nfit: don't start a full scrub by default for an MCE

Starting a full Address Range Scrub (ARS) on hitting a memory error
machine check exception may not always be desirable. Provide a way
through sysfs to toggle the behavior between just adding the address
(cache line) where the MCE happened to the poison list and doing a full
scrub. The former (selective insertion of the address) is done
unconditionally.

Cc: linux-acpi@vger.kernel.org
Cc: Linda Knippers <linda.knippers@hpe.com>
Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Vishal Verma <vishal.l.verma@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
This commit is contained in:
Vishal Verma 2016-09-30 17:19:29 -06:00 committed by Dan Williams
parent a0056afe21
commit 9ffd6350a1
3 changed files with 78 additions and 5 deletions

View File

@ -878,6 +878,58 @@ static ssize_t revision_show(struct device *dev,
}
static DEVICE_ATTR_RO(revision);
static ssize_t hw_error_scrub_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
return sprintf(buf, "%d\n", acpi_desc->scrub_mode);
}
/*
* The 'hw_error_scrub' attribute can have the following values written to it:
* '0': Switch to the default mode where an exception will only insert
* the address of the memory error into the poison and badblocks lists.
* '1': Enable a full scrub to happen if an exception for a memory error is
* received.
*/
static ssize_t hw_error_scrub_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t size)
{
struct nvdimm_bus_descriptor *nd_desc;
ssize_t rc;
long val;
rc = kstrtol(buf, 0, &val);
if (rc)
return rc;
device_lock(dev);
nd_desc = dev_get_drvdata(dev);
if (nd_desc) {
struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
switch (val) {
case HW_ERROR_SCRUB_ON:
acpi_desc->scrub_mode = HW_ERROR_SCRUB_ON;
break;
case HW_ERROR_SCRUB_OFF:
acpi_desc->scrub_mode = HW_ERROR_SCRUB_OFF;
break;
default:
rc = -EINVAL;
break;
}
}
device_unlock(dev);
if (rc)
return rc;
return size;
}
static DEVICE_ATTR_RW(hw_error_scrub);
/*
* This shows the number of full Address Range Scrubs that have been
* completed since driver load time. Userspace can wait on this using
@ -950,6 +1002,7 @@ static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n)
static struct attribute *acpi_nfit_attributes[] = {
&dev_attr_revision.attr,
&dev_attr_scrub.attr,
&dev_attr_hw_error_scrub.attr,
NULL,
};

View File

@ -14,6 +14,7 @@
*/
#include <linux/notifier.h>
#include <linux/acpi.h>
#include <linux/nd.h>
#include <asm/mce.h>
#include "nfit.h"
@ -62,13 +63,26 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
}
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_poison(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
* We can ignore an -EBUSY here because if an ARS is
* already in progress, just let that be the last
* authoritative one
*/
if (found_match)
acpi_nfit_ars_rescan(acpi_desc);
}
break;
}
mutex_unlock(&acpi_desc_lock);
return NOTIFY_DONE;

View File

@ -161,6 +161,7 @@ struct acpi_nfit_desc {
struct list_head list;
struct kernfs_node *scrub_count_state;
unsigned int scrub_count;
unsigned int scrub_mode;
unsigned int cancel:1;
unsigned long dimm_cmd_force_en;
unsigned long bus_cmd_force_en;
@ -168,6 +169,11 @@ struct acpi_nfit_desc {
void *iobuf, u64 len, int rw);
};
enum scrub_mode {
HW_ERROR_SCRUB_OFF,
HW_ERROR_SCRUB_ON,
};
enum nd_blk_mmio_selector {
BDW,
DCR,