diff options
author | Huang Ying <ying.huang@intel.com> | 2016-06-29 22:04:29 +0200 |
---|---|---|
committer | Rafael J. Wysocki <rafael.j.wysocki@intel.com> | 2016-06-29 23:35:05 +0200 |
commit | a3e2acc5e37b22b6808a0b8e46887c3577de9c9e (patch) | |
tree | e5d8f83cee1504d31d034df5f63283b0f98094ca /drivers/acpi/apei | |
parent | ACPI / einj: Make error paths more talkative (diff) | |
download | linux-a3e2acc5e37b22b6808a0b8e46887c3577de9c9e.tar.xz linux-a3e2acc5e37b22b6808a0b8e46887c3577de9c9e.zip |
ACPI / APEI: Add Boot Error Record Table (BERT) support
ACPI/APEI is designed to verifiy/report H/W errors, like Corrected
Error(CE) and Uncorrected Error(UC). It contains four tables: HEST,
ERST, EINJ and BERT. The first three tables have been merged for
a long time, but because of lacking BIOS support for BERT, the
support for BERT is pending until now. Recently on ARM 64 platform
it is has been supported. So here we come.
Under normal circumstances, when a hardware error occurs, kernel will
be notified via NMI, MCE or some other method, then kernel will
process the error condition, report it, and recover it if possible.
But sometime, the situation is so bad, so that firmware may choose to
reset directly without notifying Linux kernel.
Linux kernel can use the Boot Error Record Table (BERT) to get the
un-notified hardware errors that occurred in a previous boot. In this
patch, the error information is reported via printk.
For more information about BERT, please refer to ACPI Specification
version 6.0, section 18.3.1:
http://www.uefi.org/sites/default/files/resources/ACPI_6.0.pdf
The following log is a BERT record after system reboot because of hitting
a fatal memory error:
BERT: Error records from previous boot:
[Hardware Error]: It has been corrected by h/w and requires no further action
[Hardware Error]: event severity: corrected
[Hardware Error]: Error 0, type: recoverable
[Hardware Error]: section_type: memory error
[Hardware Error]: error_status: 0x0000000000000400
[Hardware Error]: physical_address: 0xffffffffffffffff
[Hardware Error]: card: 1 module: 2 bank: 3 row: 1 column: 2 bit_position: 5
[Hardware Error]: error_type: 2, single-bit ECC
[Tomasz Nowicki: Clear error status at the end of error handling]
[Tony: Applied some cleanups suggested by Fu Wei]
[Fu Wei: delete EXPORT_SYMBOL_GPL(bert_disable), improve the code]
Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Tomasz Nowicki <tomasz.nowicki@linaro.org>
Signed-off-by: Chen, Gong <gong.chen@linux.intel.com>
Tested-by: Jonathan (Zhixiong) Zhang <zjzhang@codeaurora.org>
Signed-off-by: Fu Wei <fu.wei@linaro.org>
Tested-by: Tyler Baicar <tbaicar@codeaurora.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Diffstat (limited to 'drivers/acpi/apei')
-rw-r--r-- | drivers/acpi/apei/Makefile | 2 | ||||
-rw-r--r-- | drivers/acpi/apei/apei-internal.h | 2 | ||||
-rw-r--r-- | drivers/acpi/apei/bert.c | 150 |
3 files changed, 152 insertions, 2 deletions
diff --git a/drivers/acpi/apei/Makefile b/drivers/acpi/apei/Makefile index 5d575a955940..e50573de25f1 100644 --- a/drivers/acpi/apei/Makefile +++ b/drivers/acpi/apei/Makefile @@ -3,4 +3,4 @@ obj-$(CONFIG_ACPI_APEI_GHES) += ghes.o obj-$(CONFIG_ACPI_APEI_EINJ) += einj.o obj-$(CONFIG_ACPI_APEI_ERST_DEBUG) += erst-dbg.o -apei-y := apei-base.o hest.o erst.o +apei-y := apei-base.o hest.o erst.o bert.o diff --git a/drivers/acpi/apei/apei-internal.h b/drivers/acpi/apei/apei-internal.h index 16129c78b489..6e9f14c0a71b 100644 --- a/drivers/acpi/apei/apei-internal.h +++ b/drivers/acpi/apei/apei-internal.h @@ -1,6 +1,6 @@ /* * apei-internal.h - ACPI Platform Error Interface internal - * definations. + * definitions. */ #ifndef APEI_INTERNAL_H diff --git a/drivers/acpi/apei/bert.c b/drivers/acpi/apei/bert.c new file mode 100644 index 000000000000..a05b5c0cf181 --- /dev/null +++ b/drivers/acpi/apei/bert.c @@ -0,0 +1,150 @@ +/* + * APEI Boot Error Record Table (BERT) support + * + * Copyright 2011 Intel Corp. + * Author: Huang Ying <ying.huang@intel.com> + * + * Under normal circumstances, when a hardware error occurs, the error + * handler receives control and processes the error. This gives OSPM a + * chance to process the error condition, report it, and optionally attempt + * recovery. In some cases, the system is unable to process an error. + * For example, system firmware or a management controller may choose to + * reset the system or the system might experience an uncontrolled crash + * or reset.The boot error source is used to report unhandled errors that + * occurred in a previous boot. This mechanism is described in the BERT + * table. + * + * For more information about BERT, please refer to ACPI Specification + * version 4.0, section 17.3.1 + * + * This file is licensed under GPLv2. + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/acpi.h> +#include <linux/io.h> + +#include "apei-internal.h" + +#undef pr_fmt +#define pr_fmt(fmt) "BERT: " fmt + +static int bert_disable; + +static void __init bert_print_all(struct acpi_bert_region *region, + unsigned int region_len) +{ + struct acpi_hest_generic_status *estatus = + (struct acpi_hest_generic_status *)region; + int remain = region_len; + u32 estatus_len; + + if (!estatus->block_status) + return; + + while (remain > sizeof(struct acpi_bert_region)) { + if (cper_estatus_check(estatus)) { + pr_err(FW_BUG "Invalid error record.\n"); + return; + } + + estatus_len = cper_estatus_len(estatus); + if (remain < estatus_len) { + pr_err(FW_BUG "Truncated status block (length: %u).\n", + estatus_len); + return; + } + + pr_info_once("Error records from previous boot:\n"); + + cper_estatus_print(KERN_INFO HW_ERR, estatus); + + /* + * Because the boot error source is "one-time polled" type, + * clear Block Status of current Generic Error Status Block, + * once it's printed. + */ + estatus->block_status = 0; + + estatus = (void *)estatus + estatus_len; + /* No more error records. */ + if (!estatus->block_status) + return; + + remain -= estatus_len; + } +} + +static int __init setup_bert_disable(char *str) +{ + bert_disable = 1; + + return 0; +} +__setup("bert_disable", setup_bert_disable); + +static int __init bert_check_table(struct acpi_table_bert *bert_tab) +{ + if (bert_tab->header.length < sizeof(struct acpi_table_bert) || + bert_tab->region_length < sizeof(struct acpi_bert_region)) + return -EINVAL; + + return 0; +} + +static int __init bert_init(void) +{ + struct acpi_bert_region *boot_error_region; + struct acpi_table_bert *bert_tab; + unsigned int region_len; + acpi_status status; + int rc = 0; + + if (acpi_disabled) + return 0; + + if (bert_disable) { + pr_info("Boot Error Record Table support is disabled.\n"); + return 0; + } + + status = acpi_get_table(ACPI_SIG_BERT, 0, (struct acpi_table_header **)&bert_tab); + if (status == AE_NOT_FOUND) + return 0; + + if (ACPI_FAILURE(status)) { + pr_err("get table failed, %s.\n", acpi_format_exception(status)); + return -EINVAL; + } + + rc = bert_check_table(bert_tab); + if (rc) { + pr_err(FW_BUG "table invalid.\n"); + return rc; + } + + region_len = bert_tab->region_length; + if (!request_mem_region(bert_tab->address, region_len, "APEI BERT")) { + pr_err("Can't request iomem region <%016llx-%016llx>.\n", + (unsigned long long)bert_tab->address, + (unsigned long long)bert_tab->address + region_len - 1); + return -EIO; + } + + boot_error_region = ioremap_cache(bert_tab->address, region_len); + if (boot_error_region) { + bert_print_all(boot_error_region, region_len); + iounmap(boot_error_region); + } else { + rc = -ENOMEM; + } + + release_mem_region(bert_tab->address, region_len); + + return rc; +} + +late_initcall(bert_init); |