We only want a machine check error to be added to libnvdimm's 'badblock'
if it was an uncorrectable error. Currently we insert both corrected and
uncorrectable errors. Add a check in the nfit mce handler to filter out
corrected mce events.
Reported-by: Omar Avelar <omar.avelar@xxxxxxxxx>
Fixes: 6839a6d96f4e ("nfit: do an ARS scrub on hitting a latent media error")
Cc: stable@xxxxxxxxxxxxxxx
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>
---
arch/x86/include/asm/mce.h | 1 +
arch/x86/kernel/cpu/mcheck/mce.c | 3 ++-
drivers/acpi/nfit/mce.c | 4 ++--
3 files changed, 5 insertions(+), 3 deletions(-)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 3a17107594c8..3111b3cee2ee 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -216,6 +216,7 @@ static inline int umc_normaddr_to_sysaddr(u64 norm_addr, u16 nid, u8 umc, u64 *s
int mce_available(struct cpuinfo_x86 *c);
bool mce_is_memory_error(struct mce *m);
+bool mce_is_correctable(struct mce *m);
DECLARE_PER_CPU(unsigned, mce_exception_count);
DECLARE_PER_CPU(unsigned, mce_poll_count);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 953b3ce92dcc..27015948bc41 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -534,7 +534,7 @@ bool mce_is_memory_error(struct mce *m)
}
EXPORT_SYMBOL_GPL(mce_is_memory_error);
-static bool mce_is_correctable(struct mce *m)
+bool mce_is_correctable(struct mce *m)
{
if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)
return false;
@@ -544,6 +544,7 @@ static bool mce_is_correctable(struct mce *m)
return true;
}
+EXPORT_SYMBOL_GPL(mce_is_correctable);
static bool cec_add_mce(struct mce *m)
{
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index e9626bf6ca29..7a51707f87e9 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -25,8 +25,8 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
struct acpi_nfit_desc *acpi_desc;
struct nfit_spa *nfit_spa;
- /* We only care about memory errors */
- if (!mce_is_memory_error(mce))
+ /* We only care about uncorrectable memory errors */
+ if (!mce_is_memory_error(mce) || mce_is_correctable(mce))
return NOTIFY_DONE;
/*
--
2.17.1
