[PATCH v3] x86/mce: Do not log spurious corrected mce errors

From: Prarit Bhargava
Date: Wed Feb 19 2020 - 08:16:56 EST


A user has reported that they are seeing spurious corrected errors on
their hardware.

Intel Errata HSD131, HSM142, HSW131, and BDM48 report that
"spurious corrected errors may be logged in the IA32_MC0_STATUS register
with the valid field (bit 63) set, the uncorrected error field (bit 61)
not set, a Model Specific Error Code (bits [31:16]) of 0x000F, and
an MCA Error Code (bits [15:0]) of 0x0005." The Errata PDFs are linked in
the bugzilla below.

Block these spurious errors from the console and logs.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=206587
Co-developed-by: Alexander Krupp <centos@xxxxxxxxxxxx>
Signed-off-by: Alexander Krupp <centos@xxxxxxxxxxxx>
Signed-off-by: Prarit Bhargava <prarit@xxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
Cc: linux-edac@xxxxxxxxxxxxxxx
---
v2: Fix intel_filter_mce() declaration
v3: Fix !CONFIG_X86_MCE_INTEL compile

arch/x86/kernel/cpu/mce/core.c | 2 ++
arch/x86/kernel/cpu/mce/intel.c | 17 +++++++++++++++++
arch/x86/kernel/cpu/mce/internal.h | 5 +++++
3 files changed, 24 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2c4f949611e4..fe3983d551cc 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1877,6 +1877,8 @@ bool filter_mce(struct mce *m)
{
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
return amd_filter_mce(m);
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ return intel_filter_mce(m);

return false;
}
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index 5627b1091b85..989148e6746c 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -520,3 +520,20 @@ void mce_intel_feature_clear(struct cpuinfo_x86 *c)
{
intel_clear_lmce();
}
+
+bool intel_filter_mce(struct mce *m)
+{
+ struct cpuinfo_x86 *c = &boot_cpu_data;
+
+ /* MCE errata HSD131, HSM142, HSW131, BDM48, and HSM142 */
+ if ((c->x86 == 6) &&
+ ((c->x86_model == INTEL_FAM6_HASWELL) ||
+ (c->x86_model == INTEL_FAM6_HASWELL_L) ||
+ (c->x86_model == INTEL_FAM6_BROADWELL) ||
+ (c->x86_model == INTEL_FAM6_HASWELL_G)) &&
+ (m->bank == 0) &&
+ ((m->status & 0xa0000000ffffffff) == 0x80000000000f0005))
+ return true;
+
+ return false;
+}
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index b785c0d0b590..f6e0419969c5 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -175,5 +175,10 @@ extern bool amd_filter_mce(struct mce *m);
#else
static inline bool amd_filter_mce(struct mce *m) { return false; };
#endif
+#ifdef CONFIG_X86_MCE_INTEL
+extern bool intel_filter_mce(struct mce *m);
+#else
+static inline bool intel_filter_mce(struct mce *m) { return false; };
+#endif

#endif /* __X86_MCE_INTERNAL_H__ */
--
2.21.1