diff options
Diffstat (limited to 'arch/x86/kernel/cpu/mce')
| -rw-r--r-- | arch/x86/kernel/cpu/mce/amd.c | 167 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/apei.c | 119 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/core.c | 522 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/dev-mcelog.c | 14 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/genpool.c | 75 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/inject.c | 16 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/intel.c | 32 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/internal.h | 8 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/severity.c | 38 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mce/threshold.c | 2 |
10 files changed, 531 insertions, 462 deletions
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c index 9a0133ef7e20..1075a90141da 100644 --- a/arch/x86/kernel/cpu/mce/amd.c +++ b/arch/x86/kernel/cpu/mce/amd.c @@ -4,8 +4,6 @@ * * 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> @@ -20,7 +18,6 @@ #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> @@ -221,6 +218,32 @@ static const struct smca_hwid smca_hwid_mcatypes[] = { #define MAX_MCATYPE_NAME_LEN 30 static char buf_mcatype[MAX_MCATYPE_NAME_LEN]; +struct threshold_block { + /* This block's number within its bank. */ + unsigned int block; + /* MCA bank number that contains this block. */ + unsigned int bank; + /* CPU which controls this block's MCA bank. */ + unsigned int cpu; + /* MCA_MISC MSR address for this block. */ + u32 address; + /* Enable/Disable APIC interrupt. */ + bool interrupt_enable; + /* Bank can generate an interrupt. */ + bool interrupt_capable; + /* Value upon which threshold interrupt is generated. */ + u16 threshold_limit; + /* sysfs object */ + struct kobject kobj; + /* List of threshold blocks within this block's MCA bank. */ + struct list_head miscj; +}; + +struct threshold_bank { + struct kobject *kobj; + struct threshold_block *blocks; +}; + static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); /* @@ -333,19 +356,6 @@ struct thresh_restart { 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) { @@ -381,7 +391,7 @@ static bool lvt_interrupt_supported(unsigned int bank, u32 msr_high_bits) return msr_high_bits & BIT(28); } -static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) +static bool lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) { int msr = (hi & MASK_LVTOFF_HI) >> 20; @@ -389,7 +399,7 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) 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; + return false; } if (apic != msr) { @@ -399,15 +409,15 @@ static int lvt_off_valid(struct threshold_block *b, int apic, u32 lo, u32 hi) * was set is reserved. Return early here: */ if (mce_flags.smca) - return 0; + return false; 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 false; } - return 1; + return true; }; /* Reprogram MCx_MISC MSR behind this threshold bank. */ @@ -778,29 +788,33 @@ bool amd_mce_usable_address(struct mce *m) static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc) { - struct mce m; + struct mce_hw_err err; + struct mce *m = &err.m; - mce_setup(&m); + mce_prep_record(&err); - m.status = status; - m.misc = misc; - m.bank = bank; - m.tsc = rdtsc(); + m->status = status; + m->misc = misc; + m->bank = bank; + m->tsc = rdtsc(); - if (m.status & MCI_STATUS_ADDRV) { - m.addr = addr; + if (m->status & MCI_STATUS_ADDRV) { + m->addr = addr; - smca_extract_err_addr(&m); + smca_extract_err_addr(m); } if (mce_flags.smca) { - rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m.ipid); + rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid); - if (m.status & MCI_STATUS_SYNDV) - rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m.synd); + if (m->status & MCI_STATUS_SYNDV) { + rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd); + rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1); + rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2); + } } - mce_log(&m); + mce_log(&err); } DEFINE_IDTENTRY_SYSVEC(sysvec_deferred_error) @@ -1194,35 +1208,10 @@ out_free: 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; @@ -1230,26 +1219,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, if (!dev) return -ENODEV; - if (is_shared_bank(bank)) { - nb = node_to_amd_nb(topology_amd_node_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; @@ -1263,17 +1232,6 @@ static int threshold_create_bank(struct threshold_bank **bp, unsigned int cpu, 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; @@ -1306,40 +1264,11 @@ static void deallocate_threshold_blocks(struct threshold_bank *bank) 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_amd_node_id(smp_processor_id())); - nb->bank4 = NULL; - } - -out_dealloc: deallocate_threshold_blocks(bank); out_free: diff --git a/arch/x86/kernel/cpu/mce/apei.c b/arch/x86/kernel/cpu/mce/apei.c index 7f7309ff67d0..0a89947e47bc 100644 --- a/arch/x86/kernel/cpu/mce/apei.c +++ b/arch/x86/kernel/cpu/mce/apei.c @@ -28,7 +28,8 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) { - struct mce m; + struct mce_hw_err err; + struct mce *m; int lsb; if (!