Merge tag 'please-pull-mce-f-bit' of git://git.kernel.org/pub/scm/linux/kernel/git/ras/ras into x86/ras

Pull MCE-uncorrected-error fix from Tony Luck:

 "Bit 12 may or may not be set in MCi_STATUS.MCACOD when
  an uncorrected error is reported. Ignore it when checking
  error signatures."

Signed-off-by: Ingo Molnar <mingo@kernel.org>

3 files changed, 14 insertions, 4 deletions

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 163d7a4451f0..cbe6b9e404ce 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 */
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",
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 <linux/kernel.h>
 #include <linux/irq.h>
 #include <linux/module.h>
+#include <linux/reboot.h>
 #include <linux/serial_reg.h>
 #include <linux/serial_8250.h>
 #include <linux/reboot.h>