m.socketid = cpu_data(m.extcpu).phys_proc_id; + break; + } + } + + m.apicid = lapic_id; + m.bank = (ctx_info->msr_addr >> 4) & 0xFF; + m.status = *i_mce; + m.addr = *(i_mce + 1); + m.misc = *(i_mce + 2); + /* Skipping MCA_CONFIG */ + m.ipid = *(i_mce + 4); + m.synd = *(i_mce + 5); + + mce_log(&m); + + return 0; +} + +#define CPER_CREATOR_MCE \ + GUID_INIT(0x75a574e3, 0x5052, 0x4b29, 0x8a, 0x8e, 0xbe, 0x2c, \ + 0x64, 0x90, 0xb8, 0x9d) +#define CPER_SECTION_TYPE_MCE \ + GUID_INIT(0xfe08ffbe, 0x95e4, 0x4be7, 0xbc, 0x73, 0x40, 0x96, \ + 0x04, 0x4a, 0x38, 0xfc) + +/* + * CPER specification (in UEFI specification 2.3 appendix N) requires + * byte-packed. + */ +struct cper_mce_record { + struct cper_record_header hdr; + struct cper_section_descriptor sec_hdr; + struct mce mce; +} __packed; + +int apei_write_mce(struct mce *m) +{ + struct cper_mce_record rcd; + + memset(&rcd, 0, sizeof(rcd)); + memcpy(rcd.hdr.signature, CPER_SIG_RECORD, CPER_SIG_SIZE); + rcd.hdr.revision = CPER_RECORD_REV; + rcd.hdr.signature_end = CPER_SIG_END; + rcd.hdr.section_count = 1; + rcd.hdr.error_severity = CPER_SEV_FATAL; + /* timestamp, platform_id, partition_id are all invalid */ + rcd.hdr.validation_bits = 0; + rcd.hdr.record_length = sizeof(rcd); + rcd.hdr.creator_id = CPER_CREATOR_MCE; + rcd.hdr.notification_type = CPER_NOTIFY_MCE; + rcd.hdr.record_id = cper_next_record_id(); + rcd.hdr.flags = CPER_HW_ERROR_FLAGS_PREVERR; + + rcd.sec_hdr.section_offset = (void *)&rcd.mce - (void *)&rcd; + rcd.sec_hdr.section_length = sizeof(rcd.mce); + rcd.sec_hdr.revision = CPER_SEC_REV; + /* fru_id and fru_text is invalid */ + rcd.sec_hdr.validation_bits = 0; + rcd.sec_hdr.flags = CPER_SEC_PRIMARY; + rcd.sec_hdr.section_type = CPER_SECTION_TYPE_MCE; + rcd.sec_hdr.section_severity = CPER_SEV_FATAL; + + memcpy(&rcd.mce, m, sizeof(*m)); + + return erst_write(&rcd.hdr); +} + +ssize_t apei_read_mce(struct mce *m, u64 *record_id) +{ + struct cper_mce_record rcd; + int rc, pos; + + rc = erst_get_record_id_begin(&pos); + if (rc) + return rc; +retry: + rc = erst_get_record_id_next(&pos, record_id); + if (rc) + goto out; + /* no more record */ + if (*record_id == APEI_ERST_INVALID_RECORD_ID) + goto out; + rc = erst_read_record(*record_id, &rcd.hdr, sizeof(rcd), sizeof(rcd), + &CPER_CREATOR_MCE); + /* someone else has cleared the record, try next one */ + if (rc == -ENOENT) + goto retry; + else if (rc < 0) + goto out; + + memcpy(m, &rcd.mce, sizeof(*m)); + rc = sizeof(*m); +out: + erst_get_record_id_end(); + + return rc; +} + +/* Check whether there is record in ERST */ +int apei_check_mce(void) +{ + return erst_get_record_count(); +} + +int apei_clear_mce(u64 record_id) +{ + return erst_clear(record_id); +} diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c new file mode 100644 index 0000000000..6f35f724cc --- /dev/null +++ b/arch/x86/kernel/cpu/mce/core.c @@ -0,0 +1,2871 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Machine check handler. + * + * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. + * Rest from unknown author(s). + * 2004 Andi Kleen. Rewrote most of it. + * Copyright 2008 Intel Corporation + * Author: Andi Kleen + */ + +#include <linux/thread_info.h> +#include <linux/capability.h> +#include <linux/miscdevice.h> +#include <linux/ratelimit.h> +#include <linux/rcupdate.h> +#include <linux/kobject.h> +#include <linux/uaccess.h> +#include <linux/kdebug.h> +#include <linux/kernel.h> +#include <linux/percpu.h> +#include <linux/string.h> +#include <linux/device.h> +#include <linux/syscore_ops.h> +#include <linux/delay.h> +#include <linux/ctype.h> +#include <linux/sched.h> +#include <linux/sysfs.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/kmod.h> +#include <linux/poll.h> +#include <linux/nmi.h> +#include <linux/cpu.h> +#include <linux/ras.h> +#include <linux/smp.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/debugfs.h> +#include <linux/irq_work.h> +#include <linux/export.h> +#include <linux/set_memory.h> +#include <linux/sync_core.h> +#include <linux/task_work.h> +#include <linux/hardirq.h> + +#include <asm/intel-family.h> +#include <asm/processor.h> +#include <asm/traps.h> +#include <asm/tlbflush.h> +#include <asm/mce.h> +#include <asm/msr.h> +#include <asm/reboot.h> + +#include "internal.h" + +/* sysfs synchronization */ +static DEFINE_MUTEX(mce_sysfs_mutex); + +#define CREATE_TRACE_POINTS +#include <trace/events/mce.h> + +#define SPINUNIT 100 /* 100ns */ + +DEFINE_PER_CPU(unsigned, mce_exception_count); + +DEFINE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); + +DEFINE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); + +#define ATTR_LEN 16 +/* One object for each MCE bank, shared by all CPUs */ +struct mce_bank_dev { + struct device_attribute attr; /* device attribute */ + char attrname[ATTR_LEN]; /* attribute name */ + u8 bank; /* bank number */ +}; +static struct mce_bank_dev mce_bank_devs[MAX_NR_BANKS]; + +struct mce_vendor_flags mce_flags __read_mostly; + +struct mca_config mca_cfg __read_mostly = { + .bootlog = -1, + .monarch_timeout = -1 +}; + +static DEFINE_PER_CPU(struct mce, mces_seen); +static unsigned long mce_need_notify; + +/* + * MCA banks polled by the period polling timer for corrected events. + * With Intel CMCI, this only has MCA banks which do not support CMCI (if any). + */ +DEFINE_PER_CPU(mce_banks_t, mce_poll_banks) = { + [0 ... BITS_TO_LONGS(MAX_NR_BANKS)-1] = ~0UL +}; + +/* + * MCA banks controlled through firmware first for corrected errors. + * This is a global list of banks for which we won't enable CMCI and we + * won't poll. Firmware controls these banks and is responsible for + * reporting corrected errors through GHES. Uncorrected/recoverable + * errors are still notified through a machine check. + */ +mce_banks_t mce_banks_ce_disabled; + +static struct work_struct mce_work; +static struct irq_work mce_irq_work; + +/* + * CPU/chipset specific EDAC code can register a notifier call here to print + * MCE errors in a human-readable form. + */ +BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); + +/* Do initial initialization of a struct mce */ +void mce_setup(struct mce *m) +{ + memset(m, 0, sizeof(struct mce)); + m->cpu = m->extcpu = smp_processor_id(); + /* need the internal __ version to avoid deadlocks */ + m->time = __ktime_get_real_seconds(); + m->cpuvendor = boot_cpu_data.x86_vendor; + m->cpuid = cpuid_eax(1); + m->socketid = cpu_data(m->extcpu).phys_proc_id; + m->apicid = cpu_data(m->extcpu).initial_apicid; + m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); + m->ppin = cpu_data(m->extcpu).ppin; + m->microcode = boot_cpu_data.microcode; +} + +DEFINE_PER_CPU(struct mce, injectm); +EXPORT_PER_CPU_SYMBOL_GPL(injectm); + +void mce_log(struct mce *m) +{ + if (!mce_gen_pool_add(m)) + irq_work_queue(&mce_irq_work); +} +EXPORT_SYMBOL_GPL(mce_log); + +void mce_register_decode_chain(struct notifier_block *nb) +{ + if (WARN_ON(nb->priority < MCE_PRIO_LOWEST || + nb->priority > MCE_PRIO_HIGHEST)) + return; + + blocking_notifier_chain_register(&x86_mce_decoder_chain, nb); +} +EXPORT_SYMBOL_GPL(mce_register_decode_chain); + +void mce_unregister_decode_chain(struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&x86_mce_decoder_chain, nb); +} +EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); + +static void __print_mce(struct mce *m) +{ + pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", + m->extcpu, + (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""), + m->mcgstatus, m->bank, m->status); + + if (m->ip) { + pr_emerg(HW_ERR "RIP%s %02x:<%016Lx> ", + !(m->mcgstatus & MCG_STATUS_EIPV) ? " !INEXACT!" : "", + m->cs, m->ip); + + if (m->cs == __KERNEL_CS) + pr_cont("{%pS}", (void *)(unsigned long)m->ip); + pr_cont("\n"); + } + + pr_emerg(HW_ERR "TSC %llx ", m->tsc); + if (m->addr) + pr_cont("ADDR %llx ", m->addr); + if (m->misc) + pr_cont("MISC %llx ", m->misc); + if (m->ppin) + pr_cont("PPIN %llx ", m->ppin); + + if (mce_flags.smca) { + if (m->synd) + pr_cont("SYND %llx ", m->synd); + if (m->ipid) + pr_cont("IPID %llx ", m->ipid); + } + + pr_cont("\n"); + + /* + * Note this output is parsed by external tools and old fields + * should not be changed. + */ + pr_emerg(HW_ERR "PROCESSOR %u:%x TIME %llu SOCKET %u APIC %x microcode %x\n", + m->cpuvendor, m->cpuid, m->time, m->socketid, m->apicid, + m->microcode); +} + +static void print_mce(struct mce *m) +{ + __print_mce(m); + + if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON) + pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); +} + +#define PANIC_TIMEOUT 5 /* 5 seconds */ + +static atomic_t mce_panicked; + +static int fake_panic; +static atomic_t mce_fake_panicked; + +/* Panic in progress. Enable interrupts and wait for final IPI */ +static void wait_for_panic(void) +{ + long timeout = PANIC_TIMEOUT*USEC_PER_SEC; + + preempt_disable(); + local_irq_enable(); + while (timeout-- > 0) + udelay(1); + if (panic_timeout == 0) + panic_timeout = mca_cfg.panic_timeout; + panic("Panicing machine check CPU died"); +} + +static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) +{ + struct llist_node *pending; + struct mce_evt_llist *l; + int apei_err = 0; + + /* + * Allow instrumentation around external facilities usage. Not that it + * matters a whole lot since the machine is going to panic anyway. + */ + instrumentation_begin(); + + if (!fake_panic) { + /* + * Make sure only one CPU runs in machine check panic + */ + if (atomic_inc_return(&mce_panicked) > 1) + wait_for_panic(); + barrier(); + + bust_spinlocks(1); + console_verbose(); + } else { + /* Don't log too much for fake panic */ + if (atomic_inc_return(&mce_fake_panicked) > 1) + goto out; + } + pending = mce_gen_pool_prepare_records(); + /* First print corrected ones that are still unlogged */ + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; + if (!(m->status & MCI_STATUS_UC)) { + print_mce(m); + if (!apei_err) + apei_err = apei_write_mce(m); + } + } + /* Now print uncorrected but with the final one last */ + llist_for_each_entry(l, pending, llnode) { + struct mce *m = &l->mce; + if (!(m->status & MCI_STATUS_UC)) + continue; + if (!final || mce_cmp(m, final)) { + print_mce(m); + if (!apei_err) + apei_err = apei_write_mce(m); + } + } + if (final) { + print_mce(final); + if (!apei_err) + apei_err = apei_write_mce(final); + } + if (exp) + pr_emerg(HW_ERR "Machine check: %s\n", exp); + if (!fake_panic) { + if (panic_timeout == 0) + panic_timeout = mca_cfg.panic_timeout; + panic(msg); + } else + pr_emerg(HW_ERR "Fake kernel panic: %s\n", msg); + +out: + instrumentation_end(); +} + +/* Support code for software error injection */ + +static int msr_to_offset(u32 msr) +{ + unsigned bank = __this_cpu_read(injectm.bank); + + if (msr == mca_cfg.rip_msr) + return offsetof(struct mce, ip); + if (msr == mca_msr_reg(bank, MCA_STATUS)) + return offsetof(struct mce, status); + if (msr == mca_msr_reg(bank, MCA_ADDR)) + return offsetof(struct mce, addr); + if (msr == mca_msr_reg(bank, MCA_MISC)) + return offsetof(struct mce, misc); + if (msr == MSR_IA32_MCG_STATUS) + return offsetof(struct mce, mcgstatus); + return -1; +} + +void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr) +{ + if (wrmsr) { + pr_emerg("MSR access error: WRMSR to 0x%x (tried to write 0x%08x%08x) at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, (unsigned int)regs->dx, (unsigned int)regs->ax, + regs->ip, (void *)regs->ip); + } else { + pr_emerg("MSR access error: RDMSR from 0x%x at rIP: 0x%lx (%pS)\n", + (unsigned int)regs->cx, regs->ip, (void *)regs->ip); + } + + show_stack_regs(regs); + + panic("MCA architectural violation!\n"); + + while (true) + cpu_relax(); +} + +/* MSR access wrappers used for error injection */ +noinstr u64 mce_rdmsrl(u32 msr) +{ + DECLARE_ARGS(val, low, high); + + if (__this_cpu_read(injectm.finished)) { + int offset; + u64 ret; + + instrumentation_begin(); + + offset = msr_to_offset(msr); + if (offset < 0) + ret = 0; + else + ret = *(u64 *)((char *)this_cpu_ptr(&injectm) + offset); + + instrumentation_end(); + + return ret; + } + + /* + * RDMSR on MCA MSRs should not fault. If they do, this is very much an + * architectural violation and needs to be reported to hw vendor. Panic + * the box to not allow any further progress. + */ + asm volatile("1: rdmsr\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_RDMSR_IN_MCE) + : EAX_EDX_RET(val, low, high) : "c" (msr)); + + + return EAX_EDX_VAL(val, low, high); +} + +static noinstr void mce_wrmsrl(u32 msr, u64 v) +{ + u32 low, high; + + if (__this_cpu_read(injectm.finished)) { + int offset; + + instrumentation_begin(); + + offset = msr_to_offset(msr); + if (offset >= 0) + *(u64 *)((char *)this_cpu_ptr(&injectm) + offset) = v; + + instrumentation_end(); + + return; + } + + low = (u32)v; + high = (u32)(v >> 32); + + /* See comment in mce_rdmsrl() */ + asm volatile("1: wrmsr\n" + "2:\n" + _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE) + : : "c" (msr), "a"(low), "d" (high) : "memory"); +} + +/* + * Collect all global (w.r.t. this processor) status about this machine + * check into our "mce" struct so that we can use it later to assess + * the severity of the problem as we read per-bank specific details. + */ +static noinstr void mce_gather_info(struct mce *m, struct pt_regs *regs) +{ + /* + * Enable instrumentation around mce_setup() which calls external + * facilities. + */ + instrumentation_begin(); + mce_setup(m); + instrumentation_end(); + + m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + if (regs) { + /* + * Get the address of the instruction at the time of + * the machine check error. + */ + if (m->mcgstatus & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) { + m->ip = regs->ip; + m->cs = regs->cs; + + /* + * When in VM86 mode make the cs look like ring 3 + * always. This is a lie, but it's better than passing + * the additional vm86 bit around everywhere. + */ + if (v8086_mode(regs)) + m->cs |= 3; + } + /* Use accurate RIP reporting if available. */ + if (mca_cfg.rip_msr) + m->ip = mce_rdmsrl(mca_cfg.rip_msr); + } +} + +int mce_available(struct cpuinfo_x86 *c) +{ + if (mca_cfg.disabled) + return 0; + return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); +} + +static void mce_schedule_work(void) +{ + if (!mce_gen_pool_empty()) + schedule_work(&mce_work); +} + +static void mce_irq_work_cb(struct irq_work *entry) +{ + mce_schedule_work(); +} + +/* + * Check if the address reported by the CPU is in a format we can parse. + * It would be possible to add code for most other cases, but all would + * be somewhat complicated (e.g. segment offset would require an instruction + * parser). So only support physical addresses up to page granularity for now. + */ +int mce_usable_address(struct mce *m) +{ + if (!(m->status & MCI_STATUS_ADDRV)) + return 0; + + /* Checks after this one are Intel/Zhaoxin-specific: */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + return 1; + + if (!(m->status & MCI_STATUS_MISCV)) + return 0; + + if (MCI_MISC_ADDR_LSB(m->misc) > PAGE_SHIFT) + return 0; + + if (MCI_MISC_ADDR_MODE(m->misc) != MCI_MISC_ADDR_PHYS) + return 0; + + return 1; +} +EXPORT_SYMBOL_GPL(mce_usable_address); + +bool mce_is_memory_error(struct mce *m) +{ + switch (m->cpuvendor) { + case X86_VENDOR_AMD: + case X86_VENDOR_HYGON: + return amd_mce_is_memory_error(m); + + case X86_VENDOR_INTEL: + case X86_VENDOR_ZHAOXIN: + /* + * Intel SDM Volume 3B - 15.9.2 Compound Error Codes + * + * Bit 7 of the MCACOD field of IA32_MCi_STATUS is used for + * indicating a memory error. Bit 8 is used for indicating a + * cache hierarchy error. The combination of bit 2 and bit 3 + * is used for indicating a `generic' cache hierarchy error + * But we can't just blindly check the above bits, because if + * bit 11 is set, then it is a bus/interconnect error - and + * either way the above bits just gives more detail on what + * bus/interconnect error happened. Note that bit 12 can be + * ignored, as it's the "filter" bit. + */ + return (m->status & 0xef80) == BIT(7) || + (m->status & 0xef00) == BIT(8) || + (m->status & 0xeffc) == 0xc; + + default: + return false; + } +} +EXPORT_SYMBOL_GPL(mce_is_memory_error); + +static bool whole_page(struct mce *m) +{ + if (!mca_cfg.ser || !