(mem_err->validation_bits & CPER_MEM_VALID_PA)) @@ -44,30 +45,33 @@ void apei_mce_report_mem_error(int severity, struct cper_sec_mem_err *mem_err) else lsb = PAGE_SHIFT; - mce_setup(&m); - m.bank = -1; + mce_prep_record(&err); + m = &err.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; + 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; + m->status |= MCI_STATUS_UC; if (severity >= GHES_SEV_PANIC) { - m.status |= MCI_STATUS_PCC; - m.tsc = rdtsc(); + m->status |= MCI_STATUS_PCC; + m->tsc = rdtsc(); } - m.addr = mem_err->physical_addr; - mce_log(&m); + m->addr = mem_err->physical_addr; + mce_log(&err); } 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; + unsigned int cpu, num_regs; + bool apicid_found = false; + struct mce_hw_err err; + struct mce *m; if (!boot_cpu_has(X86_FEATURE_SMCA)) return -EINVAL; @@ -85,41 +89,86 @@ int apei_smca_report_x86_error(struct cper_ia_proc_ctx *ctx_info, u64 lapic_id) 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. + * Sanity-check registers array size. */ - if (ctx_info->reg_arr_size < 48) + num_regs = ctx_info->reg_arr_size >> 3; + if (!num_regs) return -EINVAL; - mce_setup(&m); - - m.extcpu = -1; - m.socketid = -1; - for_each_possible_cpu(cpu) { if (cpu_data(cpu).topo.initial_apicid == lapic_id) { - m.extcpu = cpu; - m.socketid = cpu_data(m.extcpu).topo.pkg_id; + apicid_found = true; 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); + if (!apicid_found) + return -EINVAL; + + m = &err.m; + memset(&err, 0, sizeof(struct mce_hw_err)); + mce_prep_record_common(m); + mce_prep_record_per_cpu(cpu, m); + + m->bank = (ctx_info->msr_addr >> 4) & 0xFF; + + /* + * The SMCA register layout is fixed and includes 16 registers. + * The end of the array may be variable, but the beginning is known. + * Cap the number of registers to expected max (15). + */ + if (num_regs > 15) + num_regs = 15; + + switch (num_regs) { + /* MCA_SYND2 */ + case 15: + err.vendor.amd.synd2 = *(i_mce + 14); + fallthrough; + /* MCA_SYND1 */ + case 14: + err.vendor.amd.synd1 = *(i_mce + 13); + fallthrough; + /* MCA_MISC4 */ + case 13: + /* MCA_MISC3 */ + case 12: + /* MCA_MISC2 */ + case 11: + /* MCA_MISC1 */ + case 10: + /* MCA_DEADDR */ + case 9: + /* MCA_DESTAT */ + case 8: + /* reserved */ + case 7: + /* MCA_SYND */ + case 6: + m->synd = *(i_mce + 5); + fallthrough; + /* MCA_IPID */ + case 5: + m->ipid = *(i_mce + 4); + fallthrough; + /* MCA_CONFIG */ + case 4: + /* MCA_MISC0 */ + case 3: + m->misc = *(i_mce + 2); + fallthrough; + /* MCA_ADDR */ + case 2: + m->addr = *(i_mce + 1); + fallthrough; + /* MCA_STATUS */ + case 1: + m->status = *i_mce; + } - mce_log(&m); + mce_log(&err); return 0; } diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c index b5cc557cfc37..f6fd71b64b66 100644 --- a/arch/x86/kernel/cpu/mce/core.c +++ b/arch/x86/kernel/cpu/mce/core.c @@ -47,7 +47,7 @@ #include <linux/kexec.h> #include <asm/fred.h> -#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #include <asm/processor.h> #include <asm/traps.h> #include <asm/tlbflush.h> @@ -88,7 +88,7 @@ struct mca_config mca_cfg __read_mostly = { .monarch_timeout = -1 }; -static DEFINE_PER_CPU(struct mce, mces_seen); +static DEFINE_PER_CPU(struct mce_hw_err, hw_errs_seen); static unsigned long mce_need_notify; /* @@ -117,28 +117,41 @@ static struct irq_work mce_irq_work; */ BLOCKING_NOTIFIER_HEAD(x86_mce_decoder_chain); -/* Do initial initialization of a struct mce */ -void mce_setup(struct mce *m) +void mce_prep_record_common(struct mce *m) { - memset(m, 0, sizeof(struct mce)); - m->cpu = m->extcpu = smp_processor_id(); + m->cpuid = cpuid_eax(1); + m->cpuvendor = boot_cpu_data.x86_vendor; + m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); /* 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).topo.pkg_id; - m->apicid = cpu_data(m->extcpu).topo.initial_apicid; - m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP); - m->ppin = cpu_data(m->extcpu).ppin; - m->microcode = boot_cpu_data.microcode; + m->time = __ktime_get_real_seconds(); +} + +void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m) +{ + m->cpu = cpu; + m->extcpu = cpu; + m->apicid = cpu_data(cpu).topo.initial_apicid; + m->microcode = cpu_data(cpu).microcode; + m->ppin = topology_ppin(cpu); + m->socketid = topology_physical_package_id(cpu); +} + +/* Do initial initialization of struct mce_hw_err */ +void mce_prep_record(struct mce_hw_err *err) +{ + struct mce *m = &err->m; + + memset(err, 0, sizeof(struct mce_hw_err)); + mce_prep_record_common(m); + mce_prep_record_per_cpu(smp_processor_id(), m); } DEFINE_PER_CPU(struct mce, injectm); EXPORT_PER_CPU_SYMBOL_GPL(injectm); -void mce_log(struct mce *m) +void mce_log(struct mce_hw_err *err) { - if (!mce_gen_pool_add(m)) + if (mce_gen_pool_add(err)) irq_work_queue(&mce_irq_work); } EXPORT_SYMBOL_GPL(mce_log); @@ -159,8 +172,10 @@ void mce_unregister_decode_chain(struct notifier_block *nb) } EXPORT_SYMBOL_GPL(mce_unregister_decode_chain); -static void __print_mce(struct mce *m) +static void __print_mce(struct mce_hw_err *err) { + struct mce *m = &err->m; + pr_emerg(HW_ERR "CPU %d: Machine Check%s: %Lx Bank %d: %016Lx\n", m->extcpu, (m->mcgstatus & MCG_STATUS_MCIP ? " Exception" : ""), @@ -187,6 +202,10 @@ static void __print_mce(struct mce *m) if (mce_flags.smca) { if (m->synd) pr_cont("SYND %llx ", m->synd); + if (err->vendor.amd.synd1) + pr_cont("SYND1 %llx ", err->vendor.amd.synd1); + if (err->vendor.amd.synd2) + pr_cont("SYND2 %llx ", err->vendor.amd.synd2); if (m->ipid) pr_cont("IPID %llx ", m->ipid); } @@ -202,9 +221,11 @@ static void __print_mce(struct mce *m) m->microcode); } -static void print_mce(struct mce *m) +static void print_mce(struct mce_hw_err *err) { - __print_mce(m); + struct mce *m = &err->m; + + __print_mce(err); if (m->cpuvendor != X86_VENDOR_AMD && m->cpuvendor != X86_VENDOR_HYGON) pr_emerg_ratelimited(HW_ERR "Run the above through 'mcelog --ascii'\n"); @@ -239,7 +260,7 @@ static const char *mce_dump_aux_info(struct mce *m) return NULL; } -static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) +static noinstr void mce_panic(const char *msg, struct mce_hw_err *final, char *exp) { struct llist_node *pending; struct mce_evt_llist *l; @@ -270,20 +291,22 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) 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; + struct mce_hw_err *err = &l->err; + struct mce *m = &err->m; if (!(m->status & MCI_STATUS_UC)) { - print_mce(m); + print_mce(err); 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; + struct mce_hw_err *err = &l->err; + struct mce *m = &err->m; if (!(m->status & MCI_STATUS_UC)) continue; - if (!final || mce_cmp(m, final)) { - print_mce(m); + if (!final || mce_cmp(m, &final->m)) { + print_mce(err); if (!apei_err) apei_err = apei_write_mce(m); } @@ -291,12 +314,12 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) if (final) { print_mce(final); if (!apei_err) - apei_err = apei_write_mce(final); + apei_err = apei_write_mce(&final->m); } if (exp) pr_emerg(HW_ERR "Machine check: %s\n", exp); - memmsg = mce_dump_aux_info(final); + memmsg = mce_dump_aux_info(&final->m); if (memmsg) pr_emerg(HW_ERR "Machine check: %s\n", memmsg); @@ -311,9 +334,9 @@ static noinstr void mce_panic(const char *msg, struct mce *final, char *exp) * panic. */ if (kexec_crash_loaded()) { - if (final && (final->status & MCI_STATUS_ADDRV)) { + if (final && (final->m.status & MCI_STATUS_ADDRV)) { struct page *p; - p = pfn_to_online_page(final->addr >> PAGE_SHIFT); + p = pfn_to_online_page(final->m.addr >> PAGE_SHIFT); if (p) SetPageHWPoison(p); } @@ -433,16 +456,18 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v) * 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) +static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs) { + struct mce *m; /* - * Enable instrumentation around mce_setup() which calls external + * Enable instrumentation around mce_prep_record() which calls external * facilities. */ instrumentation_begin(); - mce_setup(m); + mce_prep_record(err); instrumentation_end(); + m = &err->m; m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS); if (regs) { /* @@ -467,10 +492,10 @@ static noinstr void mce_gather_info(struct mce *m, struct pt_regs *regs) } } -int mce_available(struct cpuinfo_x86 *c) +bool mce_available(struct cpuinfo_x86 *c) { if (mca_cfg.disabled) - return 0; + return false; return cpu_has(c, X86_FEATURE_MCE) && cpu_has(c, X86_FEATURE_MCA); } @@ -559,16 +584,38 @@ bool mce_is_correctable(struct mce *m) } EXPORT_SYMBOL_GPL(mce_is_correctable); +/* + * Notify the user(s) about new machine check events. + * Can be called from interrupt context, but not from machine check/NMI + * context. + */ +static bool 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 true; + } + + return false; +} + static int mce_early_notifier(struct notifier_block *nb, unsigned long val, void *data) { - struct mce *m = (struct mce *)data; + struct mce_hw_err *err = to_mce_hw_err(data); - if (!m) + if (!err) return NOTIFY_DONE; /* Emit the trace record: */ - trace_mce_record(m); + trace_mce_record(err); set_bit(0, &mce_need_notify); @@ -612,13 +659,13 @@ static struct notifier_block mce_uc_nb = { static int mce_default_notifier(struct notifier_block *nb, unsigned long val, void *data) { - struct mce *m = (struct mce *)data; + struct mce_hw_err *err = to_mce_hw_err(data); - if (!m) + if (!err) return NOTIFY_DONE; - if (mca_cfg.print_all || !m->kflags) - __print_mce(m); + if (mca_cfg.print_all || !(err->m.kflags)) + __print_mce(err); return NOTIFY_DONE; } @@ -632,8 +679,10 @@ static struct notifier_block mce_default_nb = { /* * Read ADDR and MISC registers. */ -static noinstr void mce_read_aux(struct mce *m, int i) +static noinstr void mce_read_aux(struct mce_hw_err *err, int i) { + struct mce *m = &err->m; + if (m->status & MCI_STATUS_MISCV) m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC)); @@ -655,8 +704,11 @@ static noinstr void mce_read_aux(struct mce *m, int i) if (mce_flags.smca) { m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i)); - if (m->status & MCI_STATUS_SYNDV) + if (m->status & MCI_STATUS_SYNDV) { m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i)); + err->vendor.amd.synd1 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(i)); + err->vendor.amd.synd2 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(i)); + } } } @@ -677,30 +729,31 @@ DEFINE_PER_CPU(unsigned, mce_poll_count); * 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) +void 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; + struct mce_hw_err err; + struct mce *m; int i; this_cpu_inc(mce_poll_count); - mce_gather_info(&m, NULL); + mce_gather_info(&err, NULL); + m = &err.m; if (flags & MCP_TIMESTAMP) - m.tsc = rdtsc(); + 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; + m->misc = 0; + m->addr = 0; + m->bank = i; barrier(); - m.status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); + m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS)); /* * Update storm tracking here, before checking for the @@ -710,17 +763,17 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * storm status. */ if (!mca_cfg.cmci_disabled) - mce_track_storm(&m); + mce_track_storm(m); /* If this entry is not valid, ignore it */ - if (!(m.status & MCI_STATUS_VAL)) + 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)) + if ((flags & MCP_UC) || !(m->status & MCI_STATUS_UC)) goto log_it; /* @@ -730,20 +783,20 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) * everything else. */ if (!mca_cfg.ser) { - if (m.status & MCI_STATUS_UC) + if (m->status & MCI_STATUS_UC) continue; goto log_it; } /* Log "not enabled" (speculative) errors */ - if (!(m.status & MCI_STATUS_EN)) + 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)) + if (!(m->status & MCI_STATUS_PCC) && !(m->status & MCI_STATUS_S)) goto log_it; /* @@ -754,25 +807,23 @@ bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b) 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); + mce_read_aux(&err, 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)) + if (mca_cfg.dont_log_ce && !mce_usable_address(m)) goto clear_it; if (flags & MCP_QUEUE_LOG) - mce_gen_pool_add(&m); + mce_gen_pool_add(&err); else - mce_log(&m); + mce_log(&err); clear_it: /* @@ -787,8 +838,6 @@ clear_it: */ sync_core(); - - return error_seen; } EXPORT_SYMBOL_GPL(machine_check_poll); @@ -898,9 +947,10 @@ static __always_inline void quirk_zen_ifu(int bank, struct mce *m, struct pt_reg * 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, +static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, unsigned long *validp, struct pt_regs *regs) { + struct mce *m = &err->m; char *tmp = *msg; int i; @@ -918,7 +968,7 @@ static __always_inline int mce_no_way_out(struct mce *m, char **msg, unsigned lo m->bank = i; if (mce_severity(m, regs, &tmp, true) >= MCE_PANIC_SEVERITY) { - mce_read_aux(m, i); + mce_read_aux(err, i); *msg = tmp; return 1; } @@ -1009,10 +1059,11 @@ out: */ static void mce_reign(void) { - int cpu; + struct mce_hw_err *err = NULL; struct mce *m = NULL; int global_worst = 0; char *msg = NULL; + int cpu; /* * This CPU is the Monarch and the other CPUs have run @@ -1020,11 +1071,13 @@ static void mce_reign(void) * Grade the severity of the errors of all the CPUs. */ for_each_possible_cpu(cpu) { - struct mce *mtmp = &per_cpu(mces_seen, cpu); + struct mce_hw_err *etmp = &per_cpu(hw_errs_seen, cpu); + struct mce *mtmp = &etmp->m; if (mtmp->severity > global_worst) { global_worst = mtmp->severity; - m = &per_cpu(mces_seen, cpu); + err = &per_cpu(hw_errs_seen, cpu); + m = &err->m; } } @@ -1036,7 +1089,7 @@ static void mce_reign(void) 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); + mce_panic("Fatal machine check", err, msg); } /* @@ -1053,11 +1106,11 @@ static void mce_reign(void) mce_panic("Fatal machine check from unknown source", NULL, NULL); /* - * Now clear all the mces_seen so that they don't reappear on + * Now clear all the hw_errs_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)); + memset(&per_cpu(hw_errs_seen, cpu), 0, sizeof(struct mce_hw_err)); } static atomic_t global_nwo; @@ -1261,13 +1314,14 @@ static noinstr bool mce_check_crashing_cpu(void) } 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) +__mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs, + struct mce_hw_err *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; + struct mce *m = &err->m; for (i = 0; i < this_cpu_read(mce_num_banks); i++) { arch___clear_bit(i, toclear); @@ -1312,7 +1366,7 @@ __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, if (severity == MCE_NO_SEVERITY) continue; - mce_read_aux(m, i); + mce_read_aux(err, i); /* assuming valid severity level != 0 */ m->severity = severity; @@ -1322,17 +1376,17 @@ __mc_scan_banks(struct mce *m, struct pt_regs *regs, struct mce *final, * done in #MC context, where instrumentation is disabled. */ instrumentation_begin(); - mce_log(m); + mce_log(err); instrumentation_end(); if (severity > *worst) { - *final = *m; + *final = *err; *worst = severity; } } /* mce_clear_state will clear *final, save locally for use later */ - *m = *final; + *err = *final; return taint; } @@ -1392,9 +1446,10 @@ static void kill_me_never(struct callback_head *cb) set_mce_nospec(pfn); } -static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callback_head *)) +static void queue_task_work(struct mce_hw_err *err, char *msg, void (*func)(struct callback_head *)) { int count = ++current->mce_count; + struct mce *m = &err->m; /* First call, save all the details */ if (count == 1) { @@ -1407,11 +1462,12 @@ static void queue_task_work(struct mce *m, char *msg, void (*func)(struct callba /* 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); + mce_panic("Too many consecutive machine checks while accessing user data", + err, 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); + mce_panic("Consecutive machine checks to different user pages", err, msg); /* Do not call task_work_add() more than once */ if (count > 1) @@ -1460,8 +1516,10 @@ 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; + struct mce_hw_err *final; + struct mce_hw_err err; char *msg = NULL; + struct mce *m; if (unlikely(mce_flags.p5)) return pentium_machine_check(regs); @@ -1499,13 +1557,14 @@ noinstr void do_machine_check(struct pt_regs *regs) this_cpu_inc(mce_exception_count); - mce_gather_info(&m, regs); - m.tsc = rdtsc(); + mce_gather_info(&err, regs); + m = &err.m; + m->tsc = rdtsc(); - final = this_cpu_ptr(&mces_seen); - *final = m; + final = this_cpu_ptr(&hw_errs_seen); + *final = err; - no_way_out = mce_no_way_out(&m, &msg, valid_banks, regs); + no_way_out = mce_no_way_out(&err, &msg, valid_banks, regs); barrier(); @@ -1514,15 +1573,15 @@ noinstr void do_machine_check(struct pt_regs *regs) * 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)) + 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; + 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. @@ -1533,12 +1592,12 @@ noinstr void do_machine_check(struct pt_regs *regs) */ if (lmce) { if (no_way_out) - mce_panic("Fatal local machine check", &m, msg); + mce_panic("Fatal local machine check", &err, msg); } else { order = mce_start(&no_way_out); } - taint = __mc_scan_banks(&m, regs, final, toclear, valid_banks, no_way_out, &worst); + taint = __mc_scan_banks(&err, regs, final, toclear, valid_banks, no_way_out, &worst); if (!no_way_out) mce_clear_state(toclear); @@ -1553,7 +1612,7 @@ noinstr void do_machine_check(struct pt_regs *regs) no_way_out = worst >= MCE_PANIC_SEVERITY; if (no_way_out) - mce_panic("Fatal machine check on current CPU", &m, msg); + mce_panic("Fatal machine check on current CPU", &err, msg); } } else { /* @@ -1565,8 +1624,8 @@ noinstr void do_machine_check(struct pt_regs *regs) * 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); + mce_severity(m, regs, &msg, true); + mce_panic("Local fatal machine check!", &err, msg); } } @@ -1584,15 +1643,33 @@ noinstr void do_machine_check(struct pt_regs *regs) goto out; /* Fault was in user mode and we need to take some action */ - if ((m.cs & 3) == 3) { + 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); + if (!mce_usable_address(m)) + queue_task_work(&err, msg, kill_me_now); else - queue_task_work(&m, msg, kill_me_maybe); + queue_task_work(&err, msg, kill_me_maybe); + } else if (m->mcgstatus & MCG_STATUS_SEAM_NR) { + /* + * Saved RIP on stack makes it look like the machine check + * was taken in the kernel on the instruction following + * the entry to SEAM mode. But MCG_STATUS_SEAM_NR indicates + * that the machine check was taken inside SEAM non-root + * mode. CPU core has already marked that guest as dead. + * It is OK for the kernel to resume execution at the + * apparent point of the machine check as the fault did + * not occur there. Mark the page as poisoned so it won't + * be added to free list when the guest is terminated. + */ + if (mce_usable_address(m)) { + struct page *p = pfn_to_online_page(m->addr >> PAGE_SHIFT); + + if (p) + SetPageHWPoison(p); + } } else { /* * Handle an MCE which has happened in kernel space but from @@ -1603,13 +1680,13 @@ noinstr void do_machine_check(struct pt_regs *regs) * corresponding exception handler which would do that is the * proper one. */ - if (m.kflags & MCE_IN_KERNEL_RECOV) { + if (m->kflags & MCE_IN_KERNEL_RECOV) { if (!fixup_exception(regs, X86_TRAP_MC, 0, 0)) - mce_panic("Failed kernel mode recovery", &m, msg); + mce_panic("Failed kernel mode recovery", &err, msg); } - if (m.kflags & MCE_IN_KERNEL_COPYIN) - queue_task_work(&m, msg, kill_me_never); + if (m->kflags & MCE_IN_KERNEL_COPYIN) + queue_task_work(&err, msg, kill_me_never); } out: @@ -1709,36 +1786,14 @@ void mce_timer_kick(bool storm) __this_cpu_write(mce_next_interval, check_interval * HZ); } -/* Must not be called in IRQ context where del_timer_sync() can deadlock */ +/* Must not be called in IRQ context where timer_delete_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; + timer_delete_sync(&per_cpu(mce_timer, cpu)); } -EXPORT_SYMBOL_GPL(mce_notify_irq); static void __mcheck_cpu_mce_banks_init(void) { @@ -1855,101 +1910,120 @@ static void __mcheck_cpu_check_banks(void) } } -/* Add per CPU specific workarounds here */ -static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +static void apply_quirks_amd(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; - } + if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) { /* - * Various K7s with broken bank 0 around. Always disable - * by default. + * disable GART TBL walk error reporting, which + * trips off incorrectly with the IOMMU & 3ware + * & Cerberus: */ - if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].ctl = 0; + clear_bit(10, (unsigned long *)&mce_banks[4].ctl); + } + if (c->x86 < 