Normally, an ARS (Address Range Scrub) only happens at
boot/initialization time. There can however arise situations where a
bus-wide rescan is needed - notably, in the case of discovering a latent
media error, we should do a full rescan to figure out what other sectors
are bad, and thus potentially avoid triggering an mce on them in the
future. Also provide a sysfs trigger to start a bus-wide scrub.
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: <linux-acpi@xxxxxxxxxxxxxxx>
Cc: <linux-nvdimm@xxxxxxxxxxxx>
Signed-off-by: Vishal Verma <vishal.l.verma@xxxxxxxxx>
---
drivers/acpi/nfit.c | 134 +++++++++++++++++++++++++++++++++++++++++++---
drivers/acpi/nfit.h | 4 +-
drivers/nvdimm/core.c | 7 +++
include/linux/libnvdimm.h | 1 +
4 files changed, 138 insertions(+), 8 deletions(-)
diff --git a/drivers/acpi/nfit.c b/drivers/acpi/nfit.c
index c0e1c3a..6e45183 100644
--- a/drivers/acpi/nfit.c
+++ b/drivers/acpi/nfit.c
@@ -15,6 +15,7 @@
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/ndctl.h>
+#include <linux/sysfs.h>
#include <linux/delay.h>
#include <linux/list.h>
#include <linux/acpi.h>
@@ -874,14 +875,76 @@ static ssize_t revision_show(struct device *dev,
}
static DEVICE_ATTR_RO(revision);
+/*
+ * This shows the number of full Address Range Scrubs that have been
+ * completed since driver load time. Userspace can wait on this using
+ * select/poll etc. A '+' at the end indicates an ARS is in progress
+ */
+static ssize_t 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%s", acpi_desc->scrub_count,
+ (work_busy(&acpi_desc->work)) ? "+\n" : "\n");
+}
+
+static int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc);
+
+static ssize_t scrub_store(struct device *dev,
+ struct device_attribute *attr, const char *buf, size_t size)
+{
+ 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);
+ int rc;
+
+ rc = acpi_nfit_ars_rescan(acpi_desc);
+ if (rc)
+ return rc;
+ return size;
+}
+static DEVICE_ATTR_RW(scrub);
+
+static bool acpi_nfit_ars_supported(struct nvdimm_bus *nvdimm_bus)
+{
+ struct nvdimm_bus_descriptor *nd_desc = to_nd_desc(nvdimm_bus);
+
+ if (test_bit(ND_CMD_ARS_CAP, &nd_desc->cmd_mask))
+ return true;
+
+ return false;
+}
+
+static umode_t nfit_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+ struct device *dev = container_of(kobj, struct device, kobj);
+ struct nvdimm_bus *nvdimm_bus = to_nvdimm_bus(dev);
+
+ if (a == &dev_attr_revision.attr)
+ return a->mode;
+
+ /* check if scrub is supported */
+ if (a == &dev_attr_scrub.attr) {
+ if (!acpi_nfit_ars_supported(nvdimm_bus))
+ return 0;
+ }
+
+ return a->mode;
+}
+
static struct attribute *acpi_nfit_attributes[] = {
&dev_attr_revision.attr,
+ &dev_attr_scrub.attr,
NULL,
};
static struct attribute_group acpi_nfit_attribute_group = {
.name = "nfit",
.attrs = acpi_nfit_attributes,
+ .is_visible = nfit_visible,
};
static const struct attribute_group *acpi_nfit_attribute_groups[] = {
@@ -2055,7 +2118,7 @@ static void acpi_nfit_async_scrub(struct acpi_nfit_desc *acpi_desc,
unsigned int tmo = scrub_timeout;
int rc;
- if (nfit_spa->ars_done || !nfit_spa->nd_region)
+ if (!nfit_spa->ars_required || !nfit_spa->nd_region)
return;
rc = ars_start(acpi_desc, nfit_spa);
@@ -2144,7 +2207,9 @@ static void acpi_nfit_scrub(struct work_struct *work)
* firmware initiated scrubs to complete and then we go search for the
* affected spa regions to mark them scanned. In the second phase we
* initiate a directed scrub for every range that was not scrubbed in
- * phase 1.
+ * phase 1. If we're called for a 'rescan', we harmlessly pass through
+ * the first phase, but really only care about running phase 2, where
+ * regions can be notified of new poison.
*/
/* process platform firmware initiated scrubs */
@@ -2247,14 +2312,17 @@ static void acpi_nfit_scrub(struct work_struct *work)
* Flag all the ranges that still need scrubbing, but
* register them now to make data available.
