diff options
Diffstat (limited to 'drivers/acpi')
29 files changed, 768 insertions, 134 deletions
diff --git a/drivers/acpi/acpica/acconfig.h b/drivers/acpi/acpica/acconfig.h index bc533dde16c..f895a244ca7 100644 --- a/drivers/acpi/acpica/acconfig.h +++ b/drivers/acpi/acpica/acconfig.h @@ -121,7 +121,7 @@ /* Maximum sleep allowed via Sleep() operator */ -#define ACPI_MAX_SLEEP 20000 /* Two seconds */ +#define ACPI_MAX_SLEEP 2000 /* Two seconds */ /****************************************************************************** * diff --git a/drivers/acpi/acpica/acglobal.h b/drivers/acpi/acpica/acglobal.h index 73863d86f02..76dc02f1557 100644 --- a/drivers/acpi/acpica/acglobal.h +++ b/drivers/acpi/acpica/acglobal.h @@ -126,6 +126,12 @@ u8 ACPI_INIT_GLOBAL(acpi_gbl_copy_dsdt_locally, FALSE); */ u8 ACPI_INIT_GLOBAL(acpi_gbl_truncate_io_addresses, FALSE); +/* + * Disable runtime checking and repair of values returned by control methods. + * Use only if the repair is causing a problem on a particular machine. + */ +u8 ACPI_INIT_GLOBAL(acpi_gbl_disable_auto_repair, FALSE); + /* acpi_gbl_FADT is a local copy of the FADT, converted to a common format. */ struct acpi_table_fadt acpi_gbl_FADT; diff --git a/drivers/acpi/acpica/aclocal.h b/drivers/acpi/acpica/aclocal.h index c7f743ca395..5552125d834 100644 --- a/drivers/acpi/acpica/aclocal.h +++ b/drivers/acpi/acpica/aclocal.h @@ -357,6 +357,7 @@ struct acpi_predefined_data { char *pathname; const union acpi_predefined_info *predefined; union acpi_operand_object *parent_package; + struct acpi_namespace_node *node; u32 flags; u8 node_flags; }; diff --git a/drivers/acpi/acpica/acpredef.h b/drivers/acpi/acpica/acpredef.h index 94e73c97cf8..c445cca490e 100644 --- a/drivers/acpi/acpica/acpredef.h +++ b/drivers/acpi/acpica/acpredef.h @@ -468,6 +468,7 @@ static const union acpi_predefined_info predefined_names[] = {{"_SWS", 0, ACPI_RTYPE_INTEGER}}, {{"_TC1", 0, ACPI_RTYPE_INTEGER}}, {{"_TC2", 0, ACPI_RTYPE_INTEGER}}, + {{"_TDL", 0, ACPI_RTYPE_INTEGER}}, {{"_TIP", 1, ACPI_RTYPE_INTEGER}}, {{"_TIV", 1, ACPI_RTYPE_INTEGER}}, {{"_TMP", 0, ACPI_RTYPE_INTEGER}}, diff --git a/drivers/acpi/acpica/nspredef.c b/drivers/acpi/acpica/nspredef.c index 9fb03fa8ffd..c845c8089f3 100644 --- a/drivers/acpi/acpica/nspredef.c +++ b/drivers/acpi/acpica/nspredef.c @@ -193,14 +193,20 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node, } /* - * 1) We have a return value, but if one wasn't expected, just exit, this is - * not a problem. For example, if the "Implicit Return" feature is - * enabled, methods will always return a value. + * Return value validation and possible repair. * - * 2) If the return value can be of any type, then we cannot perform any - * validation, exit. + * 1) Don't perform return value validation/repair if this feature + * has been disabled via a global option. + * + * 2) We have a return value, but if one wasn't expected, just exit, + * this is not a problem. For example, if the "Implicit Return" + * feature is enabled, methods will always return a value. + * + * 3) If the return value can be of any type, then we cannot perform + * any validation, just exit. */ - if ((!predefined->info.expected_btypes) || + if (acpi_gbl_disable_auto_repair || + (!predefined->info.expected_btypes) || (predefined->info.expected_btypes == ACPI_RTYPE_ALL)) { goto cleanup; } @@ -212,6 +218,7 @@ acpi_ns_check_predefined_names(struct acpi_namespace_node *node, goto cleanup; } data->predefined = predefined; + data->node = node; data->node_flags = node->flags; data->pathname = pathname; diff --git a/drivers/acpi/acpica/nsrepair2.c b/drivers/acpi/acpica/nsrepair2.c