linux/drivers/acpi/nfit/mce.c

101 lines
2.6 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0-only
/*
* NFIT - Machine Check Handler
*
* Copyright(c) 2013-2016 Intel Corporation. All rights reserved.
*/
#include <linux/notifier.h>
#include <linux/acpi.h>
#include <linux/nd.h>
#include <asm/mce.h>
#include "nfit.h"
static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
void *data)
{
struct mce *mce = (struct mce *)data;
struct acpi_nfit_desc *acpi_desc;
struct nfit_spa *nfit_spa;
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
2018-10-26 00:37:28 +00:00
/* We only care about uncorrectable memory errors */
if (!mce_is_memory_error(mce) || mce_is_correctable(mce))
return NOTIFY_DONE;
/* Verify the address reported in the MCE is valid. */
if (!mce_usable_address(mce))
return NOTIFY_DONE;
/*
* mce->addr contains the physical addr accessed that caused the
* machine check. We need to walk through the list of NFITs, and see
* if any of them matches that address, and only then start a scrub.
*/
mutex_lock(&acpi_desc_lock);
list_for_each_entry(acpi_desc, &acpi_descs, list) {
struct device *dev = acpi_desc->dev;
int found_match = 0;
mutex_lock(&acpi_desc->init_mutex);
list_for_each_entry(nfit_spa, &acpi_desc->spas, list) {
struct acpi_nfit_system_address *spa = nfit_spa->spa;
if (nfit_spa_type(spa) != NFIT_SPA_PM)
continue;
/* find the spa that covers the mce addr */
if (spa->address > mce->addr)
continue;
if ((spa->address + spa->length - 1) < mce->addr)
continue;
found_match = 1;
dev_dbg(dev, "addr in SPA %d (0x%llx, 0x%llx)\n",
spa->range_index, spa->address, spa->length);
/*
* We can break at the first match because we're going
* to rescan all the SPA ranges. There shouldn't be any
* aliasing anyway.
*/
break;
}
mutex_unlock(&acpi_desc->init_mutex);
if (!found_match)
continue;
/* If this fails due to an -ENOMEM, there is little we can do */
nvdimm_bus_add_badrange(acpi_desc->nvdimm_bus,
ALIGN(mce->addr, L1_CACHE_BYTES),
L1_CACHE_BYTES);
nvdimm_region_notify(nfit_spa->nd_region,
NVDIMM_REVALIDATE_POISON);
if (acpi_desc->scrub_mode == HW_ERROR_SCRUB_ON) {
/*
* We can ignore an -EBUSY here because if an ARS is
* already in progress, just let that be the last
* authoritative one
*/
acpi_nfit_ars_rescan(acpi_desc, 0);
}
mce->kflags |= MCE_HANDLED_NFIT;
break;
}
mutex_unlock(&acpi_desc_lock);
return NOTIFY_DONE;
}
static struct notifier_block nfit_mce_dec = {
.notifier_call = nfit_handle_mce,
.priority = MCE_PRIO_NFIT,
};
void nfit_mce_register(void)
{
mce_register_decode_chain(&nfit_mce_dec);
}
void nfit_mce_unregister(void)
{
mce_unregister_decode_chain(&nfit_mce_dec);
}