On 2013/07/23 01:34PM, Tony Luck wrote:
> The 0x1000 bit of the MCACOD field of machine check MCi_STATUS
> registers is only defined for corrected errors (where it means
> that hardware may be filtering errors see SDM section 15.9.2.1).
>
> For uncorrected errors it may, or may not be set - so we should mask
> it out when checking for the architecturaly defined recoverable
> error signatures (see SDM 15.9.3.1 and 15.9.3.2)
>
> While fixing this - I also noticed a bug introduced by
> commit 33d7885b594e169256daef652e8d3527b2298e75
> x86/mce: Update MCE severity condition check
> where we were including MCACOD bits in the check for the
> unaffected thread(s) during a machine check.
Good catch!
>
> Signed-off-by: Tony Luck <tony.l...@intel.com>
> ---
> arch/x86/include/asm/mce.h | 3 ++-
> arch/x86/kernel/cpu/mcheck/mce-severity.c | 8 ++++----
> 2 files changed, 6 insertions(+), 5 deletions(-)
>
> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
> index fa5f71e..a528f28 100644
> --- a/arch/x86/include/asm/mce.h
> +++ b/arch/x86/include/asm/mce.h
> @@ -33,10 +33,11 @@
> #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */
> #define MCI_STATUS_AR (1ULL<<55) /* Action required */
> #define MCACOD 0xffff /* MCA Error Code */
> +#define MCACOD_UC 0xefff /* MCA Error Code - for UC errors */
How about just changing MCACOD to 0xefff? I don't think we ever care
about the 'F' bit, so we could simplify this by just changing MCACOD.
Regards,
Naveen
>
> /* Architecturally defined codes from SDM Vol. 3B Chapter 15 */
> #define MCACOD_SCRUB 0x00C0 /* 0xC0-0xCF Memory Scrubbing */
> -#define MCACOD_SCRUBMSK 0xfff0
> +#define MCACOD_SCRUBMSK 0xeff0
> #define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */
> #define MCACOD_DATA 0x0134 /* Data Load */
> #define MCACOD_INSTR 0x0150 /* Instruction Fetch */
> diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c
> b/arch/x86/kernel/cpu/mcheck/mce-severity.c
> index e2703520..7f6ab4e 100644
> --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
> +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
> @@ -111,17 +111,17 @@ static struct severity {
> #ifdef CONFIG_MEMORY_FAILURE
> MCESEV(
> KEEP, "Action required but unaffected thread is continuable",
> - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD,
> MCI_UC_SAR|MCI_ADDR),
> + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR,
> MCI_UC_SAR|MCI_ADDR),
> MCGMASK(MCG_STATUS_RIPV, MCG_STATUS_RIPV)
> ),
> MCESEV(
> AR, "Action required: data load error in a user process",
> - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD,
> MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
> + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD_UC,
> MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
> USER
> ),
> MCESEV(
> AR, "Action required: instruction fetch error in a user
> process",
> - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD,
> MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
> + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD_UC,
> MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
> USER
> ),
> #endif
> @@ -137,7 +137,7 @@ static struct severity {
> ),
> MCESEV(
> AO, "Action optional: last level cache writeback error",
> - SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD,
> MCI_UC_S|MCACOD_L3WB)
> + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCACOD_UC,
> MCI_UC_S|MCACOD_L3WB)
> ),
> MCESEV(
> SOME, "Action optional: unknown MCACOD",
> --
> 1.8.1.4
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
