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

stellarhopper · suryasaimadhu · commit 5d96c9342c23 · 2018-11-06T19:13:10.000+01:00
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: 6839a6d ("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
@@ -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
@@ -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
@@ -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;
 
 	/*

Original file line number	Diff line number	Diff line change
`@@ -534,7 +534,7 @@ bool mce_is_memory_error(struct mce *m)`
`534`	`534`	`}`
`535`	`535`	`EXPORT_SYMBOL_GPL(mce_is_memory_error);`
`536`	`536`
`537`		`-static bool mce_is_correctable(struct mce *m)`
	`537`	`+bool mce_is_correctable(struct mce *m)`
`538`	`538`	`{`
`539`	`539`	`if (m->cpuvendor == X86_VENDOR_AMD && m->status & MCI_STATUS_DEFERRED)`
`540`	`540`	`return false;`
`@@ -547,6 +547,7 @@ static bool mce_is_correctable(struct mce *m)`
`547`	`547`
`548`	`548`	`return true;`
`549`	`549`	`}`
	`550`	`+EXPORT_SYMBOL_GPL(mce_is_correctable);`
`550`	`551`
`551`	`552`	`static bool cec_add_mce(struct mce *m)`
`552`	`553`	`{`