(m->status & MCI_STATUS_MISCV)) + return true; + + return MCI_MISC_ADDR_LSB(m->misc) >= PAGE_SHIFT; +} + +bool mce_is_correctable(struct mce *m) +{ + if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED) + return false; + + if (m->cpuvendor == X86_VENDOR_HYGON && m->status & MCI_STATUS_DEFERRED) + return false; + + if (m->status & MCI_STATUS_UC) + return false; + + return true; +} +EXPORT_SYMBOL_GPL(mce_is_correctable); + +static int mce_early_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + /* Emit the trace record: */ + trace_mce_record(m); + + set_bit(0, &mce_need_notify); + + mce_notify_irq(); + + return NOTIFY_DONE; +} + +static struct notifier_block early_nb = { + .notifier_call = mce_early_notifier, + .priority = MCE_PRIO_EARLY, +}; + +static int uc_decode_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + unsigned long pfn; + + if (!mce || !mce_usable_address(mce)) + return NOTIFY_DONE; + + if (mce->severity != MCE_AO_SEVERITY && + mce->severity != MCE_DEFERRED_SEVERITY) + return NOTIFY_DONE; + + pfn = (mce->addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) { + set_mce_nospec(pfn); + mce->kflags |= MCE_HANDLED_UC; + } + + return NOTIFY_OK; +} + +static struct notifier_block mce_uc_nb = { + .notifier_call = uc_decode_notifier, + .priority = MCE_PRIO_UC, +}; + +static int mce_default_notifier(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + if (mca_cfg.print_all || !m->kflags) + __print_mce(m); + + return NOTIFY_DONE; +} + +static struct notifier_block mce_default_nb = { + .notifier_call = mce_default_notifier, + /* lowest prio, we want it to run last. */ + .priority = MCE_PRIO_LOWEST, +}; + +/* + * Read ADDR and MISC registers. + */ +static noinstr void mce_read_aux(struct mce *m, int i) +{ + if (m->status & MCI_STATUS_MISCV) + m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC)); + + if (m->status & MCI_STATUS_ADDRV) { + m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR)); + + /* + * Mask the reported address by the reported granularity. + */ + if (mca_cfg.ser && (m->status & MCI_STATUS_MISCV)) { + u8 shift = MCI_MISC_ADDR_LSB(m->misc); + m->addr >>= shift; + m->addr <<= shift; + } + + smca_extract_err_addr(m); + } + + if (mce_flags.smca) { + m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i)); + + if (m->status & MCI_STATUS_SYNDV) + m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i)); + } +} + +DEFINE_PER_CPU(unsigned, mce_poll_count); + +/* + * Poll for corrected events or events that happened before reset. + * Those are just logged through /dev/mcelog. + * + * This is executed in standard interrupt context. + * + * Note: spec recommends to panic for fatal unsignalled + * errors here. However this would be quite problematic -- + * we would need to reimplement the Monarch handling and + * it would mess up the exclusion between exception handler + * and poll handler -- * so we skip this for now. + * These cases should not happen anyways, or only when the CPU + * is already totally * confused. In this case it's likely it will + * not fully execute the machine check handler either. + */ +bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + bool error_seen = false; + struct mce m; + int i; + + this_cpu_inc(mce_poll_count); + + mce_gather_info(&m, NULL); + + if (flags & MCP_TIMESTAMP) + m.tsc = rdtsc(); + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + if (!mce_banks[i].ctl || !test_bit(i, *b)) + continue; + + m.misc = 0; + m.addr = 0; + m.bank = i; + + barrier(); + m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); + + /* If this entry is not valid, ignore it */ + if (!(m.status & MCI_STATUS_VAL)) + continue; + + /* + * If we are logging everything (at CPU online) or this + * is a corrected error, then we must log it. + */ + if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC)) + goto log_it; + + /* + * Newer Intel systems that support software error + * recovery need to make additional checks. Other + * CPUs should skip over uncorrected errors, but log + * everything else. + */ + if (!mca_cfg.ser) { + if (m.status & MCI_STATUS_UC) + continue; + goto log_it; + } + + /* Log "not enabled" (speculative) errors */ + if (!(m.status & MCI_STATUS_EN)) + goto log_it; + + /* + * Log UCNA (SDM: 15.6.3 "UCR Error Classification") + * UC == 1 && PCC == 0 && S == 0 + */ + if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S)) + goto log_it; + + /* + * Skip anything else. Presumption is that our read of this + * bank is racing with a machine check. Leave the log alone + * for do_machine_check() to deal with it. + */ + continue; + +log_it: + error_seen = true; + + if (flags & MCP_DONTLOG) + goto clear_it; + + mce_read_aux(&m, i); + m.severity = mce_severity(&m, NULL, NULL, false); + /* + * Don't get the IP here because it's unlikely to + * have anything to do with the actual error location. + */ + + if (mca_cfg.dont_log_ce && !mce_usable_address(&m)) + goto clear_it; + + if (flags & MCP_QUEUE_LOG) + mce_gen_pool_add(&m); + else + mce_log(&m); + +clear_it: + /* + * Clear state for this bank. + */ + mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); + } + + /* + * Don't clear MCG_STATUS here because it's only defined for + * exceptions. + */ + + sync_core(); + + return error_seen; +} +EXPORT_SYMBOL_GPL(machine_check_poll); + +/* + * During IFU recovery Sandy Bridge -EP4S processors set the RIPV and + * EIPV bits in MCG_STATUS to zero on the affected logical processor (SDM + * Vol 3B Table 15-20). But this confuses both the code that determines + * whether the machine check occurred in kernel or user mode, and also + * the severity assessment code. Pretend that EIPV was set, and take the + * ip/cs values from the pt_regs that mce_gather_info() ignored earlier. + */ +static __always_inline void +quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 0) + return; + if ((m->mcgstatus & (MCG_STATUS_EIPV|MCG_STATUS_RIPV)) != 0) + return; + if ((m->status & (MCI_STATUS_OVER|MCI_STATUS_UC| + MCI_STATUS_EN|MCI_STATUS_MISCV|MCI_STATUS_ADDRV| + MCI_STATUS_PCC|MCI_STATUS_S|MCI_STATUS_AR| + MCACOD)) != + (MCI_STATUS_UC|MCI_STATUS_EN| + MCI_STATUS_MISCV|MCI_STATUS_ADDRV|MCI_STATUS_S| + MCI_STATUS_AR|MCACOD_INSTR)) + return; + + m->mcgstatus |= MCG_STATUS_EIPV; + m->ip = regs->ip; + m->cs = regs->cs; +} + +/* + * Disable fast string copy and return from the MCE handler upon the first SRAR + * MCE on bank 1 due to a CPU erratum on Intel Skylake/Cascade Lake/Cooper Lake + * CPUs. + * The fast string copy instructions ("REP; MOVS*") could consume an + * uncorrectable memory error in the cache line _right after_ the desired region + * to copy and raise an MCE with RIP pointing to the instruction _after_ the + * "REP; MOVS*". + * This mitigation addresses the issue completely with the caveat of performance + * degradation on the CPU affected. This is still better than the OS crashing on + * MCEs raised on an irrelevant process due to "REP; MOVS*" accesses from a + * kernel context (e.g., copy_page). + * + * Returns true when fast string copy on CPU has been disabled. + */ +static noinstr bool quirk_skylake_repmov(void) +{ + u64 mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); + u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE); + u64 mc1_status; + + /* + * Apply the quirk only to local machine checks, i.e., no broadcast + * sync is needed. + */ + if (!(mcgstatus & MCG_STATUS_LMCES) || + !(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING)) + return false; + + mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1)); + + /* Check for a software-recoverable data fetch error. */ + if ((mc1_status & + (MCI_STATUS_VAL | MCI_STATUS_OVER | MCI_STATUS_UC | MCI_STATUS_EN | + MCI_STATUS_ADDRV | MCI_STATUS_MISCV | MCI_STATUS_PCC | + MCI_STATUS_AR | MCI_STATUS_S)) == + (MCI_STATUS_VAL | MCI_STATUS_UC | MCI_STATUS_EN | + MCI_STATUS_ADDRV | MCI_STATUS_MISCV | + MCI_STATUS_AR | MCI_STATUS_S)) { + misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING; + mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable); + mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0); + + instrumentation_begin(); + pr_err_once("Erratum detected, disable fast string copy instructions.\n"); + instrumentation_end(); + + return true; + } + + return false; +} + +/* + * Some Zen-based Instruction Fetch Units set EIPV=RIPV=0 on poison consumption + * errors. This means mce_gather_info() will not save the "ip" and "cs" registers. + * + * However, the context is still valid, so save the "cs" register for later use. + * + * The "ip" register is truly unknown, so don't save it or fixup EIPV/RIPV. + * + * The Instruction Fetch Unit is at MCA bank 1 for all affected systems. + */ +static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_regs *regs) +{ + if (bank != 1) + return; + if (!(m->status & MCI_STATUS_POISON)) + return; + + m->cs = regs->cs; +} + +/* + * Do a quick check if any of the events requires a panic. + * This decides if we keep the events around or clear them. + */ +static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp, + struct pt_regs *regs) +{ + char *tmp = *msg; + int i; + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); + if (!(m->status & MCI_STATUS_VAL)) + continue; + + arch___set_bit(i, validp); + if (mce_flags.snb_ifu_quirk) + quirk_sandybridge_ifu(i, m, regs); + + if (mce_flags.zen_ifu_quirk) + quirk_zen_ifu(i, m, regs); + + m->bank = i; + if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { + mce_read_aux(m, i); + *msg = tmp; + return 1; + } + } + return 0; +} + +/* + * Variable to establish order between CPUs while scanning. + * Each CPU spins initially until executing is equal its number. + */ +static atomic_t mce_executing; + +/* + * Defines order of CPUs on entry. First CPU becomes Monarch. + */ +static atomic_t mce_callin; + +/* + * Track which CPUs entered the MCA broadcast synchronization and which not in + * order to print holdouts. + */ +static cpumask_t mce_missing_cpus = CPU_MASK_ALL; + +/* + * Check if a timeout waiting for other CPUs happened. + */ +static noinstr int mce_timed_out(u64 *t, const char *msg) +{ + int ret = 0; + + /* Enable instrumentation around calls to external facilities */ + instrumentation_begin(); + + /* + * The others already did panic for some reason. + * Bail out like in a timeout. + * rmb() to tell the compiler that system_state + * might have been modified by someone else. + */ + rmb(); + if (atomic_read(&mce_panicked)) + wait_for_panic(); + if (!mca_cfg.monarch_timeout) + goto out; + if ((s64)*t < SPINUNIT) { + if (cpumask_and(&mce_missing_cpus, cpu_online_mask, &mce_missing_cpus)) + pr_emerg("CPUs not responding to MCE broadcast (may include false positives): %*pbl\n", + cpumask_pr_args(&mce_missing_cpus)); + mce_panic(msg, NULL, NULL); + + ret = 1; + goto out; + } + *t -= SPINUNIT; + +out: + touch_nmi_watchdog(); + + instrumentation_end(); + + return ret; +} + +/* + * The Monarch's reign. The Monarch is the CPU who entered + * the machine check handler first. It waits for the others to + * raise the exception too and then grades them. When any + * error is fatal panic. Only then let the others continue. + * + * The other CPUs entering the MCE handler will be controlled by the + * Monarch. They are called Subjects. + * + * This way we prevent any potential data corruption in a unrecoverable case + * and also makes sure always all CPU's errors are examined. + * + * Also this detects the case of a machine check event coming from outer + * space (not detected by any CPUs) In this case some external agent wants + * us to shut down, so panic too. + * + * The other CPUs might still decide to panic if the handler happens + * in a unrecoverable place, but in this case the system is in a semi-stable + * state and won't corrupt anything by itself. It's ok to let the others + * continue for a bit first. + * + * All the spin loops have timeouts; when a timeout happens a CPU + * typically elects itself to be Monarch. + */ +static void mce_reign(void) +{ + int cpu; + struct mce *m = NULL; + int global_worst = 0; + char *msg = NULL; + + /* + * This CPU is the Monarch and the other CPUs have run + * through their handlers. + * Grade the severity of the errors of all the CPUs. + */ + for_each_possible_cpu(cpu) { + struct mce *mtmp = &per_cpu(mces_seen, cpu); + + if (mtmp->severity > global_worst) { + global_worst = mtmp->severity; + m = &per_cpu(mces_seen, cpu); + } + } + + /* + * Cannot recover? Panic here then. + * This dumps all the mces in the log buffer and stops the + * other CPUs. + */ + if (m && global_worst >= MCE_PANIC_SEVERITY) { + /* call mce_severity() to get "msg" for panic */ + mce_severity(m, NULL, &msg, true); + mce_panic("Fatal machine check", m, msg); + } + + /* + * For UC somewhere we let the CPU who detects it handle it. + * Also must let continue the others, otherwise the handling + * CPU could deadlock on a lock. + */ + + /* + * No machine check event found. Must be some external + * source or one CPU is hung. Panic. + */ + if (global_worst <= MCE_KEEP_SEVERITY) + mce_panic("Fatal machine check from unknown source", NULL, NULL); + + /* + * Now clear all the mces_seen so that they don't reappear on + * the next mce. + */ + for_each_possible_cpu(cpu) + memset(&per_cpu(mces_seen, cpu), 0, sizeof(struct mce)); +} + +static atomic_t global_nwo; + +/* + * Start of Monarch synchronization. This waits until all CPUs have + * entered the exception handler and then determines if any of them + * saw a fatal event that requires panic. Then it executes them + * in the entry order. + * TBD double check parallel CPU hotunplug + */ +static noinstr int mce_start(int *no_way_out) +{ + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; + int order, ret = -1; + + if (!timeout) + return ret; + + raw_atomic_add(*no_way_out, &global_nwo); + /* + * Rely on the implied barrier below, such that global_nwo + * is updated before mce_callin. + */ + order = raw_atomic_inc_return(&mce_callin); + arch_cpumask_clear_cpu(smp_processor_id(), &mce_missing_cpus); + + /* Enable instrumentation around calls to external facilities */ + instrumentation_begin(); + + /* + * Wait for everyone. + */ + while (raw_atomic_read(&mce_callin) != num_online_cpus()) { + if (mce_timed_out(&timeout, + "Timeout: Not all CPUs entered broadcast exception handler")) { + raw_atomic_set(&global_nwo, 0); + goto out; + } + ndelay(SPINUNIT); + } + + /* + * mce_callin should be read before global_nwo + */ + smp_rmb(); + + if (order == 1) { + /* + * Monarch: Starts executing now, the others wait. + */ + raw_atomic_set(&mce_executing, 1); + } else { + /* + * Subject: Now start the scanning loop one by one in + * the original callin order. + * This way when there are any shared banks it will be + * only seen by one CPU before cleared, avoiding duplicates. + */ + while (raw_atomic_read(&mce_executing) < order) { + if (mce_timed_out(&timeout, + "Timeout: Subject CPUs unable to finish machine check processing")) { + raw_atomic_set(&global_nwo, 0); + goto out; + } + ndelay(SPINUNIT); + } + } + + /* + * Cache the global no_way_out state. + */ + *no_way_out = raw_atomic_read(&global_nwo); + + ret = order; + +out: + instrumentation_end(); + + return ret; +} + +/* + * Synchronize between CPUs after main scanning loop. + * This invokes the bulk of the Monarch processing. + */ +static noinstr int mce_end(int order) +{ + u64 timeout = (u64)mca_cfg.monarch_timeout * NSEC_PER_USEC; + int ret = -1; + + /* Allow instrumentation around external facilities. */ + instrumentation_begin(); + + if (!timeout) + goto reset; + if (order < 0) + goto reset; + + /* + * Allow others to run. + */ + atomic_inc(&mce_executing); + + if (order == 1) { + /* + * Monarch: Wait for everyone to go through their scanning + * loops. + */ + while (atomic_read(&mce_executing) <= num_online_cpus()) { + if (mce_timed_out(&timeout, + "Timeout: Monarch CPU unable to finish machine check processing")) + goto reset; + ndelay(SPINUNIT); + } + + mce_reign(); + barrier(); + ret = 0; + } else { + /* + * Subject: Wait for Monarch to finish. + */ + while (atomic_read(&mce_executing) != 0) { + if (mce_timed_out(&timeout, + "Timeout: Monarch CPU did not finish machine check processing")) + goto reset; + ndelay(SPINUNIT); + } + + /* + * Don't reset anything. That's done by the Monarch. + */ + ret = 0; + goto out; + } + + /* + * Reset all global state. + */ +reset: + atomic_set(&global_nwo, 0); + atomic_set(&mce_callin, 0); + cpumask_setall(&mce_missing_cpus); + barrier(); + + /* + * Let others run again. + */ + atomic_set(&mce_executing, 0); + +out: + instrumentation_end(); + + return ret; +} + +static __always_inline void mce_clear_state(unsigned long *toclear) +{ + int i; + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + if (arch_test_bit(i, toclear)) + mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); + } +} + +/* + * Cases where we avoid rendezvous handler timeout: + * 1) If this CPU is offline. + * + * 2) If crashing_cpu was set, e.g. we're entering kdump and we need to + * skip those CPUs which remain looping in the 1st kernel - see + * crash_nmi_callback(). + * + * Note: there still is a small window between kexec-ing and the new, + * kdump kernel establishing a new #MC handler where a broadcasted MCE + * might not get handled properly. + */ +static noinstr bool mce_check_crashing_cpu(void) +{ + unsigned int cpu = smp_processor_id(); + + if (arch_cpu_is_offline(cpu) || + (crashing_cpu != -1 && crashing_cpu != cpu)) { + u64 mcgstatus; + + mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS); + + if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) { + if (mcgstatus & MCG_STATUS_LMCES) + return false; + } + + if (mcgstatus & MCG_STATUS_RIPV) { + __wrmsr(MSR_IA32_MCG_STATUS, 0, 0); + return true; + } + } + return false; +} + +static __always_inline int +__mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, + unsigned long *toclear, unsigned long *valid_banks, int no_way_out, + int *worst) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + struct mca_config *cfg = &mca_cfg; + int severity, i, taint = 0; + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + arch___clear_bit(i, toclear); + if (!arch_test_bit(i, valid_banks)) + continue; + + if (!mce_banks[i].ctl) + continue; + + m->misc = 0; + m->addr = 0; + m->bank = i; + + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); + if (!(m->status & MCI_STATUS_VAL)) + continue; + + /* + * Corrected or non-signaled errors are handled by + * machine_check_poll(). Leave them alone, unless this panics. + */ + if (!