| Message ID | 1385099825-31765-1-git-send-email-gong.chen@linux.intel.com (mailing list archive) |
|---|---|
| State | Not Applicable, archived |
| Headers | show |
On 2013/11/22 12:57AM, Chen Gong wrote: > Usually SCI is employed to handle corrected error, especially > for memory corrected error but in fact SCI still can be used > to handle any error like memory uncorrected error if BIOS > enable it. For this situation, memory uncorrected error > should be logged as corrected error does, too. > > Signed-off-by: Chen, Gong <gong.chen@linux.intel.com> > --- > arch/x86/include/asm/mce.h | 3 +-- > arch/x86/kernel/cpu/mcheck/mce-apei.c | 6 ++---- > drivers/acpi/apei/ghes.c | 3 +-- > 3 files changed, 4 insertions(+), 8 deletions(-) > > diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h > index cbe6b9e..94b263f 100644 > --- a/arch/x86/include/asm/mce.h > +++ b/arch/x86/include/asm/mce.h > @@ -244,7 +244,6 @@ static inline void mcheck_intel_therm_init(void) { } > */ > > struct cper_sec_mem_err; > -extern void apei_mce_report_mem_error(int corrected, > - struct cper_sec_mem_err *mem_err); > +extern void apei_mce_report_mem_error(struct cper_sec_mem_err *mem_err); > > #endif /* _ASM_X86_MCE_H */ > diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c > index cd8b166..f09da48 100644 > --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c > +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c > @@ -37,13 +37,11 @@ > > #include "mce-internal.h" > > -void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) > +void apei_mce_report_mem_error(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 (!(mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) > return; This won't be enough. Further down, you'll see that all memory errors get logged as corrected errors due to the hardcoded MCE status. A lot more work will be needed if we have to log GHES errors through mcelog properly. - Naveen > > mce_setup(&m); > diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c > index 8ec37bb..039c23c 100644 > --- a/drivers/acpi/apei/ghes.c > +++ b/drivers/acpi/apei/ghes.c > @@ -453,8 +453,7 @@ static void ghes_do_proc(struct ghes *ghes, > ghes_edac_report_mem_error(ghes, sev, mem_err); > > #ifdef CONFIG_X86_MCE > - apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED, > - mem_err); > + apei_mce_report_mem_error(mem_err); > #endif > ghes_handle_memory_failure(gdata, sev); > } > -- > 1.8.4.rc3 > > -- > To unsubscribe from this list: send the line "unsubscribe linux-acpi" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html > -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Mon, Nov 25, 2013 at 11:38:23AM +0530, Naveen N. Rao wrote: > Date: Mon, 25 Nov 2013 11:38:23 +0530 > From: "Naveen N. Rao" <naveen.n.rao@linux.vnet.ibm.com> > To: "Chen, Gong" <gong.chen@linux.intel.com> > Cc: tony.luck@intel.com, bp@alien8.de, linux-acpi@vger.kernel.org > Subject: Re: [PATCH 1/2] ACPI, APEI, GHES: Remove strict check for memory > error handling > User-Agent: Mutt/1.5.21 (2010-09-15) > > On 2013/11/22 12:57AM, Chen Gong wrote: > > Usually SCI is employed to handle corrected error, especially > > for memory corrected error but in fact SCI still can be used > > to handle any error like memory uncorrected error if BIOS > > enable it. For this situation, memory uncorrected error > > should be logged as corrected error does, too. > > > > Signed-off-by: Chen, Gong <gong.chen@linux.intel.com> > > --- > > arch/x86/include/asm/mce.h | 3 +-- > > arch/x86/kernel/cpu/mcheck/mce-apei.c | 6 ++---- > > drivers/acpi/apei/ghes.c | 3 +-- > > 3 files changed, 4 insertions(+), 8 deletions(-) > > > > diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h > > index cbe6b9e..94b263f 100644 > > --- a/arch/x86/include/asm/mce.h > > +++ b/arch/x86/include/asm/mce.h > > @@ -244,7 +244,6 @@ static inline void mcheck_intel_therm_init(void) { } > > */ > > > > struct cper_sec_mem_err; > > -extern void apei_mce_report_mem_error(int corrected, > > - struct cper_sec_mem_err *mem_err); > > +extern void apei_mce_report_mem_error(struct cper_sec_mem_err *mem_err); > > > > #endif /* _ASM_X86_MCE_H */ > > diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c > > index cd8b166..f09da48 100644 > > --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c > > +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c > > @@ -37,13 +37,11 @@ > > > > #include "mce-internal.h" > > > > -void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) > > +void apei_mce_report_mem_error(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 (!(mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) > > return; > > This won't be enough. Further down, you'll see that all memory errors > get logged as corrected errors due to the hardcoded MCE status. A lot > more work will be needed if we have to log GHES errors through mcelog > properly. > > - Naveen > Sure. In fact, the most valuable information from CPER is physical address and most other data are faked or only little values. But at least we can make it more precisely.
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index cbe6b9e..94b263f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -244,7 +244,6 @@ static inline void mcheck_intel_therm_init(void) { } */ struct cper_sec_mem_err; -extern void apei_mce_report_mem_error(int corrected, - struct cper_sec_mem_err *mem_err); +extern void apei_mce_report_mem_error(struct cper_sec_mem_err *mem_err); #endif /* _ASM_X86_MCE_H */ diff --git a/arch/x86/kernel/cpu/mcheck/mce-apei.c b/arch/x86/kernel/cpu/mcheck/mce-apei.c index cd8b166..f09da48 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-apei.c +++ b/arch/x86/kernel/cpu/mcheck/mce-apei.c @@ -37,13 +37,11 @@ #include "mce-internal.h" -void apei_mce_report_mem_error(int corrected, struct cper_sec_mem_err *mem_err) +void apei_mce_report_mem_error(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 (!(mem_err->validation_bits & CPER_MEM_VALID_PHYSICAL_ADDRESS)) return; mce_setup(&m); diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c index 8ec37bb..039c23c 100644 --- a/drivers/acpi/apei/ghes.c +++ b/drivers/acpi/apei/ghes.c @@ -453,8 +453,7 @@ static void ghes_do_proc(struct ghes *ghes, ghes_edac_report_mem_error(ghes, sev, mem_err); #ifdef CONFIG_X86_MCE - apei_mce_report_mem_error(sev == GHES_SEV_CORRECTED, - mem_err); + apei_mce_report_mem_error(mem_err); #endif ghes_handle_memory_failure(gdata, sev); }
Usually SCI is employed to handle corrected error, especially for memory corrected error but in fact SCI still can be used to handle any error like memory uncorrected error if BIOS enable it. For this situation, memory uncorrected error should be logged as corrected error does, too. Signed-off-by: Chen, Gong <gong.chen@linux.intel.com> --- arch/x86/include/asm/mce.h | 3 +-- arch/x86/kernel/cpu/mcheck/mce-apei.c | 6 ++---- drivers/acpi/apei/ghes.c | 3 +-- 3 files changed, 4 insertions(+), 8 deletions(-)