index 973883babee..024c4f263f8 100644 --- a/drivers/acpi/acpica/nsrepair2.c +++ b/drivers/acpi/acpica/nsrepair2.c @@ -503,6 +503,21 @@ acpi_ns_repair_TSS(struct acpi_predefined_data *data, { union acpi_operand_object *return_object = *return_object_ptr; acpi_status status; + struct acpi_namespace_node *node; + + /* + * We can only sort the _TSS return package if there is no _PSS in the + * same scope. This is because if _PSS is present, the ACPI specification + * dictates that the _TSS Power Dissipation field is to be ignored, and + * therefore some BIOSs leave garbage values in the _TSS Power field(s). + * In this case, it is best to just return the _TSS package as-is. + * (May, 2011) + */ + status = + acpi_ns_get_node(data->node, "^_PSS", ACPI_NS_NO_UPSEARCH, &node); + if (ACPI_SUCCESS(status)) { + return (AE_OK); + } status = acpi_ns_check_sorted_list(data, return_object, 5, 1, ACPI_SORT_DESCENDING, diff --git a/drivers/acpi/acpica/tbinstal.c b/drivers/acpi/acpica/tbinstal.c index 48db0944ce4..62365f6075d 100644 --- a/drivers/acpi/acpica/tbinstal.c +++ b/drivers/acpi/acpica/tbinstal.c @@ -126,12 +126,29 @@ acpi_tb_add_table(struct acpi_table_desc *table_desc, u32 *table_index) } /* - * Originally, we checked the table signature for "SSDT" or "PSDT" here. - * Next, we added support for OEMx tables, signature "OEM". - * Valid tables were encountered with a null signature, so we've just - * given up on validating the signature, since it seems to be a waste - * of code. The original code was removed (05/2008). + * Validate the incoming table signature. + * + * 1) Originally, we checked the table signature for "SSDT" or "PSDT". + * 2) We added support for OEMx tables, signature "OEM". + * 3) Valid tables were encountered with a null signature, so we just + * gave up on validating the signature, (05/2008). + * 4) We encountered non-AML tables such as the MADT, which caused + * interpreter errors and kernel faults. So now, we once again allow + * only "SSDT", "OEMx", and now, also a null signature. (05/2011). */ + if ((table_desc->pointer->signature[0] != 0x00) && + (!ACPI_COMPARE_NAME(table_desc->pointer->signature, ACPI_SIG_SSDT)) + && (ACPI_STRNCMP(table_desc->pointer->signature, "OEM", 3))) { + ACPI_ERROR((AE_INFO, + "Table has invalid signature [%4.4s] (0x%8.8X), must be SSDT or OEMx", + acpi_ut_valid_acpi_name(*(u32 *)table_desc-> + pointer-> + signature) ? table_desc-> + pointer->signature : "????", + *(u32 *)table_desc->pointer->signature)); + + return_ACPI_STATUS(AE_BAD_SIGNATURE); + } (void)acpi_ut_acquire_mutex(ACPI_MTX_TABLES); diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index f739a70b1c7..e3f47872ec2 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -10,9 +10,12 @@ config ACPI_APEI error injection. config ACPI_APEI_GHES - tristate "APEI Generic Hardware Error Source" + bool "APEI Generic Hardware Error Source" depends on ACPI_APEI && X86 select ACPI_HED + select IRQ_WORK + select LLIST + select GENERIC_ALLOCATOR help Generic Hardware Error Source provides a way to report platform hardware errors (such as that from chipset). It @@ -30,6 +33,13 @@ config ACPI_APEI_PCIEAER PCIe AER errors may be reported via APEI firmware first mode. Turn on this option to enable the corresponding support. +config ACPI_APEI_MEMORY_FAILURE + bool "APEI memory error recovering support" + depends on ACPI_APEI && MEMORY_FAILURE + help + Memory errors may be reported via APEI firmware first mode. + Turn on this option to enable the memory recovering support. + config ACPI_APEI_EINJ tristate "APEI Error INJection (EINJ)" depends on ACPI_APEI && DEBUG_FS