(m->status & (cfg->ser ? MCI_STATUS_S : MCI_STATUS_UC)) && + !no_way_out) + continue; + + /* Set taint even when machine check was not enabled. */ + taint++; + + severity = mce_severity(m, regs, NULL, true); + + /* + * When machine check was for corrected/deferred handler don't + * touch, unless we're panicking. + */ + if ((severity == MCE_KEEP_SEVERITY || + severity == MCE_UCNA_SEVERITY) && !no_way_out) + continue; + + arch___set_bit(i, toclear); + + /* Machine check event was not enabled. Clear, but ignore. */ + if (severity == MCE_NO_SEVERITY) + continue; + + mce_read_aux(m, i); + + /* assuming valid severity level != 0 */ + m->severity = severity; + + /* + * Enable instrumentation around the mce_log() call which is + * done in #MC context, where instrumentation is disabled. + */ + instrumentation_begin(); + mce_log(m); + instrumentation_end(); + + if (severity > *worst) { + *final = *m; + *worst = severity; + } + } + + /* mce_clear_state will clear *final, save locally for use later */ + *m = *final; + + return taint; +} + +static void kill_me_now(struct callback_head *ch) +{ + struct task_struct *p = container_of(ch, struct task_struct, mce_kill_me); + + p->mce_count = 0; + force_sig(SIGBUS); +} + +static void kill_me_maybe(struct callback_head *cb) +{ + struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + int flags = MF_ACTION_REQUIRED; + unsigned long pfn; + int ret; + + p->mce_count = 0; + pr_err("Uncorrected hardware memory error in user-access at %llx", p->mce_addr); + + if (!p->mce_ripv) + flags |= MF_MUST_KILL; + + pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + ret = memory_failure(pfn, flags); + if (!ret) { + set_mce_nospec(pfn); + sync_core(); + return; + } + + /* + * -EHWPOISON from memory_failure() means that it already sent SIGBUS + * to the current process with the proper error info, + * -EOPNOTSUPP means hwpoison_filter() filtered the error event, + * + * In both cases, no further processing is required. + */ + if (ret == -EHWPOISON || ret == -EOPNOTSUPP) + return; + + pr_err("Memory error not recovered"); + kill_me_now(cb); +} + +static void kill_me_never(struct callback_head *cb) +{ + struct task_struct *p = container_of(cb, struct task_struct, mce_kill_me); + unsigned long pfn; + + p->mce_count = 0; + pr_err("Kernel accessed poison in user space at %llx\n", p->mce_addr); + pfn = (p->mce_addr & MCI_ADDR_PHYSADDR) >> PAGE_SHIFT; + if (!memory_failure(pfn, 0)) + set_mce_nospec(pfn); +} + +static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *)) +{ + int count = ++current->mce_count; + + /* First call, save all the details */ + if (count == 1) { + current->mce_addr = m->addr; + current->mce_kflags = m->kflags; + current->mce_ripv = !!(m->mcgstatus & MCG_STATUS_RIPV); + current->mce_whole_page = whole_page(m); + current->mce_kill_me.func = func; + } + + /* Ten is likely overkill. Don't expect more than two faults before task_work() */ + if (count > 10) + mce_panic("Too many consecutive machine checks while accessing user data", m, msg); + + /* Second or later call, make sure page address matches the one from first call */ + if (count > 1 && (current->mce_addr >> PAGE_SHIFT) != (m->addr >> PAGE_SHIFT)) + mce_panic("Consecutive machine checks to different user pages", m, msg); + + /* Do not call task_work_add() more than once */ + if (count > 1) + return; + + task_work_add(current, ¤t->mce_kill_me, TWA_RESUME); +} + +/* Handle unconfigured int18 (should never happen) */ +static noinstr void unexpected_machine_check(struct pt_regs *regs) +{ + instrumentation_begin(); + pr_err("CPU#%d: Unexpected int18 (Machine Check)\n", + smp_processor_id()); + instrumentation_end(); +} + +/* + * The actual machine check handler. This only handles real exceptions when + * something got corrupted coming in through int 18. + * + * This is executed in #MC context not subject to normal locking rules. + * This implies that most kernel services cannot be safely used. Don't even + * think about putting a printk in there! + * + * On Intel systems this is entered on all CPUs in parallel through + * MCE broadcast. However some CPUs might be broken beyond repair, + * so be always careful when synchronizing with others. + * + * Tracing and kprobes are disabled: if we interrupted a kernel context + * with IF=1, we need to minimize stack usage. There are also recursion + * issues: if the machine check was due to a failure of the memory + * backing the user stack, tracing that reads the user stack will cause + * potentially infinite recursion. + * + * Currently, the #MC handler calls out to a number of external facilities + * and, therefore, allows instrumentation around them. The optimal thing to + * have would be to do the absolutely minimal work required in #MC context + * and have instrumentation disabled only around that. Further processing can + * then happen in process context where instrumentation is allowed. Achieving + * that requires careful auditing and modifications. Until then, the code + * allows instrumentation temporarily, where required. * + */ +noinstr void do_machine_check(struct pt_regs *regs) +{ + int worst = 0, order, no_way_out, kill_current_task, lmce, taint = 0; + DECLARE_BITMAP(valid_banks, MAX_NR_BANKS) = { 0 }; + DECLARE_BITMAP(toclear, MAX_NR_BANKS) = { 0 }; + struct mce m, *final; + char *msg = NULL; + + if (unlikely(mce_flags.p5)) + return pentium_machine_check(regs); + else if (unlikely(mce_flags.winchip)) + return winchip_machine_check(regs); + else if (unlikely(!mca_cfg.initialized)) + return unexpected_machine_check(regs); + + if (mce_flags.skx_repmov_quirk && quirk_skylake_repmov()) + goto clear; + + /* + * Establish sequential order between the CPUs entering the machine + * check handler. + */ + order = -1; + + /* + * If no_way_out gets set, there is no safe way to recover from this + * MCE. + */ + no_way_out = 0; + + /* + * If kill_current_task is not set, there might be a way to recover from this + * error. + */ + kill_current_task = 0; + + /* + * MCEs are always local on AMD. Same is determined by MCG_STATUS_LMCES + * on Intel. + */ + lmce = 1; + + this_cpu_inc(mce_exception_count); + + mce_gather_info(&m, regs); + m.tsc = rdtsc(); + + final = this_cpu_ptr(&mces_seen); + *final = m; + + no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs); + + barrier(); + + /* + * When no restart IP might need to kill or panic. + * Assume the worst for now, but if we find the + * severity is MCE_AR_SEVERITY we have other options. + */ + if (!(m.mcgstatus & MCG_STATUS_RIPV)) + kill_current_task = 1; + /* + * Check if this MCE is signaled to only this logical processor, + * on Intel, Zhaoxin only. + */ + if (m.cpuvendor == X86_VENDOR_INTEL || + m.cpuvendor == X86_VENDOR_ZHAOXIN) + lmce = m.mcgstatus & MCG_STATUS_LMCES; + + /* + * Local machine check may already know that we have to panic. + * Broadcast machine check begins rendezvous in mce_start() + * Go through all banks in exclusion of the other CPUs. This way we + * don't report duplicated events on shared banks because the first one + * to see it will clear it. + */ + if (lmce) { + if (no_way_out) + mce_panic("Fatal local machine check", &m, msg); + } else { + order = mce_start(&no_way_out); + } + + taint = __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst); + + if (!no_way_out) + mce_clear_state(toclear); + + /* + * Do most of the synchronization with other CPUs. + * When there's any problem use only local no_way_out state. + */ + if (!lmce) { + if (mce_end(order) < 0) { + if (!no_way_out) + no_way_out = worst >= MCE_PANIC_SEVERITY; + + if (no_way_out) + mce_panic("Fatal machine check on current CPU", &m, msg); + } + } else { + /* + * If there was a fatal machine check we should have + * already called mce_panic earlier in this function. + * Since we re-read the banks, we might have found + * something new. Check again to see if we found a + * fatal error. We call "mce_severity()" again to + * make sure we have the right "msg". + */ + if (worst >= MCE_PANIC_SEVERITY) { + mce_severity(&m, regs, &msg, true); + mce_panic("Local fatal machine check!", &m, msg); + } + } + + /* + * Enable instrumentation around the external facilities like task_work_add() + * (via queue_task_work()), fixup_exception() etc. For now, that is. Fixing this + * properly would need a lot more involved reorganization. + */ + instrumentation_begin(); + + if (taint) + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + + if (worst != MCE_AR_SEVERITY && !kill_current_task) + goto out; + + /* Fault was in user mode and we need to take some action */ + if ((m.cs & 3) == 3) { + /* If this triggers there is no way to recover. Die hard. */ + BUG_ON(!on_thread_stack() || !user_mode(regs)); + + if (!mce_usable_address(&m)) + queue_task_work(&m, msg, kill_me_now); + else + queue_task_work(&m, msg, kill_me_maybe); + + } else { + /* + * Handle an MCE which has happened in kernel space but from + * which the kernel can recover: ex_has_fault_handler() has + * already verified that the rIP at which the error happened is + * a rIP from which the kernel can recover (by jumping to + * recovery code specified in _ASM_EXTABLE_FAULT()) and the + * corresponding exception handler which would do that is the + * proper one. + */ + if (m.kflags & MCE_IN_KERNEL_RECOV) { + if (!fixup_exception(regs, X86_TRAP_MC, 0, 0)) + mce_panic("Failed kernel mode recovery", &m, msg); + } + + if (m.kflags & MCE_IN_KERNEL_COPYIN) + queue_task_work(&m, msg, kill_me_never); + } + +out: + instrumentation_end(); + +clear: + mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); +} +EXPORT_SYMBOL_GPL(do_machine_check); + +#ifndef CONFIG_MEMORY_FAILURE +int memory_failure(unsigned long pfn, int flags) +{ + /* mce_severity() should not hand us an ACTION_REQUIRED error */ + BUG_ON(flags & MF_ACTION_REQUIRED); + pr_err("Uncorrected memory error in page 0x%lx ignored\n" + "Rebuild kernel with CONFIG_MEMORY_FAILURE=y for smarter handling\n", + pfn); + + return 0; +} +#endif + +/* + * Periodic polling timer for "silent" machine check errors. If the + * poller finds an MCE, poll 2x faster. When the poller finds no more + * errors, poll 2x slower (up to check_interval seconds). + */ +static unsigned long check_interval = INITIAL_CHECK_INTERVAL; + +static DEFINE_PER_CPU(unsigned long, mce_next_interval); /* in jiffies */ +static DEFINE_PER_CPU(struct timer_list, mce_timer); + +static unsigned long mce_adjust_timer_default(unsigned long interval) +{ + return interval; +} + +static unsigned long (*mce_adjust_timer)(unsigned long interval) = mce_adjust_timer_default; + +static void __start_timer(struct timer_list *t, unsigned long interval) +{ + unsigned long when = jiffies + interval; + unsigned long flags; + + local_irq_save(flags); + + if (!timer_pending(t) || time_before(when, t->expires)) + mod_timer(t, round_jiffies(when)); + + local_irq_restore(flags); +} + +static void mc_poll_banks_default(void) +{ + machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); +} + +void (*mc_poll_banks)(void) = mc_poll_banks_default; + +static void mce_timer_fn(struct timer_list *t) +{ + struct timer_list *cpu_t = this_cpu_ptr(&mce_timer); + unsigned long iv; + + WARN_ON(cpu_t != t); + + iv = __this_cpu_read(mce_next_interval); + + if (mce_available(this_cpu_ptr(&cpu_info))) { + mc_poll_banks(); + + if (mce_intel_cmci_poll()) { + iv = mce_adjust_timer(iv); + goto done; + } + } + + /* + * Alert userspace if needed. If we logged an MCE, reduce the polling + * interval, otherwise increase the polling interval. + */ + if (mce_notify_irq()) + iv = max(iv / 2, (unsigned long) HZ/100); + else + iv = min(iv * 2, round_jiffies_relative(check_interval * HZ)); + +done: + __this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); +} + +/* + * Ensure that the timer is firing in @interval from now. + */ +void mce_timer_kick(unsigned long interval) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + unsigned long iv = __this_cpu_read(mce_next_interval); + + __start_timer(t, interval); + + if (interval < iv) + __this_cpu_write(mce_next_interval, interval); +} + +/* Must not be called in IRQ context where del_timer_sync() can deadlock */ +static void mce_timer_delete_all(void) +{ + int cpu; + + for_each_online_cpu(cpu) + del_timer_sync(&per_cpu(mce_timer, cpu)); +} + +/* + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI + * context. + */ +int mce_notify_irq(void) +{ + /* Not more than two messages every minute */ + static DEFINE_RATELIMIT_STATE(ratelimit, 60*HZ, 2); + + if (test_and_clear_bit(0, &mce_need_notify)) { + mce_work_trigger(); + + if (__ratelimit(&ratelimit)) + pr_info(HW_ERR "Machine check events logged\n"); + + return 1; + } + return 0; +} +EXPORT_SYMBOL_GPL(mce_notify_irq); + +static void __mcheck_cpu_mce_banks_init(void) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + u8 n_banks = this_cpu_read(mce_num_banks); + int i; + + for (i = 0; i < n_banks; i++) { + struct mce_bank *b = &mce_banks[i]; + + /* + * Init them all, __mcheck_cpu_apply_quirks() is going to apply + * the required vendor quirks before + * __mcheck_cpu_init_clear_banks() does the final bank setup. + */ + b->ctl = -1ULL; + b->init = true; + } +} + +/* + * Initialize Machine Checks for a CPU. + */ +static void __mcheck_cpu_cap_init(void) +{ + u64 cap; + u8 b; + + rdmsrl(MSR_IA32_MCG_CAP, cap); + + b = cap & MCG_BANKCNT_MASK; + + if (b > MAX_NR_BANKS) { + pr_warn("CPU%d: Using only %u machine check banks out of %u\n", + smp_processor_id(), MAX_NR_BANKS, b); + b = MAX_NR_BANKS; + } + + this_cpu_write(mce_num_banks, b); + + __mcheck_cpu_mce_banks_init(); + + /* Use accurate RIP reporting if available. */ + if ((cap & MCG_EXT_P) && MCG_EXT_CNT(cap) >= 9) + mca_cfg.rip_msr = MSR_IA32_MCG_EIP; + + if (cap & MCG_SER_P) + mca_cfg.ser = 1; +} + +static void __mcheck_cpu_init_generic(void) +{ + enum mcp_flags m_fl = 0; + mce_banks_t all_banks; + u64 cap; + + if (!mca_cfg.bootlog) + m_fl = MCP_DONTLOG; + + /* + * Log the machine checks left over from the previous reset. Log them + * only, do not start processing them. That will happen in mcheck_late_init() + * when all consumers have been registered on the notifier chain. + */ + bitmap_fill(all_banks, MAX_NR_BANKS); + machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks); + + cr4_set_bits(X86_CR4_MCE); + + rdmsrl(MSR_IA32_MCG_CAP, cap); + if (cap & MCG_CTL_P) + wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff); +} + +static void __mcheck_cpu_init_clear_banks(void) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + int i; + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + struct mce_bank *b = &mce_banks[i]; + + if (!b->init) + continue; + wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl); + wrmsrl(mca_msr_reg(i, MCA_STATUS), 0); + } +} + +/* + * Do a final check to see if there are any unused/RAZ banks. + * + * This must be done after the banks have been initialized and any quirks have + * been applied. + * + * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs. + * Otherwise, a user who disables a bank will not be able to re-enable it + * without a system reboot. + */ +static void __mcheck_cpu_check_banks(void) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + u64 msrval; + int i; + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + struct mce_bank *b = &mce_banks[i]; + + if (!b->init) + continue; + + rdmsrl(mca_msr_reg(i, MCA_CTL), msrval); + b->init = !!msrval; + } +} + +/* Add per CPU specific workarounds here */ +static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + struct mca_config *cfg = &mca_cfg; + + if (c->x86_vendor == X86_VENDOR_UNKNOWN) { + pr_info("unknown CPU type - not enabling MCE support\n"); + return -EOPNOTSUPP; + } + + /* This should be disabled by the BIOS, but isn't always */ + if (c->x86_vendor == X86_VENDOR_AMD) { + if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) { + /* + * disable GART TBL walk error reporting, which + * trips off incorrectly with the IOMMU & 3ware + * & Cerberus: + */ + clear_bit(10, (unsigned long *)&mce_banks[4].ctl); + } + if (c->x86 < 0x11 && cfg->bootlog < 0) { + /* + * Lots of broken BIOS around that don't clear them + * by default and leave crap in there. Don't log: + */ + cfg->bootlog = 0; + } + /* + * Various K7s with broken bank 0 around. Always disable + * by default. + */ + if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0) + mce_banks[0].ctl = 0; + + /* + * overflow_recov is supported for F15h Models 00h-0fh + * even though we don't have a CPUID bit for it. + */ + if (c->x86 == 0x15 && c->x86_model <= 0xf) + mce_flags.overflow_recov = 1; + + if (c->x86 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; + + } + + if (c->x86_vendor == X86_VENDOR_INTEL) { + /* + * SDM documents that on family 6 bank 0 should not be written + * because it aliases to another special BIOS controlled + * register. + * But it's not aliased anymore on model 0x1a+ + * Don't ignore bank 0 completely because there could be a + * valid event later, merely don't write CTL0. + */ + + if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0) + mce_banks[0].init = false; + + /* + * All newer Intel systems support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) && + cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + + /* + * There are also broken BIOSes on some Pentium M and + * earlier systems: + */ + if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0) + cfg->bootlog = 0; + + if (c->x86 == 6 && c->x86_model == 45) + mce_flags.snb_ifu_quirk = 1; + + /* + * Skylake, Cascacde Lake and Cooper Lake require a quirk on + * rep movs. + */ + if (c->x86 == 6 && c->x86_model == INTEL_FAM6_SKYLAKE_X) + mce_flags.skx_repmov_quirk = 1; + } + + if (c->x86_vendor == X86_VENDOR_ZHAOXIN) { + /* + * All newer Zhaoxin CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } + } + + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = 0; + if (cfg->bootlog != 0) + cfg->panic_timeout = 30; + + return 0; +} + +static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) +{ + if (c->x86 != 5) + return 0; + + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + intel_p5_mcheck_init(c); + mce_flags.p5 = 1; + return 1; + case X86_VENDOR_CENTAUR: + winchip_mcheck_init(c); + mce_flags.winchip = 1; + return 1; + default: + return 0; + } + + return 0; +} + +/* + * Init basic CPU features needed for early decoding of MCEs. + */ +static void __mcheck_cpu_init_early(struct cpuinfo_x86 *c) +{ + if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) { + mce_flags.overflow_recov = !!cpu_has(c, X86_FEATURE_OVERFLOW_RECOV); + mce_flags.succor = !!cpu_has(c, X86_FEATURE_SUCCOR); + mce_flags.smca = !!cpu_has(c, X86_FEATURE_SMCA); + mce_flags.amd_threshold = 1; + } +} + +static void mce_centaur_feature_init(struct cpuinfo_x86 *c) +{ + struct mca_config *cfg = &mca_cfg; + + /* + * All newer Centaur CPUs support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if ((c->x86 == 6 && c->x86_model == 0xf && c->x86_stepping >= 0xe) || + c->x86 > 6) { + if (cfg->monarch_timeout < 0) + cfg->monarch_timeout = USEC_PER_SEC; + } +} + +static void mce_zhaoxin_feature_init(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + + /* + * These CPUs have MCA bank 8 which reports only one error type called + * SVAD (System View Address Decoder). The reporting of that error is + * controlled by IA32_MC8.CTL.0. + * + * If enabled, prefetching on these CPUs will cause SVAD MCE when + * virtual machines start and result in a system panic. Always disable + * bank 8 SVAD error by default. + */ + if ((c->x86 == 7 && c->x86_model == 0x1b) || + (c->x86_model == 0x19 || c->x86_model == 0x1f)) { + if (this_cpu_read(mce_num_banks) > 8) + mce_banks[8].ctl = 0; + } + + intel_init_cmci(); + intel_init_lmce(); + mce_adjust_timer = cmci_intel_adjust_timer; +} + +static void mce_zhaoxin_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); +} + +static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) +{ + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_feature_init(c); + mce_adjust_timer = cmci_intel_adjust_timer; + break; + + case X86_VENDOR_AMD: { + mce_amd_feature_init(c); + break; + } + + case X86_VENDOR_HYGON: + mce_hygon_feature_init(c); + break; + + case X86_VENDOR_CENTAUR: + mce_centaur_feature_init(c); + break; + + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_init(c); + break; + + default: + break; + } +} + +static void __mcheck_cpu_clear_vendor(struct cpuinfo_x86 *c) +{ + switch (c->x86_vendor) { + case X86_VENDOR_INTEL: + mce_intel_feature_clear(c); + break; + + case X86_VENDOR_ZHAOXIN: + mce_zhaoxin_feature_clear(c); + break; + + default: + break; + } +} + +static void mce_start_timer(struct timer_list *t) +{ + unsigned long iv = check_interval * HZ; + + if (mca_cfg.ignore_ce || !iv) + return; + + this_cpu_write(mce_next_interval, iv); + __start_timer(t, iv); +} + +static void __mcheck_cpu_setup_timer(void) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + + timer_setup(t, mce_timer_fn, TIMER_PINNED); +} + +static void __mcheck_cpu_init_timer(void) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + + timer_setup(t, mce_timer_fn, TIMER_PINNED); + mce_start_timer(t); +} + +bool filter_mce(struct mce *m) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) + return amd_filter_mce(m); + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) + return intel_filter_mce(m); + + return false; +} + +static __always_inline void exc_machine_check_kernel(struct pt_regs *regs) +{ + irqentry_state_t irq_state; + + WARN_ON_ONCE(user_mode(regs)); + + /* + * Only required when from kernel mode. See + * mce_check_crashing_cpu() for details. + */ + if (mca_cfg.initialized && mce_check_crashing_cpu()) + return; + + irq_state = irqentry_nmi_enter(regs); + + do_machine_check(regs); + + irqentry_nmi_exit(regs, irq_state); +} + +static __always_inline void exc_machine_check_user(struct pt_regs *regs) +{ + irqentry_enter_from_user_mode(regs); + + do_machine_check(regs); + + irqentry_exit_to_user_mode(regs); +} + +#ifdef CONFIG_X86_64 +/* MCE hit kernel mode */ +DEFINE_IDTENTRY_MCE(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + exc_machine_check_kernel(regs); + local_db_restore(dr7); +} + +/* The user mode variant. */ +DEFINE_IDTENTRY_MCE_USER(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + exc_machine_check_user(regs); + local_db_restore(dr7); +} +#else +/* 32bit unified entry point */ +DEFINE_IDTENTRY_RAW(exc_machine_check) +{ + unsigned long dr7; + + dr7 = local_db_save(); + if (user_mode(regs)) + exc_machine_check_user(regs); + else + exc_machine_check_kernel(regs); + local_db_restore(dr7); +} +#endif + +/* + * Called for each booted CPU to set up machine checks. + * Must be called with preempt off: + */ +void mcheck_cpu_init(struct cpuinfo_x86 *c) +{ + if (mca_cfg.disabled) + return; + + if (__mcheck_cpu_ancient_init(c)) + return; + + if (!mce_available(c)) + return; + + __mcheck_cpu_cap_init(); + + if (__mcheck_cpu_apply_quirks(c) < 0) { + mca_cfg.disabled = 1; + return; + } + + if (mce_gen_pool_init()) { + mca_cfg.disabled = 1; + pr_emerg("Couldn't allocate MCE records pool!\n"); + return; + } + + mca_cfg.initialized = 1; + + __mcheck_cpu_init_early(c); + __mcheck_cpu_init_generic(); + __mcheck_cpu_init_vendor(c); + __mcheck_cpu_init_clear_banks(); + __mcheck_cpu_check_banks(); + __mcheck_cpu_setup_timer(); +} + +/* + * Called for each booted CPU to clear some machine checks opt-ins + */ +void mcheck_cpu_clear(struct cpuinfo_x86 *c) +{ + if (mca_cfg.disabled) + return; + + if (!mce_available(c)) + return; + + /* + * Possibly to clear general settings generic to x86 + * __mcheck_cpu_clear_generic(c); + */ + __mcheck_cpu_clear_vendor(c); + +} + +static void __mce_disable_bank(void *arg) +{ + int bank = *((int *)arg); + __clear_bit(bank, this_cpu_ptr(mce_poll_banks)); + cmci_disable_bank(bank); +} + +void mce_disable_bank(int bank) +{ + if (bank >= this_cpu_read(mce_num_banks)) { + pr_warn(FW_BUG + "Ignoring request to disable invalid MCA bank %d.\n", + bank); + return; + } + set_bit(bank, mce_banks_ce_disabled); + on_each_cpu(__mce_disable_bank, &bank, 1); +} + +/* + * mce=off Disables machine check + * mce=no_cmci Disables CMCI + * mce=no_lmce Disables LMCE + * mce=dont_log_ce Clears corrected events silently, no log created for CEs. + * mce=print_all Print all machine check logs to console + * mce=ignore_ce Disables polling and CMCI, corrected events are not cleared. + * mce=TOLERANCELEVEL[,monarchtimeout] (number, see above) + * monarchtimeout is how long to wait for other CPUs on machine + * check, or 0 to not wait + * mce=bootlog Log MCEs from before booting. Disabled by default on AMD Fam10h + and older. + * mce=nobootlog Don't log MCEs from before booting. + * mce=bios_cmci_threshold Don't program the CMCI threshold + * mce=recovery force enable copy_mc_fragile() + */ +static int __init mcheck_enable(char *str) +{ + struct mca_config *cfg = &mca_cfg; + + if (*str == 0) { + enable_p5_mce(); + return 1; + } + if (*str == '=') + str++; + if (!strcmp(str, "off")) + cfg->disabled = 1; + else if (!strcmp(str, "no_cmci")) + cfg->cmci_disabled = true; + else if (!strcmp(str, "no_lmce")) + cfg->lmce_disabled = 1; + else if (!strcmp(str, "dont_log_ce")) + cfg->dont_log_ce = true; + else if (!strcmp(str, "print_all")) + cfg->print_all = true; + else if (!strcmp(str, "ignore_ce")) + cfg->ignore_ce = true; + else if (!strcmp(str, "bootlog") || !strcmp(str, "nobootlog")) + cfg->bootlog = (str[0] == 'b'); + else if (!strcmp(str, "bios_cmci_threshold")) + cfg->bios_cmci_threshold = 1; + else if (!strcmp(str, "recovery")) + cfg->recovery = 1; + else if (isdigit(str[0])) + get_option(&str, &(cfg->monarch_timeout)); + else { + pr_info("mce argument %s ignored. Please use /sys\n", str); + return 0; + } + return 1; +} +__setup("mce", mcheck_enable); + +int __init mcheck_init(void) +{ + mce_register_decode_chain(&early_nb); + mce_register_decode_chain(&mce_uc_nb); + mce_register_decode_chain(&mce_default_nb); + + INIT_WORK(&mce_work, mce_gen_pool_process); + init_irq_work(&mce_irq_work, mce_irq_work_cb); + + return 0; +} + +/* + * mce_syscore: PM support + */ + +/* + * Disable machine checks on suspend and shutdown. We can't really handle + * them later. + */ +static void mce_disable_error_reporting(void) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + int i; + + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + struct mce_bank *b = &mce_banks[i]; + + if (b->init) + wrmsrl(mca_msr_reg(i, MCA_CTL), 0); + } + return; +} + +static void vendor_disable_error_reporting(void) +{ + /* + * Don't clear on Intel or AMD or Hygon or Zhaoxin CPUs. Some of these + * MSRs are socket-wide. Disabling them for just a single offlined CPU + * is bad, since it will inhibit reporting for all shared resources on + * the socket like the last level cache (LLC), the integrated memory + * controller (iMC), etc. + */ + if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON || + boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) + return; + + mce_disable_error_reporting(); +} + +static int mce_syscore_suspend(void) +{ + vendor_disable_error_reporting(); + return 0; +} + +static void mce_syscore_shutdown(void) +{ + vendor_disable_error_reporting(); +} + +/* + * On resume clear all MCE state. Don't want to see leftovers from the BIOS. + * Only one CPU is active at this time, the others get re-added later using + * CPU hotplug: + */ +static void mce_syscore_resume(void) +{ + __mcheck_cpu_init_generic(); + __mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info)); + __mcheck_cpu_init_clear_banks(); +} + +static struct syscore_ops mce_syscore_ops = { + .suspend = mce_syscore_suspend, + .shutdown = mce_syscore_shutdown, + .resume = mce_syscore_resume, +}; + +/* + * mce_device: Sysfs support + */ + +static void mce_cpu_restart(void *data) +{ + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + __mcheck_cpu_init_generic(); + __mcheck_cpu_init_clear_banks(); + __mcheck_cpu_init_timer(); +} + +/* Reinit MCEs after user configuration changes */ +static void mce_restart(void) +{ + mce_timer_delete_all(); + on_each_cpu(mce_cpu_restart, NULL, 1); + mce_schedule_work(); +} + +/* Toggle features for corrected errors */ +static void mce_disable_cmci(void *data) +{ + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + cmci_clear(); +} + +static void mce_enable_ce(void *all) +{ + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + cmci_reenable(); + cmci_recheck(); + if (all) + __mcheck_cpu_init_timer(); +} + +static struct bus_type mce_subsys = { + .name = "machinecheck", + .dev_name = "machinecheck", +}; + +DEFINE_PER_CPU(struct device *, mce_device); + +static inline struct mce_bank_dev *attr_to_bank(struct device_attribute *attr) +{ + return container_of(attr, struct mce_bank_dev, attr); +} + +static ssize_t show_bank(struct device *s, struct device_attribute *attr, + char *buf) +{ + u8 bank = attr_to_bank(attr)->bank; + struct mce_bank *b; + + if (bank >= per_cpu(mce_num_banks, s->id)) + return -EINVAL; + + b = &per_cpu(mce_banks_array, s->id)[bank]; + + if (!b->init) + return -ENODEV; + + return sprintf(buf, "%llx\n", b->ctl); +} + +static ssize_t set_bank(struct device *s, struct device_attribute *attr, + const char *buf, size_t size) +{ + u8 bank = attr_to_bank(attr)->bank; + struct mce_bank *b; + u64 new; + + if (kstrtou64(buf, 0, &new) < 0) + return -EINVAL; + + if (bank >= per_cpu(mce_num_banks, s->id)) + return -EINVAL; + + b = &per_cpu(mce_banks_array, s->id)[bank]; + + if (!b->init) + return -ENODEV; + + b->ctl = new; + mce_restart(); + + return size; +} + +static ssize_t set_ignore_ce(struct device *s, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u64 new; + + if (kstrtou64(buf, 0, &new) < 0) + return -EINVAL; + + mutex_lock(&mce_sysfs_mutex); + if (mca_cfg.ignore_ce ^ !!new) { + if (new) { + /* disable ce features */ + mce_timer_delete_all(); + on_each_cpu(mce_disable_cmci, NULL, 1); + mca_cfg.ignore_ce = true; + } else { + /* enable ce features */ + mca_cfg.ignore_ce = false; + on_each_cpu(mce_enable_ce, (void *)1, 1); + } + } + mutex_unlock(&mce_sysfs_mutex); + + return size; +} + +static ssize_t set_cmci_disabled(struct device *s, + struct device_attribute *attr, + const char *buf, size_t size) +{ + u64 new; + + if (kstrtou64(buf, 0, &new) < 0) + return -EINVAL; + + mutex_lock(&mce_sysfs_mutex); + if (mca_cfg.cmci_disabled ^ !!new) { + if (new) { + /* disable cmci */ + on_each_cpu(mce_disable_cmci, NULL, 1); + mca_cfg.cmci_disabled = true; + } else { + /* enable cmci */ + mca_cfg.cmci_disabled = false; + on_each_cpu(mce_enable_ce, NULL, 1); + } + } + mutex_unlock(&mce_sysfs_mutex); + + return size; +} + +static ssize_t store_int_with_restart(struct device *s, + struct device_attribute *attr, + const char *buf, size_t size) +{ + unsigned long old_check_interval = check_interval; + ssize_t ret = device_store_ulong(s, attr, buf, size); + + if (check_interval == old_check_interval) + return ret; + + mutex_lock(&mce_sysfs_mutex); + mce_restart(); + mutex_unlock(&mce_sysfs_mutex); + + return ret; +} + +static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout); +static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce); +static DEVICE_BOOL_ATTR(print_all, 0644, mca_cfg.print_all); + +static struct dev_ext_attribute dev_attr_check_interval = { + __ATTR(check_interval, 0644, device_show_int, store_int_with_restart), + &check_interval +}; + +static struct dev_ext_attribute dev_attr_ignore_ce = { + __ATTR(ignore_ce, 0644, device_show_bool, set_ignore_ce), + &mca_cfg.ignore_ce +}; + +static struct dev_ext_attribute dev_attr_cmci_disabled = { + __ATTR(cmci_disabled, 0644, device_show_bool, set_cmci_disabled), + &mca_cfg.cmci_disabled +}; + +static struct device_attribute *mce_device_attrs[] = { + &dev_attr_check_interval.attr, +#ifdef CONFIG_X86_MCELOG_LEGACY + &dev_attr_trigger, +#endif + &dev_attr_monarch_timeout.attr, + &dev_attr_dont_log_ce.attr, + &dev_attr_print_all.attr, + &dev_attr_ignore_ce.attr, + &dev_attr_cmci_disabled.attr, + NULL +}; + +static cpumask_var_t mce_device_initialized; + +static void mce_device_release(struct device *dev) +{ + kfree(dev); +} + +/* Per CPU device init. All of the CPUs still share the same bank device: */ +static int mce_device_create(unsigned int cpu) +{ + struct device *dev; + int err; + int i, j; + + if (!mce_available(&boot_cpu_data)) + return -EIO; + + dev = per_cpu(mce_device, cpu); + if (dev) + return 0; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + dev->id = cpu; + dev->bus = &mce_subsys; + dev->release = &mce_device_release; + + err = device_register(dev); + if (err) { + put_device(dev); + return err; + } + + for (i = 0; mce_device_attrs[i]; i++) { + err = device_create_file(dev, mce_device_attrs[i]); + if (err) + goto error; + } + for (j = 0; j < per_cpu(mce_num_banks, cpu); j++) { + err = device_create_file(dev, &mce_bank_devs[j].attr); + if (err) + goto error2; + } + cpumask_set_cpu(cpu, mce_device_initialized); + per_cpu(mce_device, cpu) = dev; + + return 0; +error2: + while (--j >= 0) + device_remove_file(dev, &mce_bank_devs[j].attr); +error: + while (--i >= 0) + device_remove_file(dev, mce_device_attrs[i]); + + device_unregister(dev); + + return err; +} + +static void mce_device_remove(unsigned int cpu) +{ + struct device *dev = per_cpu(mce_device, cpu); + int i; + + if (!cpumask_test_cpu(cpu, mce_device_initialized)) + return; + + for (i = 0; mce_device_attrs[i]; i++) + device_remove_file(dev, mce_device_attrs[i]); + + for (i = 0; i < per_cpu(mce_num_banks, cpu); i++) + device_remove_file(dev, &mce_bank_devs[i].attr); + + device_unregister(dev); + cpumask_clear_cpu(cpu, mce_device_initialized); + per_cpu(mce_device, cpu) = NULL; +} + +/* Make sure there are no machine checks on offlined CPUs. */ +static void mce_disable_cpu(void) +{ + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + + if (!cpuhp_tasks_frozen) + cmci_clear(); + + vendor_disable_error_reporting(); +} + +static void mce_reenable_cpu(void) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); + int i; + + if (!mce_available(raw_cpu_ptr(&cpu_info))) + return; + + if (!cpuhp_tasks_frozen) + cmci_reenable(); + for (i = 0; i < this_cpu_read(mce_num_banks); i++) { + struct mce_bank *b = &mce_banks[i]; + + if (b->init) + wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl); + } +} + +static int mce_cpu_dead(unsigned int cpu) +{ + mce_intel_hcpu_update(cpu); + + /* intentionally ignoring frozen here */ + if (!cpuhp_tasks_frozen) + cmci_rediscover(); + return 0; +} + +static int mce_cpu_online(unsigned int cpu) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + int ret; + + mce_device_create(cpu); + + ret = mce_threshold_create_device(cpu); + if (ret) { + mce_device_remove(cpu); + return ret; + } + mce_reenable_cpu(); + mce_start_timer(t); + return 0; +} + +static int mce_cpu_pre_down(unsigned int cpu) +{ + struct timer_list *t = this_cpu_ptr(&mce_timer); + + mce_disable_cpu(); + del_timer_sync(t); + mce_threshold_remove_device(cpu); + mce_device_remove(cpu); + return 0; +} + +static __init void mce_init_banks(void) +{ + int i; + + for (i = 0; i < MAX_NR_BANKS; i++) { + struct mce_bank_dev *b = &mce_bank_devs[i]; + struct device_attribute *a = &b->attr; + + b->bank = i; + + sysfs_attr_init(&a->attr); + a->attr.name = b->attrname; + snprintf(b->attrname, ATTR_LEN, "bank%d", i); + + a->attr.mode = 0644; + a->show = show_bank; + a->store = set_bank; + } +} + +/* + * When running on XEN, this initcall is ordered against the XEN mcelog + * initcall: + * + * device_initcall(xen_late_init_mcelog); + * device_initcall_sync(mcheck_init_device); + */ +static __init int mcheck_init_device(void) +{ + int err; + + /* + * Check if we have a spare virtual bit. This will only become + * a problem if/when we move beyond 5-level page tables. + */ + MAYBE_BUILD_BUG_ON(__VIRTUAL_MASK_SHIFT >= 63); + + if (!mce_available(&boot_cpu_data)) { + err = -EIO; + goto err_out; + } + + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; + } + + mce_init_banks(); + + err = subsys_system_register(&mce_subsys, NULL); + if (err) + goto err_out_mem; + + err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL, + mce_cpu_dead); + if (err) + goto err_out_mem; + + /* + * Invokes mce_cpu_online() on all CPUs which are online when + * the state is installed. + */ + err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online", + mce_cpu_online, mce_cpu_pre_down); + if (err < 0) + goto err_out_online; + + register_syscore_ops(&mce_syscore_ops); + + return 0; + +err_out_online: + cpuhp_remove_state(CPUHP_X86_MCE_DEAD); + +err_out_mem: + free_cpumask_var(mce_device_initialized); + +err_out: + pr_err("Unable to init MCE device (rc: %d)\n", err); + + return err; +} +device_initcall_sync(mcheck_init_device); + +/* + * Old style boot options parsing. Only for compatibility. + */ +static int __init mcheck_disable(char *str) +{ + mca_cfg.disabled = 1; + return 1; +} +__setup("nomce", mcheck_disable); + +#ifdef CONFIG_DEBUG_FS +struct dentry *mce_get_debugfs_dir(void) +{ + static struct dentry *dmce; + + if (!dmce) + dmce = debugfs_create_dir("mce", NULL); + + return dmce; +} + +static void mce_reset(void) +{ + atomic_set(&mce_fake_panicked, 0); + atomic_set(&mce_executing, 0); + atomic_set(&mce_callin, 0); + atomic_set(&global_nwo, 0); + cpumask_setall(&mce_missing_cpus); +} + +static int fake_panic_get(void *data, u64 *val) +{ + *val = fake_panic; + return 0; +} + +static int fake_panic_set(void *data, u64 val) +{ + mce_reset(); + fake_panic = val; + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(fake_panic_fops, fake_panic_get, fake_panic_set, + "%llu\n"); + +static void __init mcheck_debugfs_init(void) +{ + struct dentry *dmce; + + dmce = mce_get_debugfs_dir(); + debugfs_create_file_unsafe("fake_panic", 0444, dmce, NULL, + &fake_panic_fops); +} +#else +static void __init mcheck_debugfs_init(void) { } +#endif + +static int __init mcheck_late_init(void) +{ + if (mca_cfg.recovery) + enable_copy_mc_fragile(); + + mcheck_debugfs_init(); + + /* + * Flush out everything that has been logged during early boot, now that + * everything has been initialized (workqueues, decoders, ...). + */ + mce_schedule_work(); + + return 0; +} +late_initcall(mcheck_late_init); diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c new file mode 100644 index 0000000000..a05ac0716e --- /dev/null +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -0,0 +1,373 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * /dev/mcelog driver + * + * K8 parts Copyright 2002,2003 Andi Kleen, SuSE Labs. + * Rest from unknown author(s). + * 2004 Andi Kleen. Rewrote most of it. + * Copyright 2008 Intel Corporation + * Author: Andi Kleen + */ + +#include <linux/miscdevice.h> +#include <linux/slab.h> +#include <linux/kmod.h> +#include <linux/poll.h> + +#include "internal.h" + +static BLOCKING_NOTIFIER_HEAD(mce_injector_chain); + +static DEFINE_MUTEX(mce_chrdev_read_mutex); + +static char mce_helper[128]; +static char *mce_helper_argv[2] = { mce_helper, NULL }; + +/* + * Lockless MCE logging infrastructure. + * This avoids deadlocks on printk locks without having to break locks. Also + * separate MCEs from kernel messages to avoid bogus bug reports. + */ + +static struct mce_log_buffer *mcelog; + +static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait); + +static int dev_mce_log(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *mce = (struct mce *)data; + unsigned int entry; + + if (mce->kflags & MCE_HANDLED_CEC) + return NOTIFY_DONE; + + mutex_lock(&mce_chrdev_read_mutex); + + entry = mcelog->next; + + /* + * When the buffer fills up discard new entries. Assume that the + * earlier errors are the more interesting ones: + */ + if (entry >= mcelog->len) { + set_bit(MCE_OVERFLOW, (unsigned long *)&mcelog->flags); + goto unlock; + } + + mcelog->next = entry + 1; + + memcpy(mcelog->entry + entry, mce, sizeof(struct mce)); + mcelog->entry[entry].finished = 1; + mcelog->entry[entry].kflags = 0; + + /* wake processes polling /dev/mcelog */ + wake_up_interruptible(&mce_chrdev_wait); + +unlock: + mutex_unlock(&mce_chrdev_read_mutex); + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + mce->kflags |= MCE_HANDLED_MCELOG; + + return NOTIFY_OK; +} + +static struct notifier_block dev_mcelog_nb = { + .notifier_call = dev_mce_log, + .priority = MCE_PRIO_MCELOG, +}; + +static void mce_do_trigger(struct work_struct *work) +{ + call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT); +} + +static DECLARE_WORK(mce_trigger_work, mce_do_trigger); + + +void mce_work_trigger(void) +{ + if (mce_helper[0]) + schedule_work(&mce_trigger_work); +} + +static ssize_t +show_trigger(struct device *s, struct device_attribute *attr, char *buf) +{ + strcpy(buf, mce_helper); + strcat(buf, "\n"); + return strlen(mce_helper) + 1; +} + +static ssize_t set_trigger(struct device *s, struct device_attribute *attr, + const char *buf, size_t siz) +{ + char *p; + + strscpy(mce_helper, buf, sizeof(mce_helper)); + p = strchr(mce_helper, '\n'); + + if (p) + *p = 0; + + return strlen(mce_helper) + !!p; +} + +DEVICE_ATTR(trigger, 0644, show_trigger, set_trigger); + +/* + * mce_chrdev: Character device /dev/mcelog to read and clear the MCE log. + */ + +static DEFINE_SPINLOCK(mce_chrdev_state_lock); +static int mce_chrdev_open_count; /* #times opened */ +static int mce_chrdev_open_exclu; /* already open exclusive? */ + +static int mce_chrdev_open(struct inode *inode, struct file *file) +{ + spin_lock(&mce_chrdev_state_lock); + + if (mce_chrdev_open_exclu || + (mce_chrdev_open_count && (file->f_flags & O_EXCL))) { + spin_unlock(&mce_chrdev_state_lock); + + return -EBUSY; + } + + if (file->f_flags & O_EXCL) + mce_chrdev_open_exclu = 1; + mce_chrdev_open_count++; + + spin_unlock(&mce_chrdev_state_lock); + + return nonseekable_open(inode, file); +} + +static int mce_chrdev_release(struct inode *inode, struct file *file) +{ + spin_lock(&mce_chrdev_state_lock); + + mce_chrdev_open_count--; + mce_chrdev_open_exclu = 0; + + spin_unlock(&mce_chrdev_state_lock); + + return 0; +} + +static int mce_apei_read_done; + +/* Collect MCE record of previous boot in persistent storage via APEI ERST. */ +static int __mce_read_apei(char __user **ubuf, size_t usize) +{ + int rc; + u64 record_id; + struct mce m; + + if (usize < sizeof(struct mce)) + return -EINVAL; + + rc = apei_read_mce(&m, &record_id); + /* Error or no more MCE record */ + if (rc <= 0) { + mce_apei_read_done = 1; + /* + * When ERST is disabled, mce_chrdev_read() should return + * "no record" instead of "no device." + */ + if (rc == -ENODEV) + return 0; + return rc; + } + rc = -EFAULT; + if (copy_to_user(*ubuf, &m, sizeof(struct mce))) + return rc; + /* + * In fact, we should have cleared the record after that has + * been flushed to the disk or sent to network in + * /sbin/mcelog, but we have no interface to support that now, + * so just clear it to avoid duplication. + */ + rc = apei_clear_mce(record_id); + if (rc) { + mce_apei_read_done = 1; + return rc; + } + *ubuf += sizeof(struct mce); + + return 0; +} + +static ssize_t mce_chrdev_read(struct file *filp, char __user *ubuf, + size_t usize, loff_t *off) +{ + char __user *buf = ubuf; + unsigned next; + int i, err; + + mutex_lock(&mce_chrdev_read_mutex); + + if (!mce_apei_read_done) { + err = __mce_read_apei(&buf, usize); + if (err || buf != ubuf) + goto out; + } + + /* Only supports full reads right now */ + err = -EINVAL; + if (*off != 0 || usize < mcelog->len * sizeof(struct mce)) + goto out; + + next = mcelog->next; + err = 0; + + for (i = 0; i < next; i++) { + struct mce *m = &mcelog->entry[i]; + + err |= copy_to_user(buf, m, sizeof(*m)); + buf += sizeof(*m); + } + + memset(mcelog->entry, 0, next * sizeof(struct mce)); + mcelog->next = 0; + + if (err) + err = -EFAULT; + +out: + mutex_unlock(&mce_chrdev_read_mutex); + + return err ? err : buf - ubuf; +} + +static __poll_t mce_chrdev_poll(struct file *file, poll_table *wait) +{ + poll_wait(file, &mce_chrdev_wait, wait); + if (READ_ONCE(mcelog->next)) + return EPOLLIN | EPOLLRDNORM; + if (!mce_apei_read_done && apei_check_mce()) + return EPOLLIN | EPOLLRDNORM; + return 0; +} + +static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, + unsigned long arg) +{ + int __user *p = (int __user *)arg; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + switch (cmd) { + case MCE_GET_RECORD_LEN: + return put_user(sizeof(struct mce), p); + case MCE_GET_LOG_LEN: + return put_user(mcelog->len, p); + case MCE_GETCLEAR_FLAGS: { + unsigned flags; + + do { + flags = mcelog->flags; + } while (cmpxchg(&mcelog->flags, flags, 0) != flags); + + return put_user(flags, p); + } + default: + return -ENOTTY; + } +} + +void mce_register_injector_chain(struct notifier_block *nb) +{ + blocking_notifier_chain_register(&mce_injector_chain, nb); +} +EXPORT_SYMBOL_GPL(mce_register_injector_chain); + +void mce_unregister_injector_chain(struct notifier_block *nb) +{ + blocking_notifier_chain_unregister(&mce_injector_chain, nb); +} +EXPORT_SYMBOL_GPL(mce_unregister_injector_chain); + +static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, + size_t usize, loff_t *off) +{ + 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; + + /* + * Need to give user space some time to set everything up, + * so do it a jiffie or two later everywhere. + */ + schedule_timeout(2); + + blocking_notifier_call_chain(&mce_injector_chain, 0, &m); + + return usize; +} + +static const struct file_operations mce_chrdev_ops = { + .open = mce_chrdev_open, + .release = mce_chrdev_release, + .read = mce_chrdev_read, + .write = mce_chrdev_write, + .poll = mce_chrdev_poll, + .unlocked_ioctl = mce_chrdev_ioctl, + .compat_ioctl = compat_ptr_ioctl, + .llseek = no_llseek, +}; + +static struct miscdevice mce_chrdev_device = { + MISC_MCELOG_MINOR, + "mcelog", + &mce_chrdev_ops, +}; + +static __init int dev_mcelog_init_device(void) +{ + int mce_log_len; + int err; + + mce_log_len = max(MCE_LOG_MIN_LEN, num_online_cpus()); + mcelog = kzalloc(struct_size(mcelog, entry, mce_log_len), GFP_KERNEL); + if (!mcelog) + return -ENOMEM; + + memcpy(mcelog->signature, MCE_LOG_SIGNATURE, sizeof(mcelog->signature)); + mcelog->len = mce_log_len; + mcelog->recordlen = sizeof(struct mce); + + /* register character device /dev/mcelog */ + err = misc_register(&mce_chrdev_device); + if (err) { + if (err == -EBUSY) + /* Xen dom0 might have registered the device already. */ + pr_info("Unable to init device /dev/mcelog, already registered"); + else + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); + + kfree(mcelog); + return err; + } + + mce_register_decode_chain(&dev_mcelog_nb); + return 0; +} +device_initcall_sync(dev_mcelog_init_device); diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c new file mode 100644 index 0000000000..fbe8b61c34 --- /dev/null +++ b/arch/x86/kernel/cpu/mce/genpool.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * MCE event pool management in MCE context + * + * Copyright (C) 2015 Intel Corp. + * Author: Chen, Gong <gong.chen@linux.intel.com> + */ +#include <linux/smp.h> +#include <linux/mm.h> +#include <linux/genalloc.h> +#include <linux/llist.h> +#include "internal.h" + +/* + * printk() is not safe in MCE context. This is a lock-less memory allocator + * used to save error information organized in a lock-less list. + * + * This memory pool is only to be used to save MCE records in MCE context. + * MCE events are rare, so a fixed size memory pool should be enough. Use + * 2 pages to save MCE events for now (~80 MCE records at most). + */ +#define MCE_POOLSZ (2 * PAGE_SIZE) + +static struct gen_pool *mce_evt_pool; +static LLIST_HEAD(mce_event_llist); +static char gen_pool_buf[MCE_POOLSZ]; + +/* + * Compare the record "t" with each of the records on list "l" to see if + * an equivalent one is present in the list. + */ +static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l) +{ + struct mce_evt_llist *node; + struct mce *m1, *m2; + + m1 = &t->mce; + + llist_for_each_entry(node, &l->llnode, llnode) { + m2 = &node->mce; + + if (!mce_cmp(m1, m2)) + return true; + } + return false; +} + +/* + * The system has panicked - we'd like to peruse the list of MCE records + * that have been queued, but not seen by anyone yet. The list is in + * reverse time order, so we need to reverse it. While doing that we can + * also drop duplicate records (these were logged because some banks are + * shared between cores or by all threads on a socket). + */ +struct llist_node *mce_gen_pool_prepare_records(void) +{ + struct llist_node *head; + LLIST_HEAD(new_head); + struct mce_evt_llist *node, *t; + + head = llist_del_all(&mce_event_llist); + if (!head) + return NULL; + + /* squeeze out duplicates while reversing order */ + llist_for_each_entry_safe(node, t, head, llnode) { + if (!is_duplicate_mce_record(node, t)) + llist_add(&node->llnode, &new_head); + } + + return new_head.first; +} + +void mce_gen_pool_process(struct work_struct *__unused) +{ + struct llist_node *head; + struct mce_evt_llist *node, *tmp; + struct mce *mce; + + head = llist_del_all(&mce_event_llist); + if (!head) + return; + + head = llist_reverse_order(head); + llist_for_each_entry_safe(node, tmp, head, llnode) { + mce = &node->mce; + blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); + gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); + } +} + +bool mce_gen_pool_empty(void) +{ + return llist_empty(&mce_event_llist); +} + +int mce_gen_pool_add(struct mce *mce) +{ + struct mce_evt_llist *node; + + if (filter_mce(mce)) + return -EINVAL; + + if (!mce_evt_pool) + return -EINVAL; + + node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); + if (!node) { + pr_warn_ratelimited("MCE records pool full!\n"); + return -ENOMEM; + } + + memcpy(&node->mce, mce, sizeof(*mce)); + llist_add(&node->llnode, &mce_event_llist); + + return 0; +} + +static int mce_gen_pool_create(void) +{ + struct gen_pool *tmpp; + int ret = -ENOMEM; + + tmpp = gen_pool_create(ilog2(sizeof(struct mce_evt_llist)), -1); + if (!tmpp) + goto out; + + ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1); + if (ret) { + gen_pool_destroy(tmpp); + goto out; + } + + mce_evt_pool = tmpp; + +out: + return ret; +} + +int mce_gen_pool_init(void) +{ + /* Just init mce_gen_pool once. */ + if (mce_evt_pool) + return 0; + + return mce_gen_pool_create(); +} diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c new file mode 100644 index 0000000000..72f0695c3d --- /dev/null +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -0,0 +1,800 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Machine check injection support. + * Copyright 2008 Intel Corporation. + * + * Authors: + * Andi Kleen + * Ying Huang + * + * The AMD part (from mce_amd_inj.c): a simple MCE injection facility + * for testing different aspects of the RAS code. This driver should be + * built as module so that it can be loaded on production kernels for + * testing purposes. + * + * Copyright (c) 2010-17: Borislav Petkov <bp@alien8.de> + * Advanced Micro Devices Inc. + */ + +#include <linux/cpu.h> +#include <linux/debugfs.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/notifier.h> +#include <linux/pci.h> +#include <linux/uaccess.h> + +#include <asm/amd_nb.h> +#include <asm/apic.h> +#include <asm/irq_vectors.h> +#include <asm/mce.h> +#include <asm/nmi.h> +#include <asm/smp.h> + +#include "internal.h" + +static bool hw_injection_possible = true; + +/* + * Collect all the MCi_XXX settings + */ +static struct mce i_mce; +static struct dentry *dfs_inj; + +#define MAX_FLAG_OPT_SIZE 4 +#define NBCFG 0x44 + +enum injection_type { + SW_INJ = 0, /* SW injection, simply decode the error */ + HW_INJ, /* Trigger a #MC */ + DFR_INT_INJ, /* Trigger Deferred error interrupt */ + THR_INT_INJ, /* Trigger threshold interrupt */ + N_INJ_TYPES, +}; + +static const char * const flags_options[] = { + [SW_INJ] = "sw", + [HW_INJ] = "hw", + [DFR_INT_INJ] = "df", + [THR_INT_INJ] = "th", + NULL +}; + +/* Set default injection to SW_INJ */ +static enum injection_type inj_type = SW_INJ; + +#define MCE_INJECT_SET(reg) \ +static int inj_##reg##_set(void *data, u64 val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + m->reg = val; \ + return 0; \ +} + +MCE_INJECT_SET(status); +MCE_INJECT_SET(misc); +MCE_INJECT_SET(addr); +MCE_INJECT_SET(synd); + +#define MCE_INJECT_GET(reg) \ +static int inj_##reg##_get(void *data, u64 *val) \ +{ \ + struct mce *m = (struct mce *)data; \ + \ + *val = m->reg; \ + return 0; \ +} + +MCE_INJECT_GET(status); +MCE_INJECT_GET(misc); +MCE_INJECT_GET(addr); +MCE_INJECT_GET(synd); +MCE_INJECT_GET(ipid); + +DEFINE_SIMPLE_ATTRIBUTE(status_fops, inj_status_get, inj_status_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(misc_fops, inj_misc_get, inj_misc_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(addr_fops, inj_addr_get, inj_addr_set, "%llx\n"); +DEFINE_SIMPLE_ATTRIBUTE(synd_fops, inj_synd_get, inj_synd_set, "%llx\n"); + +/* Use the user provided IPID value on a sw injection. */ +static int inj_ipid_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (cpu_feature_enabled(X86_FEATURE_SMCA)) { + if (inj_type == SW_INJ) + m->ipid = val; + } + + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(ipid_fops, inj_ipid_get, inj_ipid_set, "%llx\n"); + +static void setup_inj_struct(struct mce *m) +{ + memset(m, 0, sizeof(struct mce)); + + m->cpuvendor = boot_cpu_data.x86_vendor; + m->time = ktime_get_real_seconds(); + m->cpuid = cpuid_eax(1); + m->microcode = boot_cpu_data.microcode; +} + +/* Update fake mce registers on current CPU. */ +static void inject_mce(struct mce *m) +{ + struct mce *i = &per_cpu(injectm, m->extcpu); + + /* Make sure no one 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; +} + +static void raise_poll(struct mce *m) +{ + unsigned long flags; + mce_banks_t b; + + memset(&b, 