diff options
Diffstat (limited to 'drivers/acpi')
| -rw-r--r-- | drivers/acpi/Kconfig | 4 | ||||
| -rw-r--r-- | drivers/acpi/acpi_extlog.c | 46 | ||||
| -rw-r--r-- | drivers/acpi/apei/Kconfig | 8 | ||||
| -rw-r--r-- | drivers/acpi/apei/apei-base.c | 13 | ||||
| -rw-r--r-- | drivers/acpi/apei/ghes.c | 173 | ||||
| -rw-r--r-- | drivers/acpi/apei/hest.c | 29 |
6 files changed, 169 insertions, 104 deletions
diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index a34a228..206942b 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -370,6 +370,7 @@ config ACPI_EXTLOG tristate "Extended Error Log support" depends on X86_MCE && X86_LOCAL_APIC select UEFI_CPER + select RAS default n help Certain usages such as Predictive Failure Analysis (PFA) require @@ -384,6 +385,7 @@ config ACPI_EXTLOG Enhanced MCA Logging allows firmware to provide additional error information to system software, synchronous with MCE or CMCI. This - driver adds support for that functionality. + driver adds support for that functionality with corresponding + tracepoint which carries that information to userspace. endif # ACPI diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c index 1853341..0ad6f38 100644 --- a/drivers/acpi/acpi_extlog.c +++ b/drivers/acpi/acpi_extlog.c @@ -12,10 +12,12 @@ #include <linux/cper.h> #include <linux/ratelimit.h> #include <linux/edac.h> +#include <linux/ras.h> #include <asm/cpu.h> #include <asm/mce.h> #include "apei/apei-internal.h" +#include <ras/ras_event.h> #define EXT_ELOG_ENTRY_MASK GENMASK_ULL(51, 0) /* elog entry address mask */ @@ -137,8 +139,12 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, struct mce *mce = (struct mce *)data; int bank = mce->bank; int cpu = mce->extcpu; - struct acpi_generic_status *estatus; - int rc; + struct acpi_generic_status *estatus, *tmp; + struct acpi_generic_data *gdata; + const uuid_le *fru_id = &NULL_UUID_LE; + char *fru_text = ""; + uuid_le *sec_type; + static u32 err_seq; estatus = extlog_elog_entry_check(cpu, bank); if (estatus == NULL) @@ -148,8 +154,29 @@ static int extlog_print(struct notifier_block *nb, unsigned long val, /* clear record status to enable BIOS to update it again */ estatus->block_status = 0; - rc = print_extlog_rcd(NULL, (struct acpi_generic_status *)elog_buf, cpu); + tmp = (struct acpi_generic_status *)elog_buf; + + if (!ras_userspace_consumers()) { + print_extlog_rcd(NULL, tmp, cpu); + goto out; + } + + /* log event via trace */ + err_seq++; + gdata = (struct acpi_generic_data *)(tmp + 1); + if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID) + fru_id = (uuid_le *)gdata->fru_id; + if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT) + fru_text = gdata->fru_text; + sec_type = (uuid_le *)gdata->section_type; + if (!uuid_le_cmp(*sec_type, CPER_SEC_PLATFORM_MEM)) { + struct cper_sec_mem_err *mem = (void *)(gdata + 1); + if (gdata->error_data_length >= sizeof(*mem)) + trace_extlog_mem_event(mem, err_seq, fru_id, fru_text, + (u8)gdata->error_severity); + } +out: return NOTIFY_STOP; } @@ -196,19 +223,16 @@ static int __init extlog_init(void) u64 cap; int rc; + rdmsrl(MSR_IA32_MCG_CAP, cap); + + if (!(cap & MCG_ELOG_P) || !extlog_get_l1addr()) + return -ENODEV; + if (get_edac_report_status() == EDAC_REPORTING_FORCE) { pr_warn("Not loading eMCA, error reporting force-enabled through EDAC.\n"); return -EPERM; } - rc = -ENODEV; - rdmsrl(MSR_IA32_MCG_CAP, cap); - if (!