From 1a7f0e3c4fff449f6dd08787beb98a8e57d8cdc7 Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 24 Jul 2013 10:09:43 -0700 Subject: x86/mce: Fix mce regression from recent cleanup In commit 33d7885b594e169256daef652e8d3527b2298e75 x86/mce: Update MCE severity condition check We simplified the rules to recognise each classification of recoverable machine check combining the instruction and data fetch rules into a single entry based on clarifications in the June 2013 SDM that all recoverable events would be reported on the unaffected processor with MCG_STATUS.EIPV=0 and MCG_STATUS.RIPV=1. Unfortunately the simplified rule has a couple of bugs. Fix them here. Acked-by: Naveen N. Rao Signed-off-by: Tony Luck --- arch/x86/kernel/cpu/mcheck/mce-severity.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c index e2703520d120..c370e1c4468b 100644 --- a/arch/x86/kernel/cpu/mcheck/mce-severity.c +++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c @@ -111,8 +111,8 @@ 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), - MCGMASK(MCG_STATUS_RIPV, MCG_STATUS_RIPV) + SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR, MCI_UC_SAR|MCI_ADDR), + MCGMASK(MCG_STATUS_RIPV|MCG_STATUS_EIPV, MCG_STATUS_RIPV) ), MCESEV( AR, "Action required: data load error in a user process", -- cgit v1.2.2 From 31a1b26f16e822577def5402ffc79cfe4aed2db9 Mon Sep 17 00:00:00 2001 From: Andrew Morton Date: Wed, 31 Jul 2013 13:53:36 -0700 Subject: arch/x86/platform/ce4100/ce4100.c: include reboot.h Fix the build: arch/x86/platform/ce4100/ce4100.c: In function 'x86_ce4100_early_setup': arch/x86/platform/ce4100/ce4100.c:165:2: error: 'reboot_type' undeclared (first use in this function) Reported-by: Wu Fengguang Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H. Peter Anvin" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/x86/platform/ce4100/ce4100.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/x86') diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c index 643b8b5eee86..8244f5ec2f4c 100644 --- a/arch/x86/platform/ce4100/ce4100.c +++ b/arch/x86/platform/ce4100/ce4100.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include #include -- cgit v1.2.2 From 0ca06c0857aee11911f91621db14498496f2c2cd Mon Sep 17 00:00:00 2001 From: Tony Luck Date: Wed, 24 Jul 2013 13:54:20 -0700 Subject: x86/mce: Pay no attention to 'F' bit in MCACOD when parsing 'UC' errors 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) Acked-by: Naveen N. Rao Signed-off-by: Tony Luck --- arch/x86/include/asm/mce.h | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 29e3093bbd21..aa97342e7ca0 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -32,11 +32,20 @@ #define MCI_STATUS_PCC (1ULL<<57) /* processor context corrupt */ #define MCI_STATUS_S (1ULL<<56) /* Signaled machine check */ #define MCI_STATUS_AR (1ULL<<55) /* Action required */ -#define MCACOD 0xffff /* MCA Error Code */ + +/* + * Note that the full MCACOD field of IA32_MCi_STATUS MSR is + * bits 15:0. But bit 12 is the 'F' bit, defined for corrected + * errors to indicate that errors are being filtered by hardware. + * We should mask out bit 12 when looking for specific signatures + * of uncorrected errors - so the F bit is deliberately skipped + * in this #define. + */ +#define MCACOD 0xefff /* MCA Error Code */ /* 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 /* Skip bit 12 ('F' bit) */ #define MCACOD_L3WB 0x017A /* L3 Explicit Writeback */ #define MCACOD_DATA 0x0134 /* Data Load */ #define MCACOD_INSTR 0x0150 /* Instruction Fetch */ -- cgit v1.2.2