0x11 && mca_cfg.bootlog < 0) { /* - * overflow_recov is supported for F15h Models 00h-0fh - * even though we don't have a CPUID bit for it. + * Lots of broken BIOS around that don't clear them + * by default and leave crap in there. Don't log: */ - if (c->x86 == 0x15 && c->x86_model <= 0xf) - mce_flags.overflow_recov = 1; + mca_cfg.bootlog = 0; + } - if (c->x86 >= 0x17 && c->x86 <= 0x1A) - mce_flags.zen_ifu_quirk = 1; + /* + * Various K7s with broken bank 0 around. Always disable + * by default. + */ + if (c->x86 == 6 && this_cpu_read(mce_num_banks)) + 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_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 >= 0x17 && c->x86 <= 0x1A) + mce_flags.zen_ifu_quirk = 1; +} - if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0) - mce_banks[0].init = false; +static void apply_quirks_intel(struct cpuinfo_x86 *c) +{ + struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array); - /* - * 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; + /* Older CPUs (prior to family 6) don't need quirks. */ + if (c->x86_vfm < INTEL_PENTIUM_PRO) + return; - /* - * 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; + /* + * 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_vfm < INTEL_NEHALEM_EP && this_cpu_read(mce_num_banks)) + mce_banks[0].init = false; + + /* + * All newer Intel systems support MCE broadcasting. Enable + * synchronization with a one second timeout. + */ + if (c->x86_vfm >= INTEL_CORE_YONAH && mca_cfg.monarch_timeout < 0) + mca_cfg.monarch_timeout = USEC_PER_SEC; - if (c->x86 == 6 && c->x86_model == 45) - mce_flags.snb_ifu_quirk = 1; + /* + * There are also broken BIOSes on some Pentium M and + * earlier systems: + */ + if (c->x86_vfm < INTEL_CORE_YONAH && mca_cfg.bootlog < 0) + mca_cfg.bootlog = 0; - /* - * 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_vfm == INTEL_SANDYBRIDGE_X) + mce_flags.snb_ifu_quirk = 1; + + /* + * Skylake, Cascacde Lake and Cooper Lake require a quirk on + * rep movs. + */ + if (c->x86_vfm == INTEL_SKYLAKE_X) + mce_flags.skx_repmov_quirk = 1; +} + +static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c) +{ + /* + * 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 (mca_cfg.monarch_timeout < 0) + mca_cfg.monarch_timeout = USEC_PER_SEC; } +} - 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; - } +/* Add per CPU specific workarounds here */ +static bool __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) +{ + struct mca_config *cfg = &mca_cfg; + + switch (c->x86_vendor) { + case X86_VENDOR_UNKNOWN: + pr_info("unknown CPU type - not enabling MCE support\n"); + return false; + case X86_VENDOR_AMD: + apply_quirks_amd(c); + break; + case X86_VENDOR_INTEL: + apply_quirks_intel(c); + break; + case X86_VENDOR_ZHAOXIN: + apply_quirks_zhaoxin(c); + break; } if (cfg->monarch_timeout < 0) @@ -1957,28 +2031,28 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c) if (cfg->bootlog != 0) cfg->panic_timeout = 30; - return 0; + return true; } -static int __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) +static bool __mcheck_cpu_ancient_init(struct cpuinfo_x86 *c) { if (c->x86 != 5) - return 0; + return false; switch (c->x86_vendor) { case X86_VENDOR_INTEL: intel_p5_mcheck_init(c); mce_flags.p5 = 1; - return 1; + return true; case X86_VENDOR_CENTAUR: winchip_mcheck_init(c); mce_flags.winchip = 1; - return 1; + return true; default: - return 0; + return false; } - return 0; + return false; } /* @@ -2044,13 +2118,9 @@ static void __mcheck_cpu_init_vendor(struct cpuinfo_x86 *c) mce_intel_feature_init(c); break; - case X86_VENDOR_AMD: { - mce_amd_feature_init(c); - break; - } - + case X86_VENDOR_AMD: case X86_VENDOR_HYGON: - mce_hygon_feature_init(c); + mce_amd_feature_init(c); break; case X86_VENDOR_CENTAUR: @@ -2224,12 +2294,12 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c) __mcheck_cpu_cap_init(); - if (__mcheck_cpu_apply_quirks(c) < 0) { + if (!__mcheck_cpu_apply_quirks(c)) { mca_cfg.disabled = 1; return; } - if (mce_gen_pool_init()) { + if (!mce_gen_pool_init()) { mca_cfg.disabled = 1; pr_emerg("Couldn't allocate MCE records pool!\n"); return; @@ -2500,12 +2570,14 @@ static ssize_t set_bank(struct device *s, struct device_attribute *attr, return -EINVAL; b = &per_cpu(mce_banks_array, s->id)[bank]; - if (!b->init) return -ENODEV; b->ctl = new; + + mutex_lock(&mce_sysfs_mutex); mce_restart(); + mutex_unlock(&mce_sysfs_mutex); return size; } @@ -2748,7 +2820,7 @@ 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); + timer_delete_sync(t); mce_threshold_remove_device(cpu); mce_device_remove(cpu); return 0; diff --git a/arch/x86/kernel/cpu/mce/dev-mcelog.c b/arch/x86/kernel/cpu/mce/dev-mcelog.c index a05ac0716ecf..8d023239ce18 100644 --- a/arch/x86/kernel/cpu/mce/dev-mcelog.c +++ b/arch/x86/kernel/cpu/mce/dev-mcelog.c @@ -264,15 +264,8 @@ static long mce_chrdev_ioctl(struct file *f, unsigned int cmd, 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); - } + case MCE_GETCLEAR_FLAGS: + return put_user(xchg(&mcelog->flags, 0), p); default: return -ENOTTY; } @@ -314,7 +307,7 @@ static ssize_t mce_chrdev_write(struct file *filp, const char __user *ubuf, /* * Need