diff --git a/drivers/acpi/apei/apei-base.c b/drivers/acpi/apei/apei-base.c index 4a904a4bf05..61540360d5c 100644 --- a/drivers/acpi/apei/apei-base.c +++ b/drivers/acpi/apei/apei-base.c @@ -157,9 +157,10 @@ EXPORT_SYMBOL_GPL(apei_exec_noop); * Interpret the specified action. Go through whole action table, * execute all instructions belong to the action. */ -int apei_exec_run(struct apei_exec_context *ctx, u8 action) +int __apei_exec_run(struct apei_exec_context *ctx, u8 action, + bool optional) { - int rc; + int rc = -ENOENT; u32 i, ip; struct acpi_whea_header *entry; apei_exec_ins_func_t run; @@ -198,9 +199,9 @@ rewind: goto rewind; } - return 0; + return !optional && rc < 0 ? rc : 0; } -EXPORT_SYMBOL_GPL(apei_exec_run); +EXPORT_SYMBOL_GPL(__apei_exec_run); typedef int (*apei_exec_entry_func_t)(struct apei_exec_context *ctx, struct acpi_whea_header *entry, @@ -603,3 +604,29 @@ struct dentry *apei_get_debugfs_dir(void) return dapei; } EXPORT_SYMBOL_GPL(apei_get_debugfs_dir); + +int apei_osc_setup(void) +{ + static u8 whea_uuid_str[] = "ed855e0c-6c90-47bf-a62a-26de0fc5ad5c"; + acpi_handle handle; + u32 capbuf[3]; + struct acpi_osc_context context = { + .uuid_str = whea_uuid_str, + .rev = 1, + .cap.length = sizeof(capbuf), + .cap.pointer = capbuf, + }; + + capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE; + capbuf[OSC_SUPPORT_TYPE] = 1; + capbuf[OSC_CONTROL_TYPE] = 0; + + if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)) + || ACPI_FAILURE(acpi_run_osc(handle, &context))) + return -EIO; + else { + kfree(context.ret.pointer); + return 0; + } +} +EXPORT_SYMBOL_GPL(apei_osc_setup); diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index ef0581f2094..f57050e7a5e 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -50,7 +50,18 @@ static inline u64 apei_exec_ctx_get_output(struct apei_exec_context *ctx) return ctx->value; } -int apei_exec_run(struct apei_exec_context *ctx, u8 action); +int __apei_exec_run(struct apei_exec_context *ctx, u8 action, bool optional); + +static inline int apei_exec_run(struct apei_exec_context *ctx, u8 action) +{ + return __apei_exec_run(ctx, action, 0); +} + +/* It is optional whether the firmware provides the action */ +static inline int apei_exec_run_optional(struct apei_exec_context *ctx, u8 action) +{ + return __apei_exec_run(ctx, action, 1); +} /* Common instruction implementation */ @@ -113,4 +124,6 @@ void apei_estatus_print(const char *pfx, const struct acpi_hest_generic_status *estatus); int apei_estatus_check_header(const struct acpi_hest_generic_status *estatus); int apei_estatus_check(const struct acpi_hest_generic_status *estatus); + +int apei_osc_setup(void); #endif diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index f74b2ea11f2..589b96c3870 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -46,7 +46,8 @@ * Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the * EINJ table through an unpublished extension. Use with caution as * most will ignore the parameter and make their own choice of address - * for error injection. + * for error injection. This extension is used only if + * param_extension module parameter is specified. */ struct einj_parameter { u64 type; @@ -65,6 +66,9 @@ struct einj_parameter { ((struct acpi_whea_header *)((char *)(tab) + \ sizeof(struct acpi_table_einj))) +static bool param_extension; +module_param(param_extension, bool, 0); + static struct acpi_table_einj *einj_tab; static struct apei_resources einj_resources; @@ -285,7 +289,7 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2) einj_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_EINJ_BEGIN_OPERATION); + rc = apei_exec_run_optional(&ctx, ACPI_EINJ_BEGIN_OPERATION); if (rc) return rc; apei_exec_ctx_set_input(&ctx, type); @@ -323,7 +327,7 @@ static int __einj_error_inject(u32 type, u64 param1, u64 param2) rc = __einj_error_trigger(trigger_paddr); if (rc) return rc; - rc = apei_exec_run(&ctx, ACPI_EINJ_END_OPERATION); + rc = apei_exec_run_optional(&ctx, ACPI_EINJ_END_OPERATION); return rc; } @@ -489,14 +493,6 @@ static int __init einj_init(void) einj_debug_dir, NULL, &error_type_fops); if (!fentry) goto err_cleanup; - fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR, - einj_debug_dir, &error_param1); - if (!fentry) - goto err_cleanup; - fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR, - einj_debug_dir, &error_param2); - if (!fentry) - goto err_cleanup; fentry = debugfs_create_file("error_inject", S_IWUSR, einj_debug_dir, NULL, &error_inject_fops); if (!fentry) @@ -513,12 +509,23 @@ static int __init einj_init(void) rc = apei_exec_pre_map_gars(&ctx); if (rc) goto err_release; - param_paddr = einj_get_parameter_address(); - if (param_paddr) { - einj_param = ioremap(param_paddr, sizeof(*einj_param)); - rc = -ENOMEM; - if (!einj_param) - goto err_unmap; + if (param_extension) { + param_paddr = einj_get_parameter_address(); + if (param_paddr) { + einj_param = ioremap(param_paddr, sizeof(*einj_param)); + rc = -ENOMEM; + if (!einj_param) + goto err_unmap; + fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_param1); + if (!fentry) + goto err_unmap; + fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR, + einj_debug_dir, &error_param2); + if (!fentry) + goto err_unmap; + } else + pr_warn(EINJ_PFX "Parameter extension is not supported.\n"); } pr_info(EINJ_PFX "Error INJection is initialized.\n"); @@ -526,6 +533,8 @@ static int __init einj_init(void) return 0; err_unmap: + if (einj_param) + iounmap(einj_param); apei_exec_post_unmap_gars(&ctx); err_release: apei_resources_release(&einj_resources); diff --git a/drivers/acpi/apei/erst-dbg.c b/drivers/acpi/apei/erst-dbg.c index a4cfb64c86a..903549df809 100644 --- a/drivers/acpi/apei/erst-dbg.c +++ b/drivers/acpi/apei/erst-dbg.c @@ -33,7 +33,7 @@ #define ERST_DBG_PFX "ERST DBG: " -#define ERST_DBG_RECORD_LEN_MAX 4096 +#define ERST_DBG_RECORD_LEN_MAX 0x4000 static void *erst_dbg_buf; static unsigned int erst_dbg_buf_len; @@ -213,6 +213,10 @@ static struct miscdevice erst_dbg_dev = { static __init int erst_dbg_init(void) { + if (erst_disable) { + pr_info(ERST_DBG_PFX "ERST support is disabled.\n"); + return -ENODEV; + } return misc_register(&erst_dbg_dev); } diff --git a/drivers/acpi/apei/erst.c b/drivers/acpi/apei/erst.c index e6cef8e1b53..2ca59dc69f7 100644 --- a/drivers/acpi/apei/erst.c +++ b/drivers/acpi/apei/erst.c @@ -642,7 +642,7 @@ static int __erst_write_to_storage(u64 offset) int rc; erst_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_WRITE); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_WRITE); if (rc) return rc; apei_exec_ctx_set_input(&ctx, offset); @@ -666,7 +666,7 @@ static int __erst_write_to_storage(u64 offset) if (rc) return rc; val = apei_exec_ctx_get_output(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_END); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_END); if (rc) return rc; @@ -681,7 +681,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset) int rc; erst_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_READ); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_READ); if (rc) return rc; apei_exec_ctx_set_input(&ctx, offset); @@ -709,7 +709,7 @@ static int __erst_read_from_storage(u64 record_id, u64 offset) if (rc) return rc; val = apei_exec_ctx_get_output(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_END); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_END); if (rc) return rc; @@ -724,7 +724,7 @@ static int __erst_clear_from_storage(u64 record_id) int rc; erst_exec_ctx_init(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_BEGIN_CLEAR); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_BEGIN_CLEAR); if (rc) return rc; apei_exec_ctx_set_input(&ctx, record_id); @@ -748,7 +748,7 @@ static int __erst_clear_from_storage(u64 record_id) if (rc) return rc; val = apei_exec_ctx_get_output(&ctx); - rc = apei_exec_run(&ctx, ACPI_ERST_END); + rc = apei_exec_run_optional(&ctx, ACPI_ERST_END); if (rc) return rc; @@ -932,8 +932,11 @@ static int erst_check_table(struct acpi_table_erst *erst_tab) static int erst_open_pstore(struct pstore_info *psi); static int erst_close_pstore(struct pstore_info *psi); static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, - struct timespec *time); -static u64 erst_writer(enum pstore_type_id type, size_t size); + struct timespec *time, struct pstore_info *psi); +static u64 erst_writer(enum pstore_type_id type, unsigned int part, + size_t size, struct pstore_info *psi); +static int erst_clearer(enum pstore_type_id type, u64 id, + struct pstore_info *psi); static struct pstore_info erst_info = { .owner = THIS_MODULE, @@ -942,7 +945,7 @@ static struct pstore_info erst_info = { .close = erst_close_pstore, .read = erst_reader, .write = erst_writer, - .erase = erst_clear + .erase = erst_clearer }; #define CPER_CREATOR_PSTORE \ @@ -983,7 +986,7 @@ static int erst_close_pstore(struct pstore_info *psi) } static ssize_t erst_reader(u64 *id, enum pstore_type_id *type, - struct timespec *time) + struct timespec *time, struct pstore_info *psi) { int rc; ssize_t len = 0; @@ -1037,7 +1040,8 @@ out: return (rc < 0) ? rc : (len - sizeof(*rcd)); } -static u64 erst_writer(enum pstore_type_id type, size_t size) +static u64 erst_writer(enum pstore_type_id type, unsigned int part, + size_t size, struct pstore_info *psi) { struct cper_pstore_record *rcd = (struct cper_pstore_record *) (erst_info.buf - sizeof(*rcd)); @@ -1080,6 +1084,12 @@ static u64 erst_writer(enum pstore_type_id type, size_t size) return rcd->hdr.record_id; } +static int erst_clearer(enum pstore_type_id type, u64 id, + struct pstore_info *psi) +{ + return erst_clear(id); +} + static int __init erst_init(void) { int rc = 0; diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index f703b288115..0784f99a466 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -12,7 +12,7 @@ * For more information about Generic Hardware Error Source, please * refer to ACPI Specification version 4.0, section 17.3.2.6 * - * Copyright 2010 Intel Corp. + * Copyright 2010,2011 Intel Corp. * Author: Huang Ying <ying.huang@intel.com> * * This program is free software; you can redistribute it and/or @@ -42,6 +42,9 @@ #include <linux/mutex.h> #include <linux/ratelimit.h> #include <linux/vmalloc.h> +#include <linux/irq_work.h> +#include <linux/llist.h> +#include <linux/genalloc.h> #include <acpi/apei.h> #include <acpi/atomicio.h> #include <acpi/hed.h> @@ -53,6 +56,30 @@ #define GHES_PFX "GHES: " #define GHES_ESTATUS_MAX_SIZE 65536 +#define GHES_ESOURCE_PREALLOC_MAX_SIZE 65536 + +#define GHES_ESTATUS_POOL_MIN_ALLOC_ORDER 3 + +/* This is just an estimation for memory pool allocation */ +#define GHES_ESTATUS_CACHE_AVG_SIZE 512 + +#define GHES_ESTATUS_CACHES_SIZE 4 + +#define GHES_ESTATUS_IN_CACHE_MAX_NSEC 10000000000ULL +/* Prevent too many caches are allocated because of RCU */ +#define GHES_ESTATUS_CACHE_ALLOCED_MAX (GHES_ESTATUS_CACHES_SIZE * 3 / 2) + +#define