0xff, sizeof(mce_banks_t)); + local_irq_save(flags); + machine_check_poll(0, &b); + local_irq_restore(flags); + m->finished = 0; +} + +static void raise_exception(struct mce *m, struct pt_regs *pregs) +{ + struct pt_regs regs; + unsigned long flags; + + if (!pregs) { + memset(®s, 0, sizeof(struct pt_regs)); + regs.ip = m->ip; + regs.cs = m->cs; + pregs = ®s; + } + /* do_machine_check() expects interrupts disabled -- at least */ + local_irq_save(flags); + do_machine_check(pregs); + local_irq_restore(flags); + m->finished = 0; +} + +static cpumask_var_t mce_inject_cpumask; +static DEFINE_MUTEX(mce_inject_mutex); + +static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs) +{ + int cpu = smp_processor_id(); + struct mce *m = this_cpu_ptr(&injectm); + if (!cpumask_test_cpu(cpu, mce_inject_cpumask)) + return NMI_DONE; + cpumask_clear_cpu(cpu, mce_inject_cpumask); + if (m->inject_flags & MCJ_EXCEPTION) + raise_exception(m, regs); + else if (m->status) + raise_poll(m); + return NMI_HANDLED; +} + +static void mce_irq_ipi(void *info) +{ + int cpu = smp_processor_id(); + struct mce *m = this_cpu_ptr(&injectm); + + if (cpumask_test_cpu(cpu, mce_inject_cpumask) && + m->inject_flags & MCJ_EXCEPTION) { + cpumask_clear_cpu(cpu, mce_inject_cpumask); + raise_exception(m, NULL); + } +} + +/* Inject mce on current CPU */ +static int raise_local(void) +{ + struct mce *m = this_cpu_ptr(&injectm); + int context = MCJ_CTX(m->inject_flags); + int ret = 0; + int cpu = m->extcpu; + + if (m->inject_flags & MCJ_EXCEPTION) { + pr_info("Triggering MCE exception on CPU %d\n", cpu); + switch (context) { + case MCJ_CTX_IRQ: + /* + * Could do more to fake interrupts like + * calling irq_enter, but the necessary + * machinery isn't exported currently. + */ + fallthrough; + case MCJ_CTX_PROCESS: + raise_exception(m, NULL); + break; + default: + pr_info("Invalid MCE context\n"); + ret = -EINVAL; + } + pr_info("MCE exception done on CPU %d\n", cpu); + } else if (m->status) { + pr_info("Starting machine check poll CPU %d\n", cpu); + raise_poll(m); + mce_notify_irq(); + pr_info("Machine check poll done on CPU %d\n", cpu); + } else + m->finished = 0; + + return ret; +} + +static void __maybe_unused raise_mce(struct mce *m) +{ + int context = MCJ_CTX(m->inject_flags); + + inject_mce(m); + + if (context == MCJ_CTX_RANDOM) + return; + + if (m->inject_flags & (MCJ_IRQ_BROADCAST | MCJ_NMI_BROADCAST)) { + unsigned long start; + int cpu; + + cpus_read_lock(); + cpumask_copy(mce_inject_cpumask, cpu_online_mask); + cpumask_clear_cpu(get_cpu(), mce_inject_cpumask); + for_each_online_cpu(cpu) { + struct mce *mcpu = &per_cpu(injectm, cpu); + if (!mcpu->finished || + MCJ_CTX(mcpu->inject_flags) != MCJ_CTX_RANDOM) + cpumask_clear_cpu(cpu, mce_inject_cpumask); + } + if (!cpumask_empty(mce_inject_cpumask)) { + if (m->inject_flags & MCJ_IRQ_BROADCAST) { + /* + * don't wait because mce_irq_ipi is necessary + * to be sync with following raise_local + */ + preempt_disable(); + smp_call_function_many(mce_inject_cpumask, + mce_irq_ipi, NULL, 0); + preempt_enable(); + } else if (m->inject_flags & MCJ_NMI_BROADCAST) + __apic_send_IPI_mask(mce_inject_cpumask, NMI_VECTOR); + } + start = jiffies; + while (!cpumask_empty(mce_inject_cpumask)) { + if (!time_before(jiffies, start + 2*HZ)) { + pr_err("Timeout waiting for mce inject %lx\n", + *cpumask_bits(mce_inject_cpumask)); + break; + } + cpu_relax(); + } + raise_local(); + put_cpu(); + cpus_read_unlock(); + } else { + preempt_disable(); + raise_local(); + preempt_enable(); + } +} + +static int mce_inject_raise(struct notifier_block *nb, unsigned long val, + void *data) +{ + struct mce *m = (struct mce *)data; + + if (!m) + return NOTIFY_DONE; + + mutex_lock(&mce_inject_mutex); + raise_mce(m); + mutex_unlock(&mce_inject_mutex); + + return NOTIFY_DONE; +} + +static struct notifier_block inject_nb = { + .notifier_call = mce_inject_raise, +}; + +/* + * Caller needs to be make sure this cpu doesn't disappear + * from under us, i.e.: get_cpu/put_cpu. + */ +static int toggle_hw_mce_inject(unsigned int cpu, bool enable) +{ + u32 l, h; + int err; + + err = rdmsr_on_cpu(cpu, MSR_K7_HWCR, &l, &h); + if (err) { + pr_err("%s: error reading HWCR\n", __func__); + return err; + } + + enable ? (l |= BIT(18)) : (l &= ~BIT(18)); + + err = wrmsr_on_cpu(cpu, MSR_K7_HWCR, l, h); + if (err) + pr_err("%s: error writing HWCR\n", __func__); + + return err; +} + +static int __set_inj(const char *buf) +{ + int i; + + for (i = 0; i < N_INJ_TYPES; i++) { + if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) { + if (i > SW_INJ && !hw_injection_possible) + continue; + inj_type = i; + return 0; + } + } + return -EINVAL; +} + +static ssize_t flags_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE]; + int n; + + n = sprintf(buf, "%s\n", flags_options[inj_type]); + + return simple_read_from_buffer(ubuf, cnt, ppos, buf, n); +} + +static ssize_t flags_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[MAX_FLAG_OPT_SIZE], *__buf; + int err; + + if (!cnt || cnt > MAX_FLAG_OPT_SIZE) + return -EINVAL; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt - 1] = 0; + + /* strip whitespace */ + __buf = strstrip(buf); + + err = __set_inj(__buf); + if (err) { + pr_err("%s: Invalid flags value: %s\n", __func__, __buf); + return err; + } + + *ppos += cnt; + + return cnt; +} + +static const struct file_operations flags_fops = { + .read = flags_read, + .write = flags_write, + .llseek = generic_file_llseek, +}; + +/* + * On which CPU to inject? + */ +MCE_INJECT_GET(extcpu); + +static int inj_extcpu_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + + if (val >= nr_cpu_ids || !cpu_online(val)) { + pr_err("%s: Invalid CPU: %llu\n", __func__, val); + return -EINVAL; + } + m->extcpu = val; + return 0; +} + +DEFINE_SIMPLE_ATTRIBUTE(extcpu_fops, inj_extcpu_get, inj_extcpu_set, "%llu\n"); + +static void trigger_mce(void *info) +{ + asm volatile("int $18"); +} + +static void trigger_dfr_int(void *info) +{ + asm volatile("int %0" :: "i" (DEFERRED_ERROR_VECTOR)); +} + +static void trigger_thr_int(void *info) +{ + asm volatile("int %0" :: "i" (THRESHOLD_APIC_VECTOR)); +} + +static u32 get_nbc_for_node(int node_id) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + u32 cores_per_node; + + cores_per_node = (c->x86_max_cores * smp_num_siblings) / amd_get_nodes_per_socket(); + + return cores_per_node * node_id; +} + +static void toggle_nb_mca_mst_cpu(u16 nid) +{ + struct amd_northbridge *nb; + struct pci_dev *F3; + u32 val; + int err; + + nb = node_to_amd_nb(nid); + if (!nb) + return; + + F3 = nb->misc; + if (!F3) + return; + + err = pci_read_config_dword(F3, NBCFG, &val); + if (err) { + pr_err("%s: Error reading F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); + return; + } + + if (val & BIT(27)) + return; + + pr_err("%s: Set D18F3x44[NbMcaToMstCpuEn] which BIOS hasn't done.\n", + __func__); + + val |= BIT(27); + err = pci_write_config_dword(F3, NBCFG, val); + if (err) + pr_err("%s: Error writing F%dx%03x.\n", + __func__, PCI_FUNC(F3->devfn), NBCFG); +} + +static void prepare_msrs(void *info) +{ + struct mce m = *(struct mce *)info; + u8 b = m.bank; + + wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus); + + if (boot_cpu_has(X86_FEATURE_SMCA)) { + if (m.inject_flags == DFR_INT_INJ) { + wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr); + } else { + wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status); + wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr); + } + + wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); + wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd); + } else { + wrmsrl(MSR_IA32_MCx_STATUS(b), m.status); + wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr); + wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); + } +} + +static void do_inject(void) +{ + u64 mcg_status = 0; + unsigned int cpu = i_mce.extcpu; + u8 b = i_mce.bank; + + i_mce.tsc = rdtsc_ordered(); + + i_mce.status |= MCI_STATUS_VAL; + + if (i_mce.misc) + i_mce.status |= MCI_STATUS_MISCV; + + if (i_mce.synd) + i_mce.status |= MCI_STATUS_SYNDV; + + if (inj_type == SW_INJ) { + mce_log(&i_mce); + return; + } + + /* prep MCE global settings for the injection */ + mcg_status = MCG_STATUS_MCIP | MCG_STATUS_EIPV; + + if (!(i_mce.status & MCI_STATUS_PCC)) + mcg_status |= MCG_STATUS_RIPV; + + /* + * Ensure necessary status bits for deferred errors: + * - MCx_STATUS[Deferred]: make sure it is a deferred error + * - MCx_STATUS[UC] cleared: deferred errors are _not_ UC + */ + if (inj_type == DFR_INT_INJ) { + i_mce.status |= MCI_STATUS_DEFERRED; + i_mce.status &= ~MCI_STATUS_UC; + } + + /* + * For multi node CPUs, logging and reporting of bank 4 errors happens + * only on the node base core. Refer to D18F3x44[NbMcaToMstCpuEn] for + * Fam10h and later BKDGs. + */ + if (boot_cpu_has(X86_FEATURE_AMD_DCM) && + b == 4 && + boot_cpu_data.x86 < 0x17) { + toggle_nb_mca_mst_cpu(topology_die_id(cpu)); + cpu = get_nbc_for_node(topology_die_id(cpu)); + } + + cpus_read_lock(); + if (!cpu_online(cpu)) + goto err; + + toggle_hw_mce_inject(cpu, true); + + i_mce.mcgstatus = mcg_status; + i_mce.inject_flags = inj_type; + smp_call_function_single(cpu, prepare_msrs, &i_mce, 0); + + toggle_hw_mce_inject(cpu, false); + + switch (inj_type) { + case DFR_INT_INJ: + smp_call_function_single(cpu, trigger_dfr_int, NULL, 0); + break; + case THR_INT_INJ: + smp_call_function_single(cpu, trigger_thr_int, NULL, 0); + break; + default: + smp_call_function_single(cpu, trigger_mce, NULL, 0); + } + +err: + cpus_read_unlock(); + +} + +/* + * This denotes into which bank we're injecting and triggers + * the injection, at the same time. + */ +static int inj_bank_set(void *data, u64 val) +{ + struct mce *m = (struct mce *)data; + u8 n_banks; + u64 cap; + + /* Get bank count on target CPU so we can handle non-uniform values. */ + rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap); + n_banks = cap & MCG_BANKCNT_MASK; + + if (val >= n_banks) { + pr_err("MCA bank %llu non-existent on CPU%d\n", val, m->extcpu); + return -EINVAL; + } + + m->bank = val; + + /* + * sw-only injection allows to write arbitrary values into the MCA + * registers because it tests only the decoding paths. + */ + if (inj_type == SW_INJ) + goto inject; + + /* + * Read IPID value to determine if a bank is populated on the target + * CPU. + */ + if (cpu_feature_enabled(X86_FEATURE_SMCA)) { + u64 ipid; + + if (rdmsrl_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) { + pr_err("Error reading IPID on CPU%d\n", m->extcpu); + return -EINVAL; + } + + if (!ipid) { + pr_err("Cannot inject into unpopulated bank %llu\n", val); + return -ENODEV; + } + } + +inject: + do_inject(); + + /* Reset injection struct */ + setup_inj_struct(&i_mce); + + return 0; +} + +MCE_INJECT_GET(bank); + +DEFINE_SIMPLE_ATTRIBUTE(bank_fops, inj_bank_get, inj_bank_set, "%llu\n"); + +static const char readme_msg[] = +"Description of the files and their usages:\n" +"\n" +"Note1: i refers to the bank number below.\n" +"Note2: See respective BKDGs for the exact bit definitions of the files below\n" +"as they mirror the hardware registers.\n" +"\n" +"status:\t Set MCi_STATUS: the bits in that MSR control the error type and\n" +"\t attributes of the error which caused the MCE.\n" +"\n" +"misc:\t Set MCi_MISC: provide auxiliary info about the error. It is mostly\n" +"\t used for error thresholding purposes and its validity is indicated by\n" +"\t MCi_STATUS[MiscV].\n" +"\n" +"synd:\t Set MCi_SYND: provide syndrome info about the error. Only valid on\n" +"\t Scalable MCA systems, and its validity is indicated by MCi_STATUS[SyndV].\n" +"\n" +"addr:\t Error address value to be written to MCi_ADDR. Log address information\n" +"\t associated with the error.\n" +"\n" +"cpu:\t The CPU to inject the error on.\n" +"\n" +"bank:\t Specify the bank you want to inject the error into: the number of\n" +"\t banks in a processor varies and is family/model-specific, therefore, the\n" +"\t supplied value is sanity-checked. Setting the bank value also triggers the\n" +"\t injection.\n" +"\n" +"flags:\t Injection type to be performed. Writing to this file will trigger a\n" +"\t real machine check, an APIC interrupt or invoke the error decoder routines\n" +"\t for AMD processors.\n" +"\n" +"\t Allowed error injection types:\n" +"\t - \"sw\": Software error injection. Decode error to a human-readable \n" +"\t format only. Safe to use.\n" +"\t - \"hw\": Hardware error injection. Causes the #MC exception handler to \n" +"\t handle the error. Be warned: might cause system panic if MCi_STATUS[PCC] \n" +"\t is set. Therefore, consider setting (debugfs_mountpoint)/mce/fake_panic \n" +"\t before injecting.\n" +"\t - \"df\": Trigger APIC interrupt for Deferred error. Causes deferred \n" +"\t error APIC interrupt handler to handle the error if the feature is \n" +"\t is present in hardware. \n" +"\t - \"th\": Trigger APIC interrupt for Threshold errors. Causes threshold \n" +"\t APIC interrupt handler to handle the error. \n" +"\n" +"ipid:\t IPID (AMD-specific)\n" +"\n"; + +static ssize_t +inj_readme_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + return simple_read_from_buffer(ubuf, cnt, ppos, + readme_msg, strlen(readme_msg)); +} + +static const struct file_operations readme_fops = { + .read = inj_readme_read, +}; + +static struct dfs_node { + char *name; + const struct file_operations *fops; + umode_t perm; +} dfs_fls[] = { + { .name = "status", .fops = &status_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "misc", .fops = &misc_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "addr", .fops = &addr_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "synd", .fops = &synd_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "ipid", .fops = &ipid_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "bank", .fops = &bank_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "flags", .fops = &flags_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "cpu", .fops = &extcpu_fops, .perm = S_IRUSR | S_IWUSR }, + { .name = "README", .fops = &readme_fops, .perm = S_IRUSR | S_IRGRP | S_IROTH }, +}; + +static void __init debugfs_init(void) +{ + unsigned int i; + + dfs_inj = debugfs_create_dir("mce-inject", NULL); + + for (i = 0; i < ARRAY_SIZE(dfs_fls); i++) + debugfs_create_file(dfs_fls[i].name, dfs_fls[i].perm, dfs_inj, + &i_mce, dfs_fls[i].fops); +} + +static void check_hw_inj_possible(void) +{ + int cpu; + u8 bank; + + /* + * This behavior exists only on SMCA systems though its not directly + * related to SMCA. + */ + if (!cpu_feature_enabled(X86_FEATURE_SMCA)) + return; + + cpu = get_cpu(); + + for (bank = 0; bank < MAX_NR_BANKS; ++bank) { + u64 status = MCI_STATUS_VAL, ipid; + + /* Check whether bank is populated */ + rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid); + if (!ipid) + continue; + + toggle_hw_mce_inject(cpu, true); + + wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status); + rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status); + wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0); + + if (!status) { + hw_injection_possible = false; + pr_warn("Platform does not allow *hardware* error injection." + "Try using APEI EINJ instead.\n"); + } + + toggle_hw_mce_inject(cpu, false); + + break; + } + + put_cpu(); +} + +static int __init inject_init(void) +{ + if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL)) + return -ENOMEM; + + check_hw_inj_possible(); + + debugfs_init(); + + register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify"); + mce_register_injector_chain(&inject_nb); + + setup_inj_struct(&i_mce); + + pr_info("Machine check injector initialized\n"); + + return 0; +} + +static void __exit inject_exit(void) +{ + + mce_unregister_injector_chain(&inject_nb); + unregister_nmi_handler(NMI_LOCAL, "mce_notify"); + + debugfs_remove_recursive(dfs_inj); + dfs_inj = NULL; + + memset(&dfs_fls, 0, sizeof(dfs_fls)); + + free_cpumask_var(mce_inject_cpumask); +} + +module_init(inject_init); +module_exit(inject_exit); +MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c new file mode 100644 index 0000000000..f5323551c1 --- /dev/null +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -0,0 +1,538 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Intel specific MCE features. + * Copyright 2004 Zwane Mwaikambo <zwane@linuxpower.ca> + * Copyright (C) 2008, 2009 Intel Corporation + * Author: Andi Kleen + */ + +#include <linux/gfp.h> +#include <linux/interrupt.h> +#include <linux/percpu.h> +#include <linux/sched.h> +#include <linux/cpumask.h> +#include <asm/apic.h> +#include <asm/cpufeature.h> +#include <asm/intel-family.h> +#include <asm/processor.h> +#include <asm/msr.h> +#include <asm/mce.h> + +#include "internal.h" + +/* + * Support for Intel Correct Machine Check Interrupts. This allows + * the CPU to raise an interrupt when a corrected machine check happened. + * Normally we pick those up using a regular polling timer. + * Also supports reliable discovery of shared banks. + */ + +/* + * CMCI can be delivered to multiple cpus that share a machine check bank + * so we need to designate a single cpu to process errors logged in each bank + * in the interrupt handler (otherwise we would have many races and potential + * double reporting of the same error). + * Note that this can change when a cpu is offlined or brought online since + * some MCA banks are shared across cpus. When a cpu is offlined, cmci_clear() + * disables CMCI on all banks owned by the cpu and clears this bitfield. At + * this point, cmci_rediscover() kicks in and a different cpu may end up + * taking ownership of some of the shared MCA banks that were previously + * owned by the offlined cpu. + */ +static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned); + +/* + * CMCI storm detection backoff counter + * + * During storm, we reset this counter to INITIAL_CHECK_INTERVAL in case we've + * encountered an error. If not, we decrement it by one. We signal the end of + * the CMCI storm when it reaches 0. + */ +static DEFINE_PER_CPU(int, cmci_backoff_cnt); + +/* + * cmci_discover_lock protects against parallel discovery attempts + * which could race against each other. + */ +static DEFINE_RAW_SPINLOCK(cmci_discover_lock); + +/* + * On systems that do support CMCI but it's disabled, polling for MCEs can + * cause the same event to be reported multiple times because IA32_MCi_STATUS + * is shared by the same package. + */ +static DEFINE_SPINLOCK(cmci_poll_lock); + +#define CMCI_THRESHOLD 1 +#define CMCI_POLL_INTERVAL (30 * HZ) +#define CMCI_STORM_INTERVAL (HZ) +#define CMCI_STORM_THRESHOLD 15 + +static DEFINE_PER_CPU(unsigned long, cmci_time_stamp); +static DEFINE_PER_CPU(unsigned int, cmci_storm_cnt); +static DEFINE_PER_CPU(unsigned int, cmci_storm_state); + +enum { + CMCI_STORM_NONE, + CMCI_STORM_ACTIVE, + CMCI_STORM_SUBSIDED, +}; + +static atomic_t cmci_storm_on_cpus; + +static int cmci_supported(int *banks) +{ + u64 cap; + + if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) + return 0; + + /* + * Vendor check is not strictly needed, but the initial + * initialization is vendor keyed and this + * makes sure none of the backdoors are entered otherwise. + */ + if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && + boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) + return 0; + + if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) + return 0; + rdmsrl(MSR_IA32_MCG_CAP, cap); + *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); + return !!