to give user space some time to set everything up, - * so do it a jiffie or two later everywhere. + * so do it a jiffy or two later everywhere. */ schedule_timeout(2); @@ -331,7 +324,6 @@ static const struct file_operations mce_chrdev_ops = { .poll = mce_chrdev_poll, .unlocked_ioctl = mce_chrdev_ioctl, .compat_ioctl = compat_ptr_ioctl, - .llseek = no_llseek, }; static struct miscdevice mce_chrdev_device = { diff --git a/arch/x86/kernel/cpu/mce/genpool.c b/arch/x86/kernel/cpu/mce/genpool.c index fbe8b61c3413..3ca9c007a666 100644 --- a/arch/x86/kernel/cpu/mce/genpool.c +++ b/arch/x86/kernel/cpu/mce/genpool.c @@ -16,14 +16,14 @@ * 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). + * MCE events are rare, so a fixed size memory pool should be enough. + * Allocate on a sliding scale based on number of CPUs. */ -#define MCE_POOLSZ (2 * PAGE_SIZE) +#define MCE_MIN_ENTRIES 80 +#define MCE_PER_CPU 2 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 @@ -31,15 +31,15 @@ static char gen_pool_buf[MCE_POOLSZ]; */ static bool is_duplicate_mce_record(struct mce_evt_llist *t, struct mce_evt_llist *l) { + struct mce_hw_err *err1, *err2; struct mce_evt_llist *node; - struct mce *m1, *m2; - m1 = &t->mce; + err1 = &t->err; llist_for_each_entry(node, &l->llnode, llnode) { - m2 = &node->mce; + err2 = &node->err; - if (!mce_cmp(m1, m2)) + if (!mce_cmp(&err1->m, &err2->m)) return true; } return false; @@ -73,8 +73,8 @@ struct llist_node *mce_gen_pool_prepare_records(void) void mce_gen_pool_process(struct work_struct *__unused) { - struct llist_node *head; struct mce_evt_llist *node, *tmp; + struct llist_node *head; struct mce *mce; head = llist_del_all(&mce_event_llist); @@ -83,7 +83,7 @@ void mce_gen_pool_process(struct work_struct *__unused) head = llist_reverse_order(head); llist_for_each_entry_safe(node, tmp, head, llnode) { - mce = &node->mce; + mce = &node->err.m; blocking_notifier_call_chain(&x86_mce_decoder_chain, 0, mce); gen_pool_free(mce_evt_pool, (unsigned long)node, sizeof(*node)); } @@ -94,54 +94,63 @@ bool mce_gen_pool_empty(void) return llist_empty(&mce_event_llist); } -int mce_gen_pool_add(struct mce *mce) +bool mce_gen_pool_add(struct mce_hw_err *err) { struct mce_evt_llist *node; - if (filter_mce(mce)) - return -EINVAL; + if (filter_mce(&err->m)) + return false; if (!mce_evt_pool) - return -EINVAL; + return false; node = (void *)gen_pool_alloc(mce_evt_pool, sizeof(*node)); if (!node) { pr_warn_ratelimited("MCE records pool full!\n"); - return -ENOMEM; + return false; } - memcpy(&node->mce, mce, sizeof(*mce)); + memcpy(&node->err, err, sizeof(*err)); llist_add(&node->llnode, &mce_event_llist); - return 0; + return true; } -static int mce_gen_pool_create(void) +static bool 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; + int mce_numrecords, mce_poolsz, order; + struct gen_pool *gpool; + void *mce_pool; + + order = order_base_2(sizeof(struct mce_evt_llist)); + gpool = gen_pool_create(order, -1); + if (!gpool) + return false; + + mce_numrecords = max(MCE_MIN_ENTRIES, num_possible_cpus() * MCE_PER_CPU); + mce_poolsz = mce_numrecords * (1 << order); + mce_pool = kmalloc(mce_poolsz, GFP_KERNEL); + if (!mce_pool) { + gen_pool_destroy(gpool); + return false; + } - ret = gen_pool_add(tmpp, (unsigned long)gen_pool_buf, MCE_POOLSZ, -1); - if (ret) { - gen_pool_destroy(tmpp); - goto out; + if (gen_pool_add(gpool, (unsigned long)mce_pool, mce_poolsz, -1)) { + gen_pool_destroy(gpool); + kfree(mce_pool); + return false; } - mce_evt_pool = tmpp; + mce_evt_pool = gpool; -out: - return ret; + return true; } -int mce_gen_pool_init(void) +bool mce_gen_pool_init(void) { /* Just init mce_gen_pool once. */ if (mce_evt_pool) - return 0; + return true; return mce_gen_pool_create(); } diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c index 94953d749475..06e3cf7229ce 100644 --- a/arch/x86/kernel/cpu/mce/inject.c +++ b/arch/x86/kernel/cpu/mce/inject.c @@ -229,7 +229,6 @@ static int raise_local(void) } 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; @@ -487,19 +486,24 @@ static void prepare_msrs(void *info) 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); + + if (m.misc) + wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc); } 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); + + if (m.misc) + wrmsrl(MSR_IA32_MCx_MISC(b), m.misc); } } static void do_inject(void) { - u64 mcg_status = 0; unsigned int cpu = i_mce.extcpu; + struct mce_hw_err err; + u64 mcg_status = 0; u8 b = i_mce.bank; i_mce.tsc = rdtsc_ordered(); @@ -513,7 +517,8 @@ static void do_inject(void) i_mce.status |= MCI_STATUS_SYNDV; if (inj_type == SW_INJ) { - mce_log(&i_mce); + err.m = i_mce; + mce_log(&err); return; } @@ -795,4 +800,5 @@ static void __exit inject_exit(void) module_init(inject_init); module_exit(inject_exit); +MODULE_DESCRIPTION("Machine check injection support"); MODULE_LICENSE("GPL"); diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c index 399b62e223d2..f863df0ff42c 100644 --- a/arch/x86/kernel/cpu/mce/intel.c +++ b/arch/x86/kernel/cpu/mce/intel.c @@ -13,7 +13,7 @@ #include <linux/cpumask.h> #include <asm/apic.h> #include <asm/cpufeature.h> -#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #include <asm/processor.h> #include <asm/msr.h> #include <asm/mce.h> @@ -75,12 +75,12 @@ static u16 cmci_threshold[MAX_NR_BANKS]; */ #define CMCI_STORM_THRESHOLD 32749 -static int cmci_supported(int *banks) +static bool cmci_supported(int *banks) { u64 cap; if (mca_cfg.cmci_disabled || mca_cfg.ignore_ce) - return 0; + return false; /* * Vendor check is not strictly needed, but the initial @@ -89,12 +89,13 @@ static int cmci_supported(int *banks) */ if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL && boot_cpu_data.x86_vendor != X86_VENDOR_ZHAOXIN) - return 0; + return false; if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6) - return 0; + return false; + rdmsrl(MSR_IA32_MCG_CAP, cap); - *banks = min_t(unsigned, MAX_NR_BANKS, cap & 0xff); + *banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK); return !!(cap & MCG_CMCI_P); } @@ -455,10 +456,10 @@ 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: + switch (c->x86_vfm) { + case INTEL_SANDYBRIDGE_X: + case INTEL_IVYBRIDGE_X: + case INTEL_HASWELL_X: if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control)) return; error_control |= 2; @@ -484,12 +485,11 @@ 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)) && + if ((c->x86_vfm == INTEL_HASWELL || + c->x86_vfm == INTEL_HASWELL_L || + c->x86_vfm == INTEL_BROADWELL || + c->x86_vfm == INTEL_HASWELL_G || + c->x86_vfm == INTEL_SKYLAKE_X) && (m->bank == 0) && ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005)) return true; diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h index 01f8f03969e6..95a504ece43e 100644 --- a/arch/x86/kernel/cpu/mce/internal.h +++ b/arch/x86/kernel/cpu/mce/internal.h @@ -26,13 +26,13 @@ extern struct blocking_notifier_head x86_mce_decoder_chain; struct mce_evt_llist { struct llist_node llnode; - struct mce mce; + struct mce_hw_err err; }; 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); +bool mce_gen_pool_add(struct mce_hw_err *err); +bool 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); @@ -261,6 +261,8 @@ enum mca_msr { /* Decide whether to add MCE record to MCE event pool or filter it out. */ extern bool filter_mce(struct mce *m); +void mce_prep_record_common(struct mce *m); +void mce_prep_record_per_cpu(unsigned int cpu, struct mce *m); #ifdef CONFIG_X86_MCE_AMD extern bool amd_filter_mce(struct mce *m); diff --git a/arch/x86/kernel/cpu/mce/severity.c b/arch/x86/kernel/cpu/mce/severity.c index c4477162c07d..2235a7477436 100644 --- a/arch/x86/kernel/cpu/mce/severity.c +++ b/arch/x86/kernel/cpu/mce/severity.c @@ -12,7 +12,7 @@ #include <linux/uaccess.h> #include <asm/mce.h> -#include <asm/intel-family.h> +#include <asm/cpu_device_id.h> #include <asm/traps.h> #include <asm/insn.h> #include <asm/insn-eval.h> @@ -39,20 +39,20 @@ static struct severity { u64 mask; u64 result; unsigned char sev; - unsigned char mcgmask; - unsigned char mcgres; + unsigned short mcgmask; + unsigned short mcgres; unsigned char ser; unsigned char context; unsigned char excp; unsigned char covered; - unsigned char cpu_model; + unsigned int cpu_vfm; 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 VFM_STEPPING(m, s) .cpu_vfm = m, .cpu_minstepping = s #define KERNEL .context = IN_KERNEL #define USER .context = IN_USER #define KERNEL_RECOV .context = IN_KERNEL_RECOV @@ -128,7 +128,7 @@ static struct severity { 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) + VFM_STEPPING(INTEL_SKYLAKE_X, 4), BANK_RANGE(13, 18) ), /* ignore OVER for UCNA */ @@ -174,6 +174,18 @@ static struct severity { USER ), MCESEV( + AR, "Data load error in SEAM non-root mode", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA), + MCGMASK(MCG_STATUS_SEAM_NR, MCG_STATUS_SEAM_NR), + KERNEL + ), + MCESEV( + AR, "Instruction fetch error in SEAM non-root mode", + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR), + MCGMASK(MCG_STATUS_SEAM_NR, MCG_STATUS_SEAM_NR), + KERNEL + ), + 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 @@ -288,14 +300,12 @@ static noinstr int error_context(struct mce *m, struct pt_regs *regs) 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; + if (copy_user) { + m->kflags |= MCE_IN_KERNEL_COPYIN | MCE_IN_KERNEL_RECOV; + return IN_KERNEL_RECOV; + } + switch (fixup_type) { case EX_TYPE_FAULT_MCE_SAFE: case EX_TYPE_DEFAULT_MCE_SAFE: m->kflags |= MCE_IN_KERNEL_RECOV; @@ -386,7 +396,7 @@ static noinstr int mce_severity_intel(struct mce *m, struct pt_regs *regs, char continue; if (s->excp && excp != s->excp) continue; - if (s->cpu_model && boot_cpu_data.x86_model != s->cpu_model) + if (s->cpu_vfm && boot_cpu_data.x86_vfm != s->cpu_vfm) continue; if (s->cpu_minstepping && boot_cpu_data.x86_stepping < s->cpu_minstepping) continue; diff --git a/arch/x86/kernel/cpu/mce/threshold.c b/arch/x86/kernel/cpu/mce/threshold.c index 89e31e1e5c9c..f4a007616468 100644 --- a/arch/x86/kernel/cpu/mce/threshold.c +++ b/arch/x86/kernel/cpu/mce/threshold.c @@ -90,7 +90,7 @@ void cmci_storm_end(unsigned int bank) storm->banks[bank].in_storm_mode = false; /* If no banks left in storm mode, stop polling. */ - if (!this_cpu_dec_return(storm_desc.stormy_bank_count)) + if (!--storm->stormy_bank_count) mce_timer_kick(false); } |