GHES_ESTATUS_CACHE_LEN(estatus_len) \ + (sizeof(struct ghes_estatus_cache) + (estatus_len)) +#define GHES_ESTATUS_FROM_CACHE(estatus_cache) \ + ((struct acpi_hest_generic_status *) \ + ((struct ghes_estatus_cache *)(estatus_cache) + 1)) + +#define GHES_ESTATUS_NODE_LEN(estatus_len) \ + (sizeof(struct ghes_estatus_node) + (estatus_len)) +#define GHES_ESTATUS_FROM_NODE(estatus_node) \ + ((struct acpi_hest_generic_status *) \ + ((struct ghes_estatus_node *)(estatus_node) + 1)) /* * One struct ghes is created for each generic hardware error source. @@ -77,6 +104,22 @@ struct ghes { }; }; +struct ghes_estatus_node { + struct llist_node llnode; + struct acpi_hest_generic *generic; +}; + +struct ghes_estatus_cache { + u32 estatus_len; + atomic_t count; + struct acpi_hest_generic *generic; + unsigned long long time_in; + struct rcu_head rcu; +}; + +int ghes_disable; +module_param_named(disable, ghes_disable, bool, 0); + static int ghes_panic_timeout __read_mostly = 30; /* @@ -121,6 +164,22 @@ 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; + static int ghes_ioremap_init(void) { ghes_ioremap_area = __get_vm_area(PAGE_SIZE * GHES_IOREMAP_PAGES, @@ -180,6 +239,55 @@ static void ghes_iounmap_irq(void __iomem *vaddr_ptr) __flush_tlb_one(vaddr); } +static int ghes_estatus_pool_init(void) +{ + ghes_estatus_pool = gen_pool_create(GHES_ESTATUS_POOL_MIN_ALLOC_ORDER, -1); + if (!ghes_estatus_pool) + return -ENOMEM; + return 0; +} + +static void ghes_estatus_pool_free_chunk_page(struct gen_pool *pool, + struct gen_pool_chunk *chunk, + void *data) +{ + free_page(chunk->start_addr); +} + +static void ghes_estatus_pool_exit(void) +{ + gen_pool_for_each_chunk(ghes_estatus_pool, + ghes_estatus_pool_free_chunk_page, NULL); + gen_pool_destroy(ghes_estatus_pool); +} + +static int ghes_estatus_pool_expand(unsigned long len) +{ + unsigned long i, pages, size, addr; + int ret; + + ghes_estatus_pool_size_request += PAGE_ALIGN(len); + size = gen_pool_size(ghes_estatus_pool); + if (size >= ghes_estatus_pool_size_request) + return 0; + pages = (ghes_estatus_pool_size_request - size) / PAGE_SIZE; + for (i = 0; i < pages; i++) { + addr = __get_free_page(GFP_KERNEL); + if (!addr) + return -ENOMEM; + ret = gen_pool_add(ghes_estatus_pool, addr, PAGE_SIZE, -1); + if (ret) + return ret; + } + + 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; @@ -341,43 +449,196 @@ static void ghes_clear_estatus(struct ghes *ghes) ghes->flags &= ~GHES_TO_CLEAR; } -static void ghes_do_proc(struct ghes *ghes) +static void ghes_do_proc(const struct acpi_hest_generic_status *estatus) { - int sev, processed = 0; + int sev, sec_sev; struct acpi_hest_generic_data *gdata; - sev = ghes_severity(ghes->estatus->error_severity); - apei_estatus_for_each_section(ghes->estatus, gdata) { -#ifdef CONFIG_X86_MCE + sev = ghes_severity(estatus->error_severity); + apei_estatus_for_each_section(estatus, gdata) { + sec_sev = ghes_severity(gdata->error_severity); if (!uuid_le_cmp(*(uuid_le *)gdata->section_type, CPER_SEC_PLATFORM_MEM)) { - apei_mce_report_mem_error( - sev == GHES_SEV_CORRECTED, - (struct cper_sec_mem_err *)(gdata+1)); - processed = 1; - } + struct cper_sec_mem_err *mem_err; + mem_err = (struct cper_sec_mem_err *)(gdata+1); +#ifdef CONFIG_X86_MCE + apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED, + mem_err); #endif +#ifdef CONFIG_ACPI_APEI_MEMORY_FAILURE + if (sev == GHES_SEV_RECOVERABLE && + sec_sev == GHES_SEV_RECOVERABLE && + mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS) { + unsigned long pfn; + pfn = mem_err->physical_addr >> PAGE_SHIFT; + memory_failure_queue(pfn, 0, 0); + } +#endif + } } } -static void ghes_print_estatus(const char *pfx, struct ghes *ghes) +static void __ghes_print_estatus(const char *pfx, + const struct acpi_hest_generic *generic, + const struct acpi_hest_generic_status *estatus) { - /* Not more than 2 messages every 5 seconds */ - static DEFINE_RATELIMIT_STATE(ratelimit, 5*HZ, 2); - if (pfx == NULL) { - if (ghes_severity(ghes->estatus->error_severity) <= + if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED) pfx = KERN_WARNING HW_ERR; else pfx = KERN_ERR HW_ERR; } - if (__ratelimit(&ratelimit)) { - printk( - "%s""Hardware error from APEI Generic Hardware Error Source: %d\n", - pfx, ghes->generic->header.source_id); - apei_estatus_print(pfx, ghes->estatus); + printk("%s""Hardware error from APEI Generic Hardware Error Source: %d\n", + pfx, generic->header.source_id); + apei_estatus_print(pfx, estatus); +} + +static int ghes_print_estatus(const char *pfx, + const struct acpi_hest_generic *generic, + const struct acpi_hest_generic_status *estatus) +{ + /* Not more than 2 messages every 5 seconds */ + static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2); + static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2); + struct ratelimit_state *ratelimit; + + if (ghes_severity(estatus->error_severity) <= GHES_SEV_CORRECTED) + ratelimit = &ratelimit_corrected; + else + ratelimit = &ratelimit_uncorrected; + if (__ratelimit(ratelimit)) { + __ghes_print_estatus(pfx, generic, estatus); + return 1; } + return 0; +} + +/* + * GHES error status reporting throttle, to report more kinds of + * errors, instead of just most frequently occurred errors. + */ +static int ghes_estatus_cached(struct acpi_hest_generic_status *estatus) +{ + u32 len; + int i, cached = 0; + unsigned long long now; + struct ghes_estatus_cache *cache; + struct acpi_hest_generic_status *cache_estatus; + + len = apei_estatus_len(estatus); + rcu_read_lock(); + for (i = 0; i < GHES_ESTATUS_CACHES_SIZE; i++) { + cache = rcu_dereference(ghes_estatus_caches[i]); + if (cache == NULL) + continue; + if (len != cache->estatus_len) + continue; + cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); + if (memcmp(estatus, cache_estatus, len)) + continue; + atomic_inc(&cache->count); + now = sched_clock(); + if (now - cache->time_in < GHES_ESTATUS_IN_CACHE_MAX_NSEC) + cached = 1; + break; + } + rcu_read_unlock(); + return cached; +} + +static struct ghes_estatus_cache *ghes_estatus_cache_alloc( + struct acpi_hest_generic *generic, + struct acpi_hest_generic_status *estatus) +{ + int alloced; + u32 len, cache_len; + struct ghes_estatus_cache *cache; + struct acpi_hest_generic_status *cache_estatus; + + alloced = atomic_add_return(1, &ghes_estatus_cache_alloced); + if (alloced > GHES_ESTATUS_CACHE_ALLOCED_MAX) { + atomic_dec(&ghes_estatus_cache_alloced); + return NULL; + } + len = apei_estatus_len(estatus); + cache_len = GHES_ESTATUS_CACHE_LEN(len); + cache = (void *)gen_pool_alloc(ghes_estatus_pool, cache_len); + if (!cache) { + atomic_dec(&ghes_estatus_cache_alloced); + return NULL; + } + cache_estatus = GHES_ESTATUS_FROM_CACHE(cache); + memcpy(cache_estatus, estatus, len); + cache->estatus_len = len; + atomic_set(&cache->count, 0); + cache->generic = generic; + cache->time_in = sched_clock(); + return cache; +} + +static void ghes_estatus_cache_free(struct ghes_estatus_cache *cache) +{ + u32 len; + + len = apei_estatus_len(GHES_ESTATUS_FROM_CACHE(cache)); + len = GHES_ESTATUS_CACHE_LEN(len); + gen_pool_free(ghes_estatus_pool, (unsigned long)cache, len); + atomic_dec(&ghes_estatus_cache_alloced); +} + +static void ghes_estatus_cache_rcu_free(struct rcu_head *head) |