(cap & MCG_CMCI_P); +} + +static bool lmce_supported(void) +{ + u64 tmp; + + if (mca_cfg.lmce_disabled) + return false; + + rdmsrl(MSR_IA32_MCG_CAP, tmp); + + /* + * LMCE depends on recovery support in the processor. Hence both + * MCG_SER_P and MCG_LMCE_P should be present in MCG_CAP. + */ + if ((tmp & (MCG_SER_P | MCG_LMCE_P)) != + (MCG_SER_P | MCG_LMCE_P)) + return false; + + /* + * BIOS should indicate support for LMCE by setting bit 20 in + * IA32_FEAT_CTL without which touching MCG_EXT_CTL will generate a #GP + * fault. The MSR must also be locked for LMCE_ENABLED to take effect. + * WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally + * locks the MSR in the event that it wasn't already locked by BIOS. + */ + rdmsrl(MSR_IA32_FEAT_CTL, tmp); + if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED))) + return false; + + return tmp & FEAT_CTL_LMCE_ENABLED; +} + +bool mce_intel_cmci_poll(void) +{ + if (__this_cpu_read(cmci_storm_state) == CMCI_STORM_NONE) + return false; + + /* + * Reset the counter if we've logged an error in the last poll + * during the storm. + */ + if (machine_check_poll(0, this_cpu_ptr(&mce_banks_owned))) + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + else + this_cpu_dec(cmci_backoff_cnt); + + return true; +} + +void mce_intel_hcpu_update(unsigned long cpu) +{ + if (per_cpu(cmci_storm_state, cpu) == CMCI_STORM_ACTIVE) + atomic_dec(&cmci_storm_on_cpus); + + per_cpu(cmci_storm_state, cpu) = CMCI_STORM_NONE; +} + +static void cmci_toggle_interrupt_mode(bool on) +{ + unsigned long flags, *owned; + int bank; + u64 val; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + owned = this_cpu_ptr(mce_banks_owned); + for_each_set_bit(bank, owned, MAX_NR_BANKS) { + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + + if (on) + val |= MCI_CTL2_CMCI_EN; + else + val &= ~MCI_CTL2_CMCI_EN; + + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + } + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + +unsigned long cmci_intel_adjust_timer(unsigned long interval) +{ + if ((this_cpu_read(cmci_backoff_cnt) > 0) && + (__this_cpu_read(cmci_storm_state) == CMCI_STORM_ACTIVE)) { + mce_notify_irq(); + return CMCI_STORM_INTERVAL; + } + + switch (__this_cpu_read(cmci_storm_state)) { + case CMCI_STORM_ACTIVE: + + /* + * We switch back to interrupt mode once the poll timer has + * silenced itself. That means no events recorded and the timer + * interval is back to our poll interval. + */ + __this_cpu_write(cmci_storm_state, CMCI_STORM_SUBSIDED); + if (!atomic_sub_return(1, &cmci_storm_on_cpus)) + pr_notice("CMCI storm subsided: switching to interrupt mode\n"); + + fallthrough; + + case CMCI_STORM_SUBSIDED: + /* + * We wait for all CPUs to go back to SUBSIDED state. When that + * happens we switch back to interrupt mode. + */ + if (!atomic_read(&cmci_storm_on_cpus)) { + __this_cpu_write(cmci_storm_state, CMCI_STORM_NONE); + cmci_toggle_interrupt_mode(true); + cmci_recheck(); + } + return CMCI_POLL_INTERVAL; + default: + + /* We have shiny weather. Let the poll do whatever it thinks. */ + return interval; + } +} + +static bool cmci_storm_detect(void) +{ + unsigned int cnt = __this_cpu_read(cmci_storm_cnt); + unsigned long ts = __this_cpu_read(cmci_time_stamp); + unsigned long now = jiffies; + int r; + + if (__this_cpu_read(cmci_storm_state) != CMCI_STORM_NONE) + return true; + + if (time_before_eq(now, ts + CMCI_STORM_INTERVAL)) { + cnt++; + } else { + cnt = 1; + __this_cpu_write(cmci_time_stamp, now); + } + __this_cpu_write(cmci_storm_cnt, cnt); + + if (cnt <= CMCI_STORM_THRESHOLD) + return false; + + cmci_toggle_interrupt_mode(false); + __this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE); + r = atomic_add_return(1, &cmci_storm_on_cpus); + mce_timer_kick(CMCI_STORM_INTERVAL); + this_cpu_write(cmci_backoff_cnt, INITIAL_CHECK_INTERVAL); + + if (r == 1) + pr_notice("CMCI storm detected: switching to poll mode\n"); + return true; +} + +/* + * The interrupt handler. This is called on every event. + * Just call the poller directly to log any events. + * This could in theory increase the threshold under high load, + * but doesn't for now. + */ +static void intel_threshold_interrupt(void) +{ + if (cmci_storm_detect()) + return; + + machine_check_poll(MCP_TIMESTAMP, this_cpu_ptr(&mce_banks_owned)); +} + +/* + * Enable CMCI (Corrected Machine Check Interrupt) for available MCE banks + * on this CPU. Use the algorithm recommended in the SDM to discover shared + * banks. + */ +static void cmci_discover(int banks) +{ + unsigned long *owned = (void *)this_cpu_ptr(&mce_banks_owned); + unsigned long flags; + int i; + int bios_wrong_thresh = 0; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + for (i = 0; i < banks; i++) { + u64 val; + int bios_zero_thresh = 0; + + if (test_bit(i, owned)) + continue; + + /* Skip banks in firmware first mode */ + if (test_bit(i, mce_banks_ce_disabled)) + continue; + + rdmsrl(MSR_IA32_MCx_CTL2(i), val); + + /* Already owned by someone else? */ + if (val & MCI_CTL2_CMCI_EN) { + clear_bit(i, owned); + __clear_bit(i, this_cpu_ptr(mce_poll_banks)); + continue; + } + + if (!mca_cfg.bios_cmci_threshold) { + val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK; + val |= CMCI_THRESHOLD; + } else if (!(val & MCI_CTL2_CMCI_THRESHOLD_MASK)) { + /* + * If bios_cmci_threshold boot option was specified + * but the threshold is zero, we'll try to initialize + * it to 1. + */ + bios_zero_thresh = 1; + val |= CMCI_THRESHOLD; + } + + val |= MCI_CTL2_CMCI_EN; + wrmsrl(MSR_IA32_MCx_CTL2(i), val); + rdmsrl(MSR_IA32_MCx_CTL2(i), val); + + /* Did the enable bit stick? -- the bank supports CMCI */ + if (val & MCI_CTL2_CMCI_EN) { + set_bit(i, owned); + __clear_bit(i, this_cpu_ptr(mce_poll_banks)); + /* + * We are able to set thresholds for some banks that + * had a threshold of 0. This means the BIOS has not + * set the thresholds properly or does not work with + * this boot option. Note down now and report later. + */ + if (mca_cfg.bios_cmci_threshold && bios_zero_thresh && + (val & MCI_CTL2_CMCI_THRESHOLD_MASK)) + bios_wrong_thresh = 1; + } else { + WARN_ON(!test_bit(i, this_cpu_ptr(mce_poll_banks))); + } + } + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); + if (mca_cfg.bios_cmci_threshold && bios_wrong_thresh) { + pr_info_once( + "bios_cmci_threshold: Some banks do not have valid thresholds set\n"); + pr_info_once( + "bios_cmci_threshold: Make sure your BIOS supports this boot option\n"); + } +} + +/* + * Just in case we missed an event during initialization check + * all the CMCI owned banks. + */ +void cmci_recheck(void) +{ + unsigned long flags; + int banks; + + if (!mce_available(raw_cpu_ptr(&cpu_info)) || !cmci_supported(&banks)) + return; + + local_irq_save(flags); + machine_check_poll(0, this_cpu_ptr(&mce_banks_owned)); + local_irq_restore(flags); +} + +/* Caller must hold the lock on cmci_discover_lock */ +static void __cmci_disable_bank(int bank) +{ + u64 val; + + if (!test_bit(bank, this_cpu_ptr(mce_banks_owned))) + return; + rdmsrl(MSR_IA32_MCx_CTL2(bank), val); + val &= ~MCI_CTL2_CMCI_EN; + wrmsrl(MSR_IA32_MCx_CTL2(bank), val); + __clear_bit(bank, this_cpu_ptr(mce_banks_owned)); +} + +/* + * Disable CMCI on this CPU for all banks it owns when it goes down. + * This allows other CPUs to claim the banks on rediscovery. + */ +void cmci_clear(void) +{ + unsigned long flags; + int i; + int banks; + + if (!cmci_supported(&banks)) + return; + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + for (i = 0; i < banks; i++) + __cmci_disable_bank(i); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + +static void cmci_rediscover_work_func(void *arg) +{ + int banks; + + /* Recheck banks in case CPUs don't all have the same */ + if (cmci_supported(&banks)) + cmci_discover(banks); +} + +/* After a CPU went down cycle through all the others and rediscover */ +void cmci_rediscover(void) +{ + int banks; + + if (!cmci_supported(&banks)) + return; + + on_each_cpu(cmci_rediscover_work_func, NULL, 1); +} + +/* + * Reenable CMCI on this CPU in case a CPU down failed. + */ +void cmci_reenable(void) +{ + int banks; + if (cmci_supported(&banks)) + cmci_discover(banks); +} + +void cmci_disable_bank(int bank) +{ + int banks; + unsigned long flags; + + if (!cmci_supported(&banks)) + return; + + raw_spin_lock_irqsave(&cmci_discover_lock, flags); + __cmci_disable_bank(bank); + raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); +} + +/* Bank polling function when CMCI is disabled. */ +static void cmci_mc_poll_banks(void) +{ + spin_lock(&cmci_poll_lock); + machine_check_poll(0, this_cpu_ptr(&mce_poll_banks)); + spin_unlock(&cmci_poll_lock); +} + +void intel_init_cmci(void) +{ + int banks; + + if (!cmci_supported(&banks)) { + mc_poll_banks = cmci_mc_poll_banks; + return; + } + + mce_threshold_vector = intel_threshold_interrupt; + cmci_discover(banks); + /* + * For CPU #0 this runs with still disabled APIC, but that's + * ok because only the vector is set up. We still do another + * check for the banks later for CPU #0 just to make sure + * to not miss any events. + */ + apic_write(APIC_LVTCMCI, THRESHOLD_APIC_VECTOR|APIC_DM_FIXED); + cmci_recheck(); +} + +void intel_init_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + + if (!(val & MCG_EXT_CTL_LMCE_EN)) + wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN); +} + +void intel_clear_lmce(void) +{ + u64 val; + + if (!lmce_supported()) + return; + + rdmsrl(MSR_IA32_MCG_EXT_CTL, val); + val &= ~MCG_EXT_CTL_LMCE_EN; + wrmsrl(MSR_IA32_MCG_EXT_CTL, val); +} + +/* + * Enable additional error logs from the integrated + * memory controller on processors that support this. + */ +static void intel_imc_init(struct cpuinfo_x86 *c) +{ + u64 error_control; + + switch (c->x86_model) { + case INTEL_FAM6_SANDYBRIDGE_X: + case INTEL_FAM6_IVYBRIDGE_X: + case INTEL_FAM6_HASWELL_X: + if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control)) + return; + error_control |= 2; + wrmsrl_safe(MSR_ERROR_CONTROL, error_control); + break; + } +} + +void mce_intel_feature_init(struct cpuinfo_x86 *c) +{ + intel_init_cmci(); + intel_init_lmce(); + intel_imc_init(c); +} + +void mce_intel_feature_clear(struct cpuinfo_x86 *c) +{ + intel_clear_lmce(); +} + +bool intel_filter_mce(struct mce *m) +{ + struct cpuinfo_x86 *c = &boot_cpu_data; + + /* MCE errata HSD131, HSM142, HSW131, BDM48, HSM142 and SKX37 */ + if ((c->x86 == 6) && + ((c->x86_model == INTEL_FAM6_HASWELL) || + (c->x86_model == INTEL_FAM6_HASWELL_L) || + (c->x86_model == INTEL_FAM6_BROADWELL) || + (c->x86_model == INTEL_FAM6_HASWELL_G) || + (c->x86_model == INTEL_FAM6_SKYLAKE_X)) && + (m->bank == 0) && + ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) + return true; + + return false; +} diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h new file mode 100644 index 0000000000..bcf1b3c66c --- /dev/null +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -0,0 +1,281 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __X86_MCE_INTERNAL_H__ +#define __X86_MCE_INTERNAL_H__ + +#undef pr_fmt +#define pr_fmt(fmt) "mce: " fmt + +#include <linux/device.h> +#include <asm/mce.h> + +enum severity_level { + MCE_NO_SEVERITY, + MCE_DEFERRED_SEVERITY, + MCE_UCNA_SEVERITY = MCE_DEFERRED_SEVERITY, + MCE_KEEP_SEVERITY, + MCE_SOME_SEVERITY, + MCE_AO_SEVERITY, + MCE_UC_SEVERITY, + MCE_AR_SEVERITY, + MCE_PANIC_SEVERITY, +}; + +extern struct blocking_notifier_head x86_mce_decoder_chain; + +#define INITIAL_CHECK_INTERVAL 5 * 60 /* 5 minutes */ + +struct mce_evt_llist { + struct llist_node llnode; + struct mce mce; +}; + +void mce_gen_pool_process(struct work_struct *__unused); +bool mce_gen_pool_empty(void); +int mce_gen_pool_add(struct mce *mce); +int mce_gen_pool_init(void); +struct llist_node *mce_gen_pool_prepare_records(void); + +int mce_severity(struct mce *a, struct pt_regs *regs, char **msg, bool is_excp); +struct dentry *mce_get_debugfs_dir(void); + +extern mce_banks_t mce_banks_ce_disabled; + +#ifdef CONFIG_X86_MCE_INTEL +unsigned long cmci_intel_adjust_timer(unsigned long interval); +bool mce_intel_cmci_poll(void); +void mce_intel_hcpu_update(unsigned long cpu); +void cmci_disable_bank(int bank); +void intel_init_cmci(void); +void intel_init_lmce(void); +void intel_clear_lmce(void); +bool intel_filter_mce(struct mce *m); +#else +# define cmci_intel_adjust_timer mce_adjust_timer_default +static inline bool mce_intel_cmci_poll(void) { return false; } +static inline void mce_intel_hcpu_update(unsigned long cpu) { } +static inline void cmci_disable_bank(int bank) { } +static inline void intel_init_cmci(void) { } +static inline void intel_init_lmce(void) { } +static inline void intel_clear_lmce(void) { } +static inline bool intel_filter_mce(struct mce *m) { return false; } +#endif + +void mce_timer_kick(unsigned long interval); + +#ifdef CONFIG_ACPI_APEI +int apei_write_mce(struct mce *m); +ssize_t apei_read_mce(struct mce *m, u64 *record_id); +int apei_check_mce(void); +int apei_clear_mce(u64 record_id); +#else +static inline int apei_write_mce(struct mce *m) +{ + return -EINVAL; +} +static inline ssize_t apei_read_mce(struct mce *m, u64 *record_id) +{ + return 0; +} +static inline int apei_check_mce(void) +{ + return 0; +} +static inline int apei_clear_mce(u64 record_id) +{ + return -EINVAL; +} +#endif + +/* + * We consider records to be equivalent if bank+status+addr+misc all match. + * This is only used when the system is going down because of a fatal error + * to avoid cluttering the console log with essentially repeated information. + * In normal processing all errors seen are logged. + */ +static inline bool mce_cmp(struct mce *m1, struct mce *m2) +{ + return m1->bank != m2->bank || + m1->status != m2->status || + m1->addr != m2->addr || + m1->misc != m2->misc; +} + +extern struct device_attribute dev_attr_trigger; + +#ifdef CONFIG_X86_MCELOG_LEGACY +void mce_work_trigger(void); +void mce_register_injector_chain(struct notifier_block *nb); +void mce_unregister_injector_chain(struct notifier_block *nb); +#else +static inline void mce_work_trigger(void) { } +static inline void mce_register_injector_chain(struct notifier_block *nb) { } +static inline void mce_unregister_injector_chain(struct notifier_block *nb) { } +#endif + +struct mca_config { + __u64 lmce_disabled : 1, + disabled : 1, + ser : 1, + recovery : 1, + bios_cmci_threshold : 1, + /* Proper #MC exception handler is set */ + initialized : 1, + __reserved : 58; + + bool dont_log_ce; + bool cmci_disabled; + bool ignore_ce; + bool print_all; + + int monarch_timeout; + int panic_timeout; + u32 rip_msr; + s8 bootlog; +}; + +extern struct mca_config mca_cfg; +DECLARE_PER_CPU_READ_MOSTLY(unsigned int, mce_num_banks); + +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, + + /* Zen IFU quirk */ + zen_ifu_quirk : 1, + + /* AMD-style error thresholding banks present. */ + amd_threshold : 1, + + /* Pentium, family 5-style MCA */ + p5 : 1, + + /* Centaur Winchip C6-style MCA */ + winchip : 1, + + /* SandyBridge IFU quirk */ + snb_ifu_quirk : 1, + + /* Skylake, Cascade Lake, Cooper Lake REP;MOVS* quirk */ + skx_repmov_quirk : 1, + + __reserved_0 : 55; +}; + +extern struct mce_vendor_flags mce_flags; + +struct mce_bank { + /* subevents to enable */ + u64 ctl; + + /* initialise bank? */ + __u64 init : 1, + + /* + * (AMD) MCA_CONFIG[McaLsbInStatusSupported]: When set, this bit indicates + * the LSB field is found in MCA_STATUS and not in MCA_ADDR. + */ + lsb_in_status : 1, + + __reserved_1 : 62; +}; + +DECLARE_PER_CPU_READ_MOSTLY(struct mce_bank[MAX_NR_BANKS], mce_banks_array); + +enum mca_msr { + MCA_CTL, + MCA_STATUS, + MCA_ADDR, + MCA_MISC, +}; + +/* Decide whether to add MCE record to MCE event pool or filter it out. */ +extern bool filter_mce(struct mce *m); + +#ifdef CONFIG_X86_MCE_AMD +extern bool amd_filter_mce(struct mce *m); + +/* + * If MCA_CONFIG[McaLsbInStatusSupported] is set, extract ErrAddr in bits + * [56:0] of MCA_STATUS, else in bits [55:0] of MCA_ADDR. + */ +static __always_inline void smca_extract_err_addr(struct mce *m) +{ + u8 lsb; + + if (!mce_flags.smca) + return; + + if (this_cpu_ptr(mce_banks_array)[m->bank].lsb_in_status) { + lsb = (m->status >> 24) & 0x3f; + + m->addr &= GENMASK_ULL(56, lsb); + + return; + } + + lsb = (m->addr >> 56) & 0x3f; + + m->addr &= GENMASK_ULL(55, lsb); +} + +#else +static inline bool amd_filter_mce(struct mce *m) { return false; } +static inline void smca_extract_err_addr(struct mce *m) { } +#endif + +#ifdef CONFIG_X86_ANCIENT_MCE +void intel_p5_mcheck_init(struct cpuinfo_x86 *c); +void winchip_mcheck_init(struct cpuinfo_x86 *c); +noinstr void pentium_machine_check(struct pt_regs *regs); +noinstr void winchip_machine_check(struct pt_regs *regs); +static inline void enable_p5_mce(void) { mce_p5_enabled = 1; } +#else +static __always_inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {} +static __always_inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {} +static __always_inline void enable_p5_mce(void) {} +static __always_inline void pentium_machine_check(struct pt_regs *regs) {} +static __always_inline void winchip_machine_check(struct pt_regs *regs) {} +#endif + +noinstr u64 mce_rdmsrl(u32 msr); + +static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg) +{ + if (cpu_feature_enabled(X86_FEATURE_SMCA)) { + switch (reg) { + case MCA_CTL: return MSR_AMD64_SMCA_MCx_CTL(bank); + case MCA_ADDR: return MSR_AMD64_SMCA_MCx_ADDR(bank); + case MCA_MISC: return MSR_AMD64_SMCA_MCx_MISC(bank); + case MCA_STATUS: return MSR_AMD64_SMCA_MCx_STATUS(bank); + } + } + + switch (reg) { + case MCA_CTL: return MSR_IA32_MCx_CTL(bank); + case MCA_ADDR: return MSR_IA32_MCx_ADDR(bank); + case MCA_MISC: return MSR_IA32_MCx_MISC(bank); + case MCA_STATUS: return MSR_IA32_MCx_STATUS(bank); + } + + return 0; +} + +extern void (*mc_poll_banks)(void); +#endif /* __X86_MCE_INTERNAL_H__ */ diff --git a/arch/x86/kernel/cpu/mce/p5.c b/arch/x86/kernel/cpu/mce/p5.c new file mode 100644 index 0000000000..2272ad53fc --- /dev/null +++ b/arch/x86/kernel/cpu/mce/p5.