acpi/nfit, x86/mce: Handle only uncorrectable machine checks

The MCE handler for nfit devices is called for memory errors on a
Non-Volatile DIMM and adds the error location to a 'badblocks' list.
This list is used by the various NVDIMM drivers to avoid consuming known
poison locations during IO.

The MCE handler gets called for both corrected and uncorrectable errors.
Until now, both kinds of errors have been added to the badblocks list.
However, corrected memory errors indicate that the problem has already
been fixed by hardware, and the resulting interrupt is merely a
notification to Linux.

As far as future accesses to that location are concerned, it is
perfectly fine to use, and thus doesn't need to be included in the above
badblocks list.

Add a check in the nfit MCE handler to filter out corrected mce events,
and only process uncorrectable errors.

Fixes: 6839a6d96f4e ("nfit: do an ARS scrub on hitting a latent media error")
Reported-by: Omar Avelar <omar.avelar@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
CC: Arnd Bergmann <arnd@arndb.de>
CC: Dan Williams <dan.j.williams@intel.com>
CC: Dave Jiang <dave.jiang@intel.com>
CC: elliott@hpe.com
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Ingo Molnar <mingo@redhat.com>
CC: Len Brown <lenb@kernel.org>
CC: linux-acpi@vger.kernel.org
CC: linux-edac <linux-edac@vger.kernel.org>
CC: linux-nvdimm@lists.01.org
CC: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
CC: "Rafael J. Wysocki" <rjw@rjwysocki.net>
CC: Ross Zwisler <zwisler@kernel.org>
CC: stable <stable@vger.kernel.org>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Tony Luck <tony.luck@intel.com>
CC: x86-ml <x86@kernel.org>
CC: Yazen Ghannam <yazen.ghannam@amd.com>
Link: http://lkml.kernel.org/r/20181026003729.8420-1-vishal.l.verma@intel.com

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 4da9b1c58d287bbdda427e31dd67a1653b519043..dbd9fe2f6163d59e86430c5a471fdb66460c553e 100644 (file)
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -221,6 +221,7 @@ static inline void mce_hygon_feature_init(struct cpuinfo_x86 *c) { return mce_am
 
 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 8c66d2fc8f81dd1d2404f22e5a06ac696ee8fad9..77527b8ea982a1947521bb30b1715c14d4be9232 100644 (file)
--- 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;
@@ -547,6 +547,7 @@ 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 e9626bf6ca2960a2398aeeefc0f4c9e814e60c1b..7a51707f87e95de5ea6cc4e10392b0ffffdbcc79 100644 (file)
--- 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;
 
        /*