*/
- if (nfit_spa->nd_region)
- nfit_spa->ars_done = 1;
- else
+ if (!nfit_spa->nd_region) {
+ nfit_spa->ars_required = 1;
acpi_nfit_register_region(acpi_desc, nfit_spa);
+ }
}
list_for_each_entry(nfit_spa, &acpi_desc->spas, list)
acpi_nfit_async_scrub(acpi_desc, nfit_spa);
+ acpi_desc->scrub_count++;
+ if (acpi_desc->scrub_count_state)
+ sysfs_notify_dirent(acpi_desc->scrub_count_state);
mutex_unlock(&acpi_desc->init_mutex);
}
@@ -2292,12 +2360,39 @@ static int acpi_nfit_check_deletions(struct acpi_nfit_desc *acpi_desc,
return 0;
}
+static int acpi_nfit_desc_init_scrub_attr(struct acpi_nfit_desc *acpi_desc)
+{
+ struct device *dev = acpi_desc->dev;
+
+ if (acpi_nfit_ars_supported(acpi_desc->nvdimm_bus)) {
+ struct kernfs_node *nfit;
+ struct device *bus_dev;
+
+ bus_dev = to_nvdimm_bus_dev(acpi_desc->nvdimm_bus);
+ nfit = sysfs_get_dirent(bus_dev->kobj.sd, "nfit");
+ if (!nfit) {
+ dev_err(dev, "sysfs_get_dirent 'nfit' failed\n");
+ return -ENODEV;
+ }
+ acpi_desc->scrub_count_state = sysfs_get_dirent(nfit, "scrub");
+ sysfs_put(nfit);
+ if (!acpi_desc->scrub_count_state) {
+ dev_err(dev, "sysfs_get_dirent 'scrub' failed\n");
+ return -ENODEV;
+ }
+ }
+
+ return 0;
+}
+
static void acpi_nfit_destruct(void *data)
{
struct acpi_nfit_desc *acpi_desc = data;
acpi_desc->cancel = 1;
flush_workqueue(nfit_wq);
+ if (acpi_desc->scrub_count_state)
+ sysfs_put(acpi_desc->scrub_count_state);
nvdimm_bus_unregister(acpi_desc->nvdimm_bus);
acpi_desc->nvdimm_bus = NULL;
}
@@ -2309,6 +2404,8 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz)
const void *end;
int rc;
+ acpi_nfit_init_dsms(acpi_desc);
+
if (!acpi_desc->nvdimm_bus) {
acpi_desc->nvdimm_bus = nvdimm_bus_register(dev,
&acpi_desc->nd_desc);
@@ -2320,6 +2417,10 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz)
return rc;
}
+ rc = acpi_nfit_desc_init_scrub_attr(acpi_desc);
+ if (rc)
+ return rc;
+
mutex_lock(&acpi_desc->init_mutex);
INIT_LIST_HEAD(&prev.spas);
@@ -2361,8 +2462,6 @@ int acpi_nfit_init(struct acpi_nfit_desc *acpi_desc, void *data, acpi_size sz)
if (rc)
goto out_unlock;
- acpi_nfit_init_dsms(acpi_desc);
-
rc = acpi_nfit_register_dimms(acpi_desc);
if (rc)
goto out_unlock;
@@ -2430,6 +2529,27 @@ static int acpi_nfit_clear_to_send(struct nvdimm_bus_descriptor *nd_desc,
return 0;
}
+static int acpi_nfit_ars_rescan(struct acpi_nfit_desc *acpi_desc)
+{
+ struct device *dev = acpi_desc->dev;
+ struct nfit_spa *nfit_spa;
+
+ if (work_busy(&acpi_desc->work))
+ return -EBUSY;
+
+ 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;
+
+ nfit_spa->ars_required = 1;
+ }
+ queue_work(nfit_wq, &acpi_desc->work);
+ dev_info(dev, "%s: ars_scan triggered\n", __func__);
+ return 0;
+}
+
void acpi_nfit_desc_init(struct acpi_nfit_desc *acpi_desc, struct device *dev)
{
struct nvdimm_bus_descriptor *nd_desc;
diff --git a/drivers/acpi/nfit.h b/drivers/acpi/nfit.h
index 9696e7a..33fc2e9 100644
--- a/drivers/acpi/nfit.h
+++ b/drivers/acpi/nfit.h
@@ -80,7 +80,7 @@ enum {
struct nfit_spa {
struct list_head list;
struct nd_region *nd_region;
- unsigned int ars_done:1;
+ unsigned int ars_required:1;
u32 clear_err_unit;
u32 max_ars;
struct acpi_nfit_system_address spa[0];
@@ -148,6 +148,8 @@ struct acpi_nfit_desc {
struct nd_cmd_ars_status *ars_status;
size_t ars_status_size;
struct work_struct work;
+ struct kernfs_node *scrub_count_state;
+ unsigned int scrub_count;
unsigned int cancel:1;
unsigned long dimm_cmd_force_en;
unsigned long bus_cmd_force_en;
diff --git a/drivers/nvdimm/core.c b/drivers/nvdimm/core.c
index e852875..c128674 100644
--- a/drivers/nvdimm/core.c
+++ b/drivers/nvdimm/core.c
@@ -221,6 +221,13 @@ struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus)
}
EXPORT_SYMBOL_GPL(to_nd_desc);
+struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus)
+{
+ /* struct nvdimm_bus definition is private to libnvdimm */
+ return &nvdimm_bus->dev;
+}
+EXPORT_SYMBOL_GPL(to_nvdimm_bus_dev);
+
struct nvdimm_bus *walk_to_nvdimm_bus(struct device *nd_dev)
{
struct device *dev;
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index 2ab869d..b519e13 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -137,6 +137,7 @@ struct nvdimm *to_nvdimm(struct device *dev);
struct nd_region *to_nd_region(struct device *dev);
struct nd_blk_region *to_nd_blk_region(struct device *dev);
struct nvdimm_bus_descriptor *to_nd_desc(struct nvdimm_bus *nvdimm_bus);
+struct device *to_nvdimm_bus_dev(struct nvdimm_bus *nvdimm_bus);
const char *nvdimm_name(struct nvdimm *nvdimm);
unsigned long nvdimm_cmd_mask(struct nvdimm *nvdimm);
void *nvdimm_provider_data(struct nvdimm *nvdimm);
--
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
