Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit cbd4ebcb authored by H. Peter Anvin's avatar H. Peter Anvin
Browse files

Merge tag 'please-pull-extlog-trace' into x86/ras 



Report extended error information ("extlog") using
a trace/event.  Provide a mechanism for a smart
daemon collecting this information to tell the kernel
to skip logging corrected errors to the console.

Signed-off-by: default avatarH. Peter Anvin <hpa@zytor.com>
parents 27c93415 7c76bb5f

drivers/Kconfig

+2 −0
Original line number Diff line number Diff line
@@ -176,4 +176,6 @@ source "drivers/powercap/Kconfig" 


source "drivers/mcb/Kconfig"



source "drivers/ras/Kconfig"



endmenu

drivers/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -158,3 +158,4 @@ obj-$(CONFIG_NTB) += ntb/ 
obj-$(CONFIG_FMC)		+= fmc/

obj-$(CONFIG_POWERCAP)		+= powercap/

obj-$(CONFIG_MCB)		+= mcb/

obj-$(CONFIG_RAS)		+= ras/

drivers/acpi/Kconfig

+3 −1
Original line number Diff line number Diff line
@@ -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

drivers/acpi/acpi_extlog.c

+35 −11
Original line number Diff line number Diff line
@@ -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);

drivers/edac/Kconfig

+1 −0
Original line number Diff line number Diff line
@@ -72,6 +72,7 @@ config EDAC_MCE_INJ 


config EDAC_MM_EDAC

	tristate "Main Memory EDAC (Error Detection And Correction) reporting"

	select RAS

	help

	  Some systems are able to detect and correct errors in main

	  memory.  EDAC can report statistics on memory error