cxl/memdev: Add trigger_poison_list sysfs attribute

When a boolean 'true' is written to this attribute the memdev driver
retrieves the poison list from the device. The list consists of
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 events when cxl_poison event tracing is enabled.

Signed-off-by: Alison Schofield <alison.schofield@intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Link: https://lore.kernel.org/r/1081cfdc8a349dc754779642d584707e56db26ba.1681838291.git.alison.schofield@intel.com
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>

Author: AlisonSchofield

Documentation/ABI/testing/sysfs-bus-cxl

@@ -415,3 +415,17 @@ 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:		April, 2023
+KernelVersion:	v6.4
+Contact:	linux-cxl@vger.kernel.org
+Description:
+		(WO) When a boolean 'true' is written to this attribute the
+		memdev driver retrieves the poison list from the device. The
+		list consists of 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
+		events when cxl_poison event tracing is enabled.

drivers/cxl/core/memdev.c

@@ -106,6 +106,49 @@ static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
 }
 static DEVICE_ATTR_RO(numa_node);
 
+static int cxl_get_poison_by_memdev(struct cxl_memdev *cxlmd)
+{
+	struct cxl_dev_state *cxlds = cxlmd->cxlds;
+	u64 offset, length;
+	int rc = 0;
+
+	/* CXL 3.0 Spec 8.2.9.8.4.1 Separate pmem and ram poison requests */
+	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);
+		/*
+		 * Invalid Physical Address is not an error for
+		 * volatile addresses. Device support is optional.
+		 */
+		if (rc == -EFAULT)
+			rc = 0;
+	}
+	return rc;
+}
+
+int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
+{
+	int rc;
+
+	rc = down_read_interruptible(&cxl_dpa_rwsem);
+	if (rc)
+		return rc;
+
+	rc = cxl_get_poison_by_memdev(cxlmd);
+	up_read(&cxl_dpa_rwsem);
+
+	return rc;
+}
+EXPORT_SYMBOL_NS_GPL(cxl_trigger_poison_list, CXL);
+
 static struct attribute *cxl_memdev_attributes[] = {
 	&dev_attr_serial.attr,
 	&dev_attr_firmware_version.attr,

drivers/cxl/cxlmem.h

@@ -145,7 +145,7 @@ struct cxl_mbox_cmd {
 	C(FWROLLBACK, -ENXIO, "rolled back to the previous active FW"),         \
 	C(FWRESET, -ENXIO, "FW failed to activate, needs cold reset"),		\
 	C(HANDLE, -ENXIO, "one or more Event Record Handles were invalid"),     \
-	C(PADDR, -ENXIO, "physical address specified is invalid"),		\
+	C(PADDR, -EFAULT, "physical address specified is invalid"),		\
 	C(POISONLMT, -ENXIO, "poison injection limit has been reached"),        \
 	C(MEDIAFAILURE, -ENXIO, "permanent issue with the media"),		\
 	C(ABORT, -ENXIO, "background cmd was aborted by device"),               \
@@ -688,6 +688,7 @@ int cxl_set_timestamp(struct cxl_dev_state *cxlds);
 int cxl_poison_state_init(struct cxl_dev_state *cxlds);
 int cxl_mem_get_poison(struct cxl_memdev *cxlmd, u64 offset, u64 len,
 		       struct cxl_region *cxlr);
+int cxl_trigger_poison_list(struct cxl_memdev *cxlmd);
 
 #ifdef CONFIG_CXL_SUSPEND
 void cxl_mem_active_inc(void);

drivers/cxl/mem.c

@@ -176,10 +176,53 @@ static int cxl_mem_probe(struct device *dev)
 	return devm_add_action_or_reset(dev, enable_suspend, NULL);
 }
 
+static ssize_t trigger_poison_list_store(struct device *dev,
+					 struct device_attribute *attr,
+					 const char *buf, size_t len)
+{
+	bool trigger;
+	int rc;
+
+	if (kstrtobool(buf, &trigger) || !trigger)
+		return -EINVAL;
+
+	rc = cxl_trigger_poison_list(to_cxl_memdev(dev));
+
+	return rc ? rc : len;
+}
+static DEVICE_ATTR_WO(trigger_poison_list);
+
+static umode_t cxl_mem_visible(struct kobject *kobj, struct attribute *a, int n)
+{
+	if (a == &dev_attr_trigger_poison_list.attr) {
+		struct device *dev = kobj_to_dev(kobj);
+
+		if (!test_bit(CXL_POISON_ENABLED_LIST,
+			      to_cxl_memdev(dev)->cxlds->poison.enabled_cmds))
+			return 0;
+	}
+	return a->mode;
+}
+
+static struct attribute *cxl_mem_attrs[] = {
+	&dev_attr_trigger_poison_list.attr,
+	NULL
+};
+
+static struct attribute_group cxl_mem_group = {
+	.attrs = cxl_mem_attrs,
+	.is_visible = cxl_mem_visible,
+};
+
+__ATTRIBUTE_GROUPS(cxl_mem);
+
 static struct cxl_driver cxl_mem_driver = {
 	.name = "cxl_mem",
 	.probe = cxl_mem_probe,
 	.id = CXL_DEVICE_MEMORY_EXPANDER,
+	.drv = {
+		.dev_groups = cxl_mem_groups,
+	},
 };
 
 module_cxl_driver(cxl_mem_driver);