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@xxxxxxxxxxxxxxx
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Linda Knippers <linda.knippers@xxxxxxx>
Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>
---
drivers/acpi/nfit/core.c | 23 ++++++++++++++++++++---
drivers/acpi/nfit/mce.c | 24 +++++++++++++++++++-----
drivers/acpi/nfit/nfit.h | 6 ++++++
3 files changed, 45 insertions(+), 8 deletions(-)
diff --git a/drivers/acpi/nfit/core.c b/drivers/acpi/nfit/core.c
index 80cc7c0..ec1069e 100644
--- a/drivers/acpi/nfit/core.c
+++ b/drivers/acpi/nfit/core.c
@@ -901,6 +901,14 @@ static ssize_t scrub_show(struct device *dev,
return rc;
}
+/*
+ * The 'scrub' attribute can only have following values written to it:
+ * '1': Start an on-demand scrub, and enable a full scrub to happen if a
+ * machine check exception for a memory error is received.
+ * '2': Switch to the default mode where a machine check will only insert
+ * the address on which the memory error was received into the poison
+ * and badblocks lists.
+ */
static ssize_t scrub_store(struct device *dev,
struct device_attribute *attr, const char *buf, size_t size)
{
@@ -911,15 +919,24 @@ static ssize_t scrub_store(struct device *dev,
rc = kstrtol(buf, 0, &val);
if (rc)
return rc;
- if (val != 1)
- return -EINVAL;
device_lock(dev);
nd_desc = dev_get_drvdata(dev);
if (nd_desc) {
struct acpi_nfit_desc *acpi_desc = to_acpi_desc(nd_desc);
- rc = acpi_nfit_ars_rescan(acpi_desc);
+ switch (val) {
+ case MCE_SCRUB_ON:
+ rc = acpi_nfit_ars_rescan(acpi_desc);
+ acpi_desc->scrub_mode = MCE_SCRUB_ON;
+ break;
+ case MCE_SCRUB_OFF:
+ acpi_desc->scrub_mode = MCE_SCRUB_OFF;
+ break;
+ default:
+ rc = -EINVAL;
+ break;
+ }
}
device_unlock(dev);
if (rc)
diff --git a/drivers/acpi/nfit/mce.c b/drivers/acpi/nfit/mce.c
index 161f915..05005e2 100644
--- a/drivers/acpi/nfit/mce.c
+++ b/drivers/acpi/nfit/mce.c
@@ -14,6 +14,7 @@
*/
#include <linux/notifier.h>
#include <linux/acpi.h>
+#include <linux/nd.h>
#include <asm/mce.h>
#include "nfit.h"
@@ -62,12 +63,25 @@ static int nfit_handle_mce(struct notifier_block *nb, unsigned long val,
}
mutex_unlock(&acpi_desc->init_mutex);
- /*
- * 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)
+ 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 == MCE_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);
+ }
+ break;
}
mutex_unlock(&acpi_desc_lock);
diff --git a/drivers/acpi/nfit/nfit.h b/drivers/acpi/nfit/nfit.h
index e894ded..487dc0a 100644
--- a/drivers/acpi/nfit/nfit.h
+++ b/drivers/acpi/nfit/nfit.h
@@ -152,6 +152,7 @@ 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;
@@ -159,6 +160,11 @@ struct acpi_nfit_desc {
void *iobuf, u64 len, int rw);
};
+enum scrub_mode {
+ MCE_SCRUB_ON = 1,
+ MCE_SCRUB_OFF = 2,
+};
+
enum nd_blk_mmio_selector {
BDW,
DCR,
--
2.7.4
--
To unsubscribe from this list: send the line "unsubscribe linux-acpi" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