(cap & MCG_ELOG_P)) - return rc; - - if (!extlog_get_l1addr()) - return rc; - rc = -EINVAL; /* get L1 header to fetch necessary information */ l1_hdr_size = sizeof(struct extlog_l1_head); diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index c4dac71..b0140c8 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -1,9 +1,15 @@ +config HAVE_ACPI_APEI + bool + +config HAVE_ACPI_APEI_NMI + bool + config ACPI_APEI bool "ACPI Platform Error Interface (APEI)" select MISC_FILESYSTEMS select PSTORE select UEFI_CPER - depends on X86 + depends on HAVE_ACPI_APEI help APEI allows to report errors (for example from the chipset) to the operating system. This improves NMI handling diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 8678dfe..2cd7bdd 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -745,6 +745,19 @@ struct dentry *apei_get_debugfs_dir(void) } EXPORT_SYMBOL_GPL(apei_get_debugfs_dir); +int __weak arch_apei_enable_cmcff(struct acpi_hest_header *hest_hdr, + void *data) +{ + return 1; +} +EXPORT_SYMBOL_GPL(arch_apei_enable_cmcff); + +void __weak arch_apei_report_mem_error(int sev, + struct cper_sec_mem_err *mem_err) +{ +} +EXPORT_SYMBOL_GPL(arch_apei_report_mem_error); + int apei_osc_setup(void) { static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c"; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index dab7cb7..e05d84e7 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -47,11 +47,11 @@ #include <linux/genalloc.h> #include <linux/pci.h> #include <linux/aer.h> +#include <linux/nmi.h> #include <acpi/ghes.h> -#include <asm/mce.h> +#include <acpi/apei.h> #include <asm/tlbflush.h> -#include <asm/nmi.h> #include "apei-internal.h" @@ -86,8 +86,6 @@ bool ghes_disable; module_param_named(disable, ghes_disable, bool, 0); -static int ghes_panic_timeout __read_mostly = 30; - /* * All error sources notified with SCI shares one notifier function, * so they need to be linked and checked one by one. This is applied @@ -97,16 +95,9 @@ static int ghes_panic_timeout __read_mostly = 30; * list changing, not for traversing. */ static LIST_HEAD(ghes_sci); -static LIST_HEAD(ghes_nmi); static DEFINE_MUTEX(ghes_list_mutex); /* - * NMI may be triggered on any CPU, so ghes_nmi_lock is used for - * mutual exclusion. - */ -static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); - -/* * Because the memory area used to transfer hardware error information * from BIOS to Linux can be determined only in NMI, IRQ or timer * handler, but general ioremap can not be used in atomic context, so @@ -114,12 +105,16 @@ static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); */ /* - * Two virtual pages are used, one for NMI context, the other for - * IRQ/PROCESS context + * Two virtual pages are used, one for IRQ/PROCESS context, the other for + * NMI context (optionally). */ -#define GHES_IOREMAP_PAGES 2 -#define GHES_IOREMAP_NMI_PAGE(base) (base) -#define GHES_IOREMAP_IRQ_PAGE(base) ((base) + PAGE_SIZE) +#ifdef CONFIG_HAVE_ACPI_APEI_NMI +#define GHES_IOREMAP_PAGES 2 +#else +#define GHES_IOREMAP_PAGES 1 +#endif +#define GHES_IOREMAP_IRQ_PAGE(base) (base) +#define GHES_IOREMAP_NMI_PAGE(base) ((base) + PAGE_SIZE) /* virtual memory area for atomic ioremap */ static struct vm_struct *ghes_ioremap_area; @@ -130,18 +125,8 @@ static struct vm_struct *ghes_ioremap_area; static DEFINE_RAW_SPINLOCK(ghes_ioremap_lock_nmi); static DEFINE_SPINLOCK(ghes_ioremap_lock_irq); -/* - * printk is not safe in NMI context. So in NMI handler, we allocate - * required memory from lock-less memory allocator - * (ghes_estatus_pool), save estatus into it, put them into lock-less - * list (ghes_estatus_llist), then delay printk into IRQ context via - * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record - * required pool size by all NMI error source. - */ static struct gen_pool *ghes_estatus_pool; static unsigned long ghes_estatus_pool_size_request; -static struct llist_head ghes_estatus_llist; -static struct irq_work ghes_proc_irq_work; struct ghes_estatus_cache *ghes_estatus_caches[GHES_ESTATUS_CACHES_SIZE]; static atomic_t ghes_estatus_cache_alloced; @@ -192,7 +177,7 @@ static void ghes_iounmap_nmi(void __iomem *vaddr_ptr) BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_NMI_PAGE(base)); unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - __flush_tlb_one(vaddr); + arch_apei_flush_tlb_one(vaddr); } static void ghes_iounmap_irq(void __iomem *vaddr_ptr) @@ -202,7 +187,7 @@ static void ghes_iounmap_irq(void __iomem *vaddr_ptr) BUG_ON(vaddr != (unsigned long)GHES_IOREMAP_IRQ_PAGE(base)); unmap_kernel_range_noflush(vaddr, PAGE_SIZE); - __flush_tlb_one(vaddr); + arch_apei_flush_tlb_one(vaddr); } static int ghes_estatus_pool_init(void) @@ -249,11 +234,6 @@ static int ghes_estatus_pool_expand(unsigned long len) return 0; } -static void ghes_estatus_pool_shrink(unsigned long len) -{ - ghes_estatus_pool_size_request -= PAGE_ALIGN(len); -} - static struct ghes *ghes_new(struct acpi_hest_generic *generic) { struct ghes *ghes; @@ -455,9 +435,7 @@ static void ghes_do_proc(struct ghes *ghes, mem_err = (struct cper_sec_mem_err *)(gdata+1); ghes_edac_report_mem_error(ghes, sev, mem_err); -#ifdef CONFIG_X86_MCE - apei_mce_report_mem_error(sev, mem_err); -#endif + arch_apei_report_mem_error(sev, mem_err); ghes_handle_memory_failure(gdata, sev); } #ifdef CONFIG_ACPI_APEI_PCIEAER @@ -734,6 +712,32 @@ static int ghes_notify_sci(struct notifier_block *this, return ret; } +static struct notifier_block ghes_notifier_sci = { + .notifier_call = ghes_notify_sci, +}; + +#ifdef CONFIG_HAVE_ACPI_APEI_NMI +/* + * printk is not safe in NMI context. So in NMI handler, we allocate + * required memory from lock-less memory allocator + * (ghes_estatus_pool), save estatus into it, put them into lock-less + * list (ghes_estatus_llist), then delay printk into IRQ context via + * irq_work (ghes_proc_irq_work). ghes_estatus_size_request record + * required pool size by all NMI error source. + */ +static struct llist_head ghes_estatus_llist; +static struct irq_work ghes_proc_irq_work; + +/* + * NMI may be triggered on any CPU, so ghes_nmi_lock is used for + * mutual exclusion. + */ +static DEFINE_RAW_SPINLOCK(ghes_nmi_lock); + +static LIST_HEAD(ghes_nmi); + +static int ghes_panic_timeout __read_mostly = 30; + static struct llist_node *llist_nodes_reverse(struct llist_node *llnode) { struct llist_node *next, *tail = NULL; @@ -877,10 +881,6 @@ out: return ret; } -static struct notifier_block ghes_notifier_sci = { - .notifier_call = ghes_notify_sci, -}; - static unsigned long ghes_esource_prealloc_size( const struct acpi_hest_generic *generic) { @@ -896,11 +896,71 @@ static unsigned long ghes_esource_prealloc_size( return prealloc_size; } +static void ghes_estatus_pool_shrink(unsigned long len) +{ + ghes_estatus_pool_size_request -= PAGE_ALIGN(len); +} + +static void ghes_nmi_add(struct ghes *ghes) +{ + unsigned long len; + + len = ghes_esource_prealloc_size(ghes->generic); + ghes_estatus_pool_expand(len); + mutex_lock(&ghes_list_mutex); + if (list_empty(&ghes_nmi)) + register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, "ghes"); + list_add_rcu(&ghes->list, &ghes_nmi); + mutex_unlock(&ghes_list_mutex); +} + +static void ghes_nmi_remove(struct ghes *ghes) +{ + unsigned long len; + + mutex_lock(&ghes_list_mutex); + list_del_rcu(&ghes->list); + if (list_empty(&ghes_nmi)) + unregister_nmi_handler(NMI_LOCAL, "ghes"); + mutex_unlock(&ghes_list_mutex); + /* + * To synchronize with NMI handler, ghes can only be + * freed after NMI handler finishes. + */ + synchronize_rcu(); + len = ghes_esource_prealloc_size(ghes->generic); + ghes_estatus_pool_shrink(len); +} + +static void ghes_nmi_init_cxt(void) +{ + init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq); +} +#else /* CONFIG_HAVE_ACPI_APEI_NMI */ +static inline void ghes_nmi_add(struct ghes *ghes) +{ + pr_err(GHES_PFX "ID: %d, trying to add NMI notification which is not supported!