[v4,4/5] cxl/region: Add trigger_poison_list sysfs attribute

Commit Message

Alison Schofield Dec. 15, 2022, 9:17 p.m. UTC

From: Alison Schofield <[e-mail]>

When a boolean 'true' is written to this attribute the region driver
retrieves the poison list for the capacity each device contributes
to this region. The list consists of addresses that are poisoned,
or would result in poison if accessed, and the source of the poison.
The retrieved errors are logged as kernel trace events with the
label 'cxl_poison'.

Devices not supporting the poison list capability are ignored.

Reviewed-by: Jonathan Cameron <[e-mail]>
Signed-off-by: Alison Schofield <[e-mail]>
---
 Documentation/ABI/testing/sysfs-bus-cxl | 14 +++++++++++
 drivers/cxl/core/region.c               | 33 +++++++++++++++++++++++++
 2 files changed, 47 insertions(+)

Patch

diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index df40ed09ea67..b715a4609718 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -402,3 +402,17 @@  Description:
 		attribute is only visible for devices supporting the
 		capability. The retrieved errors are logged as kernel
 		trace events with the label 'cxl_poison'.
+
+
+What:		/sys/bus/cxl/devices/regionZ/trigger_poison_list
+Date:		November, 2022
+KernelVersion:	v6.2
+Contact:	[e-mail]
+Description:
+		(WO) When a boolean 'true' is written to this attribute the
+		region driver retrieves the poison list for the capacity
+		each device contributes to this region. The list consists
+		of addresses that are poisoned, or would result in poison
+		if accessed, and the source of the poison. The retrieved
+		errors are logged as kernel trace events with the label
+		'cxl_poison'.
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 02f28da519e3..62ba9aa6bbf8 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -72,6 +72,38 @@  static int is_dup(struct device *match, void *data)
 	return 0;
 }
 
+static ssize_t trigger_poison_list_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t len)
+{
+	struct cxl_region *cxlr = to_cxl_region(dev);
+	struct cxl_region_params *p = &cxlr->params;
+	struct cxl_endpoint_decoder *cxled;
+	struct cxl_memdev *cxlmd;
+	u64 offset, length;
+	int rc, i;
+	bool tmp;
+
+	if (kstrtobool(buf, &tmp))
+		return -EINVAL;
+
+	for (i = 0; i <  p->nr_targets; i++) {
+		cxled = p->targets[i];
+		cxlmd = cxled_to_memdev(cxled);
+		if (!test_bit(CXL_MEM_COMMAND_ID_GET_POISON,
+			      cxlmd->cxlds->enabled_cmds))
+			continue;
+
+		offset = cxl_dpa_resource_start(cxled);
+		length = cxl_dpa_size(cxled);
+		rc = cxl_mem_get_poison(cxlmd, offset, length, cxlr);
+		if (rc)
+			return rc;
+	}
+	return len;
+}
+static DEVICE_ATTR_WO(trigger_poison_list);
+
 static ssize_t uuid_store(struct device *dev, struct device_attribute *attr,
 			  const char *buf, size_t len)
 {
@@ -570,6 +602,7 @@  static struct attribute *cxl_region_attrs[] = {
 	&dev_attr_interleave_granularity.attr,
 	&dev_attr_resource.attr,
 	&dev_attr_size.attr,
+	&dev_attr_trigger_poison_list.attr,
 	NULL,
 };