From 4b3db708b114fc35ff1e0cd28a2bfb1490dbb5d3 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Mon, 21 Oct 2013 14:29:25 -0700 Subject: ACPI, x86: Extended error log driver for x86 platform This H/W error log driver (a.k.a eMCA driver) is implemented based on http://www.intel.com/content/www/us/en/architecture-and-technology/enhanced-mca-logging-xeon-paper.html After errors are captured, more detailed platform specific information can be got via this new enhanced H/W error log driver. Most notably we can track memory errors back to the DIMM slot silk screen label. Signed-off-by: Chen, Gong Signed-off-by: Tony Luck --- arch/x86/include/asm/mce.h | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cbe6b9e404ce..c696a8687567 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -16,6 +16,7 @@ #define MCG_EXT_CNT_SHIFT 16 #define MCG_EXT_CNT(c) (((c) & MCG_EXT_CNT_MASK) >> MCG_EXT_CNT_SHIFT) #define MCG_SER_P (1ULL<<24) /* MCA recovery/new status bits */ +#define MCG_ELOG_P (1ULL<<26) /* Extended error log supported */ /* MCG_STATUS register defines */ #define MCG_STATUS_RIPV (1ULL<<0) /* restart ip valid */ -- cgit v1.2.3 From dd6dad4288cb93e79bd7abfa6c6a338c47454d1a Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:29:25 -0700 Subject: DMI: Parse memory device (type 17) in SMBIOS This patch adds a new interface to decode memory device (type 17) to help error reporting on DIMMs. Original-author: Tony Luck Signed-off-by: Chen, Gong Acked-by: Naveen N. Rao Acked-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Signed-off-by: Tony Luck --- arch/x86/kernel/setup.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index f0de6294b955..918d489fa53d 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -993,6 +993,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); dmi_scan_machine(); + dmi_memdev_walk(); dmi_set_dump_stack_arch_desc(); /* -- cgit v1.2.3 From 147de14772ed897727dba7353916b02d1e0f17f4 Mon Sep 17 00:00:00 2001 From: "Chen, Gong" Date: Fri, 18 Oct 2013 14:30:13 -0700 Subject: ACPI, APEI, CPER: Add UEFI 2.4 support for memory error In latest UEFI spec(by now it is 2.4) memory error definition for CPER (UEFI 2.4 Appendix N Common Platform Error Record) adds some new fields. These fields help people to locate memory error to an actual DIMM location. Original-author: Tony Luck Signed-off-by: Chen, Gong Reviewed-by: Borislav Petkov Reviewed-by: Mauro Carvalho Chehab Acked-by: Naveen N. Rao Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/mcheck/mce-apei.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index cd8b166a1735..de8b60a53f69 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -42,8 +42,7 @@ void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) struct mce m; /* Only corrected MC is reported */ - if (!corrected || !(mem_err->validation_bits & - CPER_MEM_VALID_PHYSICAL_ADDRESS)) + if (!corrected || !(mem_err->validation_bits & CPER_MEM_VALID_PA)) return; mce_setup(&m); -- cgit v1.2.3