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * P5 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/smp.h> +#include <linux/hardirq.h> + +#include <asm/processor.h> +#include <asm/traps.h> +#include <asm/tlbflush.h> +#include <asm/mce.h> +#include <asm/msr.h> + +#include "internal.h" + +/* By default disabled */ +int mce_p5_enabled __read_mostly; + +/* Machine check handler for Pentium class Intel CPUs: */ +noinstr void pentium_machine_check(struct pt_regs *regs) +{ + u32 loaddr, hi, lotype; + + instrumentation_begin(); + rdmsr(MSR_IA32_P5_MC_ADDR, loaddr, hi); + rdmsr(MSR_IA32_P5_MC_TYPE, lotype, hi); + + pr_emerg("CPU#%d: Machine Check Exception: 0x%8X (type 0x%8X).\n", + smp_processor_id(), loaddr, lotype); + + if (lotype & (1<<5)) { + pr_emerg("CPU#%d: Possible thermal failure (CPU on fire ?).\n", + smp_processor_id()); + } + + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + instrumentation_end(); +} + +/* Set up machine check reporting for processors with Intel style MCE: */ +void intel_p5_mcheck_init(struct cpuinfo_x86 *c) +{ + u32 l, h; + + /* Default P5 to off as its often misconnected: */ + if (!mce_p5_enabled) + return; + + /* Check for MCE support: */ + if (!cpu_has(c, X86_FEATURE_MCE)) + return; + + /* Read registers before enabling: */ + rdmsr(MSR_IA32_P5_MC_ADDR, l, h); + rdmsr(MSR_IA32_P5_MC_TYPE, l, h); + pr_info("Intel old style machine check architecture supported.\n"); + + /* Enable MCE: */ + cr4_set_bits(X86_CR4_MCE); + pr_info("Intel old style machine check reporting enabled on CPU#%d.\n", + smp_processor_id()); +} diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c new file mode 100644 index 0000000000..c4477162c0 --- /dev/null +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -0,0 +1,479 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * MCE grading rules. + * Copyright 2008, 2009 Intel Corporation. + * + * Author: Andi Kleen + */ +#include <linux/kernel.h> +#include <linux/seq_file.h> +#include <linux/init.h> +#include <linux/debugfs.h> +#include <linux/uaccess.h> + +#include <asm/mce.h> +#include <asm/intel-family.h> +#include <asm/traps.h> +#include <asm/insn.h> +#include <asm/insn-eval.h> + +#include "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, IN_KERNEL_RECOV = 3 }; +enum ser { SER_REQUIRED = 1, NO_SER = 2 }; +enum exception { EXCP_CONTEXT = 1, NO_EXCP = 2 }; + +static struct severity { + u64 mask; + u64 result; + unsigned char sev; + unsigned char mcgmask; + unsigned char mcgres; + unsigned char ser; + unsigned char context; + unsigned char excp; + unsigned char covered; + unsigned char cpu_model; + unsigned char cpu_minstepping; + unsigned char bank_lo, bank_hi; + char *msg; +} severities[] = { +#define MCESEV(s, m, c...) { .sev = MCE_ ## s ## _SEVERITY, .msg = m, ## c } +#define BANK_RANGE(l, h) .bank_lo = l, .bank_hi = h +#define MODEL_STEPPING(m, s) .cpu_model = m, .cpu_minstepping = s +#define KERNEL .context = IN_KERNEL +#define USER .context = IN_USER +#define KERNEL_RECOV .context = IN_KERNEL_RECOV +#define SER .ser = SER_REQUIRED +#define NOSER .ser = NO_SER +#define EXCP .excp = EXCP_CONTEXT +#define NOEXCP .excp = NO_EXCP +#define BITCLR(x) .mask = x, .result = 0 +#define BITSET(x) .mask = x, .result = x +#define MCGMASK(x, y) .mcgmask = x, .mcgres = y +#define MASK(x, y) .mask = x, .result = y +#define MCI_UC_S (MCI_STATUS_UC|MCI_STATUS_S) +#define MCI_UC_AR (MCI_STATUS_UC|MCI_STATUS_AR) +#define MCI_UC_SAR (MCI_STATUS_UC|MCI_STATUS_S|MCI_STATUS_AR) +#define MCI_ADDR (MCI_STATUS_ADDRV|MCI_STATUS_MISCV) + + MCESEV( + NO, "Invalid", + BITCLR(MCI_STATUS_VAL) + ), + MCESEV( + NO, "Not enabled", + EXCP, BITCLR(MCI_STATUS_EN) + ), + MCESEV( + PANIC, "Processor context corrupt", + BITSET(MCI_STATUS_PCC) + ), + /* When MCIP is not set something is very confused */ + MCESEV( + PANIC, "MCIP not set in MCA handler", + EXCP, MCGMASK(MCG_STATUS_MCIP, 0) + ), + /* Neither return not error IP -- no chance to recover -> PANIC */ + MCESEV( + PANIC, "Neither restart nor error IP", + EXCP, MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, 0) + ), + MCESEV( + PANIC, "In kernel and no restart IP", + EXCP, KERNEL, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( + PANIC, "In kernel and no restart IP", + EXCP, KERNEL_RECOV, MCGMASK(MCG_STATUS_RIPV, 0) + ), + MCESEV( + KEEP, "Corrected error", + NOSER, BITCLR(MCI_STATUS_UC) + ), + /* + * known AO MCACODs reported via MCE or CMC: + * + * SRAO could be signaled either via a machine check exception or + * CMCI with the corresponding bit S 1 or 0. So we don't need to + * check bit S for SRAO. + */ + MCESEV( + AO, "Action optional: memory scrubbing error", + SER, MASK(MCI_UC_AR|MCACOD_SCRUBMSK, MCI_STATUS_UC|MCACOD_SCRUB) + ), + MCESEV( + AO, "Action optional: last level cache writeback error", + SER, MASK(MCI_UC_AR|MCACOD, MCI_STATUS_UC|MCACOD_L3WB) + ), + /* + * Quirk for Skylake/Cascade Lake. Patrol scrubber may be configured + * to report uncorrected errors using CMCI with a special signature. + * UC=0, MSCOD=0x0010, MCACOD=binary(000X 0000 1100 XXXX) reported + * in one of the memory controller banks. + * Set severity to "AO" for same action as normal patrol scrub error. + */ + MCESEV( + AO, "Uncorrected Patrol Scrub Error", + SER, MASK(MCI_STATUS_UC|MCI_ADDR|0xffffeff0, MCI_ADDR|0x001000c0), + MODEL_STEPPING(INTEL_FAM6_SKYLAKE_X, 4), BANK_RANGE(13, 18) + ), + + /* ignore OVER for UCNA */ + MCESEV( + UCNA, "Uncorrected no action required", + SER, MASK(MCI_UC_SAR, MCI_STATUS_UC) + ), + MCESEV( + PANIC, "Illegal combination (UCNA with AR=1)", + SER, + MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_UC|MCI_STATUS_AR) + ), + MCESEV( + KEEP, "Non signaled machine check", + SER, BITCLR(MCI_STATUS_S) + ), + + MCESEV( + PANIC, "Action required with lost events", + SER, BITSET(MCI_STATUS_OVER|MCI_UC_SAR) + ), + + /* known AR MCACODs: */ +#ifdef CONFIG_MEMORY_FAILURE + MCESEV( + KEEP, "Action required but unaffected thread is continuable", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR, MCI_UC_SAR|MCI_ADDR), + MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV) + ), + MCESEV( + AR, "Action required: data load in error recoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL_RECOV + ), + MCESEV( + AR, "Action required: data load error in a user process", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + USER + ), + MCESEV( + AR, "Action required: instruction fetch error in a user process", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + USER + ), + MCESEV( + PANIC, "Data load in unrecoverable area of kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + KERNEL + ), + MCESEV( + PANIC, "Instruction fetch error in kernel", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + KERNEL + ), +#endif + MCESEV( + PANIC, "Action required: unknown MCACOD", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_SAR) + ), + + MCESEV( + SOME, "Action optional: unknown MCACOD", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_UC_S) + ), + MCESEV( + SOME, "Action optional with lost events", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR, MCI_STATUS_OVER|MCI_UC_S) + ), + + MCESEV( + PANIC, "Overflowed uncorrected", + BITSET(MCI_STATUS_OVER|MCI_STATUS_UC) + ), + MCESEV( + PANIC, "Uncorrected in kernel", + BITSET(MCI_STATUS_UC), + KERNEL + ), + MCESEV( + UC, "Uncorrected", + BITSET(MCI_STATUS_UC) + ), + MCESEV( + SOME, "No match", + BITSET(0) + ) /* always matches. keep at end */ +}; + +#define mc_recoverable(mcg) (((mcg) & (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) == \ + (MCG_STATUS_RIPV|MCG_STATUS_EIPV)) + +static bool is_copy_from_user(struct pt_regs *regs) +{ + u8 insn_buf[MAX_INSN_SIZE]; + unsigned long addr; + struct insn insn; + int ret; + + if (!regs) + return false; + + if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip, MAX_INSN_SIZE)) + return false; + + ret = insn_decode_kernel(&insn, insn_buf); + if (ret < 0) + return false; + + switch (insn.opcode.value) { + /* MOV mem,reg */ + case 0x8A: case 0x8B: + /* MOVZ mem,reg */ + case 0xB60F: case 0xB70F: + addr = (unsigned long)insn_get_addr_ref(&insn, regs); + break; + /* REP MOVS */ + case 0xA4: case 0xA5: + addr = regs->si; + break; + default: + return false; + } + + if (fault_in_kernel_space(addr)) + return false; + + current->mce_vaddr = (void __user *)addr; + + return true; +} + +/* + * If mcgstatus indicated that ip/cs on the stack were + * no good, then "m->cs" will be zero and we will have + * to assume the worst case (IN_KERNEL) as we actually + * have no idea what we were executing when the machine + * check hit. + * If we do have a good "m->cs" (or a faked one in the + * case we were executing in VM86 mode) we can use it to + * distinguish an exception taken in user from from one + * taken in the kernel. + */ +static noinstr int error_context(struct mce *m, struct pt_regs *regs) +{ + int fixup_type; + bool copy_user; + + if ((m->cs & 3) == 3) + return IN_USER; + + if (!mc_recoverable(m->mcgstatus)) + return IN_KERNEL; + + /* Allow instrumentation around external facilities usage. */ + instrumentation_begin(); + fixup_type = ex_get_fixup_type(m->ip); + copy_user = is_copy_from_user(regs); + instrumentation_end(); + + switch (fixup_type) { + case EX_TYPE_UACCESS: + case EX_TYPE_COPY: + if (!copy_user) + return IN_KERNEL; + m->kflags |= MCE_IN_KERNEL_COPYIN; + fallthrough; + + case EX_TYPE_FAULT_MCE_SAFE: + case EX_TYPE_DEFAULT_MCE_SAFE: + m->kflags |= MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + + default: + return IN_KERNEL; + } +} + +/* See AMD PPR(s) section Machine Check Error Handling. */ +static noinstr int mce_severity_amd(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) +{ + char *panic_msg = NULL; + int ret; + + /* + * Default return value: Action required, the error must be handled + * immediately. + */ + ret = MCE_AR_SEVERITY; + + /* Processor Context Corrupt, no need to fumble too much, die! */ + if (m->status & MCI_STATUS_PCC) { + panic_msg = "Processor Context Corrupt"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (m->status & MCI_STATUS_DEFERRED) { + ret = MCE_DEFERRED_SEVERITY; + goto out; + } + + /* + * If the UC bit is not set, the system either corrected or deferred + * the error. No action will be required after logging the error. + */ + if (!(m->status & MCI_STATUS_UC)) { + ret = MCE_KEEP_SEVERITY; + goto out; + } + + /* + * On MCA overflow, without the MCA overflow recovery feature the + * system will not be able to recover, panic. + */ + if ((m->status & MCI_STATUS_OVER) && !mce_flags.overflow_recov) { + panic_msg = "Overflowed uncorrected error without MCA Overflow Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (!mce_flags.succor) { + panic_msg = "Uncorrected error without MCA Recovery"; + ret = MCE_PANIC_SEVERITY; + goto out; + } + + if (error_context(m, regs) == IN_KERNEL) { + panic_msg = "Uncorrected unrecoverable error in kernel context"; + ret = MCE_PANIC_SEVERITY; + } + +out: + if (msg && panic_msg) + *msg = panic_msg; + + return ret; +} + +static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) +{ + enum exception excp = (is_excp ? EXCP_CONTEXT : NO_EXCP); + enum context ctx = error_context(m, regs); + struct severity *s; + + for (s = severities;; s++) { + if ((m->status & s->mask) != s->result) + continue; + if ((m->mcgstatus & s->mcgmask) != s->mcgres) + continue; + if (s->ser == SER_REQUIRED && !mca_cfg.ser) + continue; + if (s->ser == NO_SER && mca_cfg.ser) + continue; + if (s->context && ctx != s->context) + continue; + if (s->excp && excp != s->excp) + continue; + if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model) + continue; + if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping) + continue; + if (s->bank_lo && (m->bank < s->bank_lo || m->bank > s->bank_hi)) + continue; + if (msg) + *msg = s->msg; + s->covered = 1; + + return s->sev; + } +} + +int noinstr mce_severity(struct mce *m, struct pt_regs *regs, char **msg, bool is_excp) +{ + if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || + boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) + return mce_severity_amd(m, regs, msg, is_excp); + else + return mce_severity_intel(m, regs, msg, is_excp); +} + +#ifdef CONFIG_DEBUG_FS +static void *s_start(struct seq_file *f, loff_t *pos) +{ + if (*pos >= ARRAY_SIZE(severities)) + return NULL; + return &severities[*pos]; +} + +static void *s_next(struct seq_file *f, void *data, loff_t *pos) +{ + if (++(*pos) >= ARRAY_SIZE(severities)) + return NULL; + return &severities[*pos]; +} + +static void s_stop(struct seq_file *f, void *data) +{ +} + +static int s_show(struct seq_file *f, void *data) +{ + struct severity *ser = data; + seq_printf(f, "%d\t%s\n", ser->covered, ser->msg); + return 0; +} + +static const struct seq_operations severities_seq_ops = { + .start = s_start, + .next = s_next, + .stop = s_stop, + .show = s_show, +}; + +static int severities_coverage_open(struct inode *inode, struct file *file) +{ + return seq_open(file, &severities_seq_ops); +} + +static ssize_t severities_coverage_write(struct file *file, + const char __user *ubuf, + size_t count, loff_t *ppos) +{ + int i; + for (i = 0; i < ARRAY_SIZE(severities); i++) + severities[i].covered = 0; + return count; +} + +static const struct file_operations severities_coverage_fops = { + .open = severities_coverage_open, + .release = seq_release, + .read = seq_read, + .write = severities_coverage_write, + .llseek = seq_lseek, +}; + +static int __init severities_debugfs_init(void) +{ + struct dentry *dmce; + + dmce = mce_get_debugfs_dir(); + + debugfs_create_file("severities-coverage", 0444, dmce, NULL, + &severities_coverage_fops); + return 0; +} +late_initcall(severities_debugfs_init); +#endif /* CONFIG_DEBUG_FS */ diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c new file mode 100644 index 0000000000..ef4e7bb5fd --- /dev/null +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -0,0 +1,31 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Common corrected MCE threshold handler code: + */ +#include <linux/interrupt.h> +#include <linux/kernel.h> + +#include <asm/irq_vectors.h> +#include <asm/traps.h> +#include <asm/apic.h> +#include <asm/mce.h> +#include <asm/trace/irq_vectors.h> + +#include "internal.h" + +static void default_threshold_interrupt(void) +{ + pr_err("Unexpected threshold interrupt at vector %x\n", + THRESHOLD_APIC_VECTOR); +} + +void (*mce_threshold_vector)(void) = default_threshold_interrupt; + +DEFINE_IDTENTRY_SYSVEC(sysvec_threshold) +{ + trace_threshold_apic_entry(THRESHOLD_APIC_VECTOR); + inc_irq_stat(irq_threshold_count); + mce_threshold_vector(); + trace_threshold_apic_exit(THRESHOLD_APIC_VECTOR); + apic_eoi(); +} diff --git a/arch/x86/kernel/cpu/mce/winchip.c b/arch/x86/kernel/cpu/mce/winchip.c new file mode 100644 index 0000000000..6c99f29419 --- /dev/null +++ b/arch/x86/kernel/cpu/mce/winchip.c @@ -0,0 +1,41 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * IDT Winchip 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/hardirq.h> + +#include <asm/processor.h> +#include <asm/traps.h> +#include <asm/tlbflush.h> +#include <asm/mce.h> +#include <asm/msr.h> + +#include "internal.h" + +/* Machine check handler for WinChip C6: */ +noinstr void winchip_machine_check(struct pt_regs *regs) +{ + instrumentation_begin(); + pr_emerg("CPU0: Machine Check Exception.\n"); + add_taint(TAINT_MACHINE_CHECK, LOCKDEP_NOW_UNRELIABLE); + instrumentation_end(); +} + +/* Set up machine check reporting on the Winchip C6 series */ +void winchip_mcheck_init(struct cpuinfo_x86 *c) +{ + u32 lo, hi; + + 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); + + cr4_set_bits(X86_CR4_MCE); + + pr_info("Winchip machine check reporting enabled on CPU#0.\n"); +} |