\n", + ghes->generic->header.source_id); + BUG(); +} + +static inline void ghes_nmi_remove(struct ghes *ghes) +{ + pr_err(GHES_PFX "ID: %d, trying to remove NMI notification which is not supported!\n", + ghes->generic->header.source_id); + BUG(); +} + +static inline void ghes_nmi_init_cxt(void) +{ +} +#endif /* CONFIG_HAVE_ACPI_APEI_NMI */ + static int ghes_probe(struct platform_device *ghes_dev) { struct acpi_hest_generic *generic; struct ghes *ghes = NULL; - unsigned long len; + int rc = -EINVAL; generic = *(struct acpi_hest_generic **)ghes_dev->dev.platform_data; @@ -911,7 +971,13 @@ static int ghes_probe(struct platform_device *ghes_dev) case ACPI_HEST_NOTIFY_POLLED: case ACPI_HEST_NOTIFY_EXTERNAL: case ACPI_HEST_NOTIFY_SCI: + break; case ACPI_HEST_NOTIFY_NMI: + if (!IS_ENABLED(CONFIG_HAVE_ACPI_APEI_NMI)) { + pr_warn(GHES_PFX "Generic hardware error source: %d notified via NMI interrupt is not supported!\n", + generic->header.source_id); + goto err; + } break; case ACPI_HEST_NOTIFY_LOCAL: pr_warning(GHES_PFX "Generic hardware error source: %d notified via local interrupt is not supported!\n", @@ -972,14 +1038,7 @@ static int ghes_probe(struct platform_device *ghes_dev) mutex_unlock(&ghes_list_mutex); break; case ACPI_HEST_NOTIFY_NMI: - len = ghes_esource_prealloc_size(generic); - ghes_estatus_pool_expand(len); - mutex_lock(&ghes_list_mutex); - if (list_empty(&ghes_nmi)) - register_nmi_handler(NMI_LOCAL, ghes_notify_nmi, 0, - "ghes"); - list_add_rcu(&ghes->list, &ghes_nmi); - mutex_unlock(&ghes_list_mutex); + ghes_nmi_add(ghes); break; default: BUG(); @@ -1001,7 +1060,6 @@ static int ghes_remove(struct platform_device *ghes_dev) { struct ghes *ghes; struct acpi_hest_generic *generic; - unsigned long len; ghes = platform_get_drvdata(ghes_dev); generic = ghes->generic; @@ -1022,18 +1080,7 @@ static int ghes_remove(struct platform_device *ghes_dev) mutex_unlock(&ghes_list_mutex); break; case ACPI_HEST_NOTIFY_NMI: - mutex_lock(&ghes_list_mutex); - list_del_rcu(&ghes->list); - if (list_empty(&ghes_nmi)) - unregister_nmi_handler(NMI_LOCAL, "ghes"); - mutex_unlock(&ghes_list_mutex); - /* - * To synchronize with NMI handler, ghes can only be - * freed after NMI handler finishes. - */ - synchronize_rcu(); - len = ghes_esource_prealloc_size(generic); - ghes_estatus_pool_shrink(len); + ghes_nmi_remove(ghes); break; default: BUG(); @@ -1077,7 +1124,7 @@ static int __init ghes_init(void) return -EINVAL; } - init_irq_work(&ghes_proc_irq_work, ghes_proc_in_irq); + ghes_nmi_init_cxt(); rc = ghes_ioremap_init(); if (rc) diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c index f5e37f3..06e9b41 100644 --- a/drivers/acpi/apei/hest.c +++ b/drivers/acpi/apei/hest.c @@ -36,7 +36,6 @@ #include <linux/io.h> #include <linux/platform_device.h> #include <acpi/apei.h> -#include <asm/mce.h> #include "apei-internal.h" @@ -128,33 +127,7 @@ EXPORT_SYMBOL_GPL(apei_hest_parse); */ static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data) { -#ifdef CONFIG_X86_MCE - int i; - struct acpi_hest_ia_corrected *cmc; - struct acpi_hest_ia_error_bank *mc_bank; - - if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK) - return 0; - - cmc = (struct acpi_hest_ia_corrected *)hest_hdr; - if (!cmc->enabled) - return 0; - - /* - * We expect HEST to provide a list of MC banks that report errors - * in firmware first mode. Otherwise, return non-zero value to - * indicate that we are done parsing HEST. - */ - if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks) - return 1; - - pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n"); - - mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1); - for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++) - mce_disable_bank(mc_bank->bank_number); -#endif - return 1; + return arch_apei_enable_cmcff(hest_hdr, data); } struct ghes_arr { |
