[v2,3/4] cxl/memdev: Add trigger_poison_list sysfs attribute

Commit Message

Alison Schofield Oct. 12, 2022, 9:28 p.m. UTC

From: Alison Schofield <[e-mail]>

When a boolean 'true' is written to this attribute the memdev driver
retrieves the poison list from the device. The list includes addresses
that are poisoned, or would result in poison if accessed, and the
source of the poison. This attribute is only visible for devices
supporting the capability. The retrieved errors are logged as kernel
trace events with the label 'cxl_poison'.

Signed-off-by: Alison Schofield <[e-mail]>
---
 Documentation/ABI/testing/sysfs-bus-cxl | 14 +++++++++
 drivers/cxl/core/memdev.c               | 41 +++++++++++++++++++++++++
 2 files changed, 55 insertions(+)

Patch

diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
index 0debe2955f34..ab3665f8738e 100644
--- a/Documentation/ABI/testing/sysfs-bus-cxl
+++ b/Documentation/ABI/testing/sysfs-bus-cxl
@@ -354,3 +354,17 @@  Description:
 		1), and checks that the hardware accepts the commit request.
 		Reading this value indicates whether the region is committed or
 		not.
+
+
+What:		/sys/bus/cxl/devices/memX/trigger_poison_list
+Date:		October, 2022
+KernelVersion:	v6.2
+Contact:	[e-mail]
+Description:
+		(WO) When a boolean 'true' is written to this attribute the
+		memdev driver retrieves the poison list from the device. The
+		list includes addresses that are poisoned or would result in
+		poison if accessed, and the source of the poison. This
+		attribute is only visible for devices supporting the
+		capability. The retrieved errors are logged as kernel
+		trace events with the label 'cxl_poison'.
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index 20ce488a7754..06d265db5127 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -106,12 +106,45 @@  static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(numa_node);
 
+static ssize_t trigger_poison_list_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t len)
+{
+	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	u64 offset, length;
+	bool tmp;
+	int rc;
+
+	if (kstrtobool(buf, &tmp))
+		return -EINVAL;
+
+	/* Per CXL Spec, separate the pmem and ram poison list reads */
+	if (resource_size(&cxlds->pmem_res)) {
+		offset = cxlds->pmem_res.start;
+		length = resource_size(&cxlds->pmem_res);
+		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
+		if (rc)
+			return rc;
+	}
+	if (resource_size(&cxlds->ram_res)) {
+		offset = cxlds->ram_res.start;
+		length = resource_size(&cxlds->ram_res);
+		rc = cxl_mem_get_poison(cxlmd, offset, length, NULL);
+		if (rc)
+			return rc;
+	}
+	return len;
+}
+static DEVICE_ATTR_WO(trigger_poison_list);
+
 static struct attribute *cxl_memdev_attributes[] = {
 	&dev_attr_serial.attr,
 	&dev_attr_firmware_version.attr,
 	&dev_attr_payload_max.attr,
 	&dev_attr_label_storage_size.attr,
 	&dev_attr_numa_node.attr,
+	&dev_attr_trigger_poison_list.attr,
 	NULL,
 };
 
@@ -130,6 +163,14 @@  static umode_t cxl_memdev_visible(struct kobject *kobj, struct attribute *a,
 {
 	if (!IS_ENABLED(CONFIG_NUMA) && a == &dev_attr_numa_node.attr)
 		return 0;
+
+	if (a == &dev_attr_trigger_poison_list.attr) {
+		struct device *dev = kobj_to_dev(kobj);
+
+		if (!test_bit(CXL_MEM_COMMAND_ID_GET_POISON,
+			      to_cxl_memdev(dev)->cxlds->enabled_cmds))
+			return 0;
+	}
 	return a->mode;
 }