x86/mce: Improve error message when kernel cannot recover

aegl · KAGA-KOKO · commit c7d606f560e4 · 2018-06-07T22:22:12.000+02:00
Since we added support to add recovery from some errors inside the kernel in: commit b2f9d67 ("x86/mce: Check for faults tagged in EXTABLE_CLASS_FAULT exception table entries") we have done a less than stellar job at reporting the cause of recoverable machine checks that occur in other parts of the kernel. The user just gets the unhelpful message: mce: [Hardware Error]: Machine check: Action required: unknown MCACOD doubly unhelpful when they check the manual for the reported IA32_MSR_STATUS.MCACOD and see that it is listed as one of the standard recoverable values. Add an extra rule to the MCE severity table to catch this case and report it as: mce: [Hardware Error]: Machine check: Data load in unrecoverable area of kernel Fixes: b2f9d67 ("x86/mce: Check for faults tagged in EXTABLE_CLASS_FAULT exception table entries") Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: stable@vger.kernel.org # 4.6+ Cc: Dan Williams <dan.j.williams@intel.com> Cc: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/4cc7c465150a9a48b8b9f45d0b840278e77eb9b5.1527283897.git.tony.luck@intel.com
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -160,6 +160,11 @@ static struct severity {
 		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
 		USER
 		),
+	MCESEV(
+		PANIC, "Data load in unrecoverable area of kernel",
+		SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+		KERNEL
+		),
 #endif
 	MCESEV(
 		PANIC, "Action required: unknown MCACOD",
