[PATCH v2] EDAC: expose per-dimm error counts in sysfs

From: Aaron Miller
Date: Thu Oct 27 2016 - 17:34:59 EST


The old 'csrowX' sysfs directories had per-csrow error counters, but the
new 'dimmX' directories do not currently expose error counts.

EDAC already keeps these counts, add them to sysfs so per-dimm counts
are still available when CONFIG_EDAC_LEGACY_SYSFS=n

Signed-off-by: Aaron Miller <aaronmiller@xxxxxx>
---

Notes:
v2: Add commit messsage and documentation

Documentation/ABI/testing/sysfs-devices-edac | 17 +++++++++++++
drivers/edac/edac_mc_sysfs.c | 38 ++++++++++++++++++++++++++++
2 files changed, 55 insertions(+)

diff --git a/Documentation/ABI/testing/sysfs-devices-edac b/Documentation/ABI/testing/sysfs-devices-edac
index 6568e0010e1a..46ff929fd52a 100644
--- a/Documentation/ABI/testing/sysfs-devices-edac
+++ b/Documentation/ABI/testing/sysfs-devices-edac
@@ -138,3 +138,20 @@ Contact: Mauro Carvalho Chehab <m.chehab@xxxxxxxxxxx>
Description: This attribute file will display what type of memory is
currently on this csrow. Normally, either buffered or
unbuffered memory (for example, Unbuffered-DDR3).
+
+What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ce_count
+Date: October 2016
+Contact: linux-edac@xxxxxxxxxxxxxxx
+Description: This attribute file displays the total count of correctable
+ errors that have occurred on this DIMM. This count is very important
+ to examine. CEs provide early indications that a DIMM is beginning
+ to fail. This count field should be monitored for non-zero values
+ and report such information to the system administrator.
+
+What: /sys/devices/system/edac/mc/mc*/(dimm|rank)*/dimm_ue_count
+Date: October 2016
+Contact: linux-edac@xxxxxxxxxxxxxxx
+Description: This attribute file displays the total count of uncorrectable
+ errors that have occurred on this DIMM. If panic_on_ue is set, this
+ counter will not have a chance to increment, since EDAC will panic the
+ system
diff --git a/drivers/edac/edac_mc_sysfs.c b/drivers/edac/edac_mc_sysfs.c
index 4e0f8e720ad9..11440462a3f2 100644
--- a/drivers/edac/edac_mc_sysfs.c
+++ b/drivers/edac/edac_mc_sysfs.c
@@ -569,6 +569,40 @@ static ssize_t dimmdev_edac_mode_show(struct device *dev,
return sprintf(data, "%s\n", edac_caps[dimm->edac_mode]);
}

+static ssize_t dimmdev_ce_count_show(struct device *dev,
+ struct device_attribute *mattr,
+ char *data)
+{
+ struct dimm_info *dimm = to_dimm(dev);
+ u32 count;
+ int off;
+
+ off = EDAC_DIMM_OFF(dimm->mci->layers,
+ dimm->mci->n_layers,
+ dimm->location[0],
+ dimm->location[1],
+ dimm->location[2]);
+ count = dimm->mci->ce_per_layer[dimm->mci->n_layers-1][off];
+ return sprintf(data, "%u\n", count);
+}
+
+static ssize_t dimmdev_ue_count_show(struct device *dev,
+ struct device_attribute *mattr,
+ char *data)
+{
+ struct dimm_info *dimm = to_dimm(dev);
+ u32 count;
+ int off;
+
+ off = EDAC_DIMM_OFF(dimm->mci->layers,
+ dimm->mci->n_layers,
+ dimm->location[0],
+ dimm->location[1],
+ dimm->location[2]);
+ count = dimm->mci->ue_per_layer[dimm->mci->n_layers-1][off];
+ return sprintf(data, "%u\n", count);
+}
+
/* dimm/rank attribute files */
static DEVICE_ATTR(dimm_label, S_IRUGO | S_IWUSR,
dimmdev_label_show, dimmdev_label_store);
@@ -577,6 +611,8 @@ static DEVICE_ATTR(size, S_IRUGO, dimmdev_size_show, NULL);
static DEVICE_ATTR(dimm_mem_type, S_IRUGO, dimmdev_mem_type_show, NULL);
static DEVICE_ATTR(dimm_dev_type, S_IRUGO, dimmdev_dev_type_show, NULL);
static DEVICE_ATTR(dimm_edac_mode, S_IRUGO, dimmdev_edac_mode_show, NULL);
+static DEVICE_ATTR(dimm_ce_count, S_IRUGO, dimmdev_ce_count_show, NULL);
+static DEVICE_ATTR(dimm_ue_count, S_IRUGO, dimmdev_ue_count_show, NULL);

/* attributes of the dimm<id>/rank<id> object */
static struct attribute *dimm_attrs[] = {
@@ -586,6 +622,8 @@ static struct attribute *dimm_attrs[] = {
&dev_attr_dimm_mem_type.attr,
&dev_attr_dimm_dev_type.attr,
&dev_attr_dimm_edac_mode.attr,
+ &dev_attr_dimm_ce_count.attr,
+ &dev_attr_dimm_ue_count.attr,
NULL,
};

--
2.9.3