Re: [PATCH 3/3] cxl/core: Add sysfs attribute get_poison for list retrieval

[Ira Weiny]

On Tue, Jun 14, 2022 at 05:10:28PM -0700, Alison Schofield wrote:
> From: Alison Schofield <alison.schofield@xxxxxxxxx>
> 
> The sysfs attribute, get_poison, allows user space to request the
> retrieval of a CXL devices poison list for its persistent memory.
> 
> From Documentation/ABI/.../sysfs-bus-cxl
>         (WO) When a '1' 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_list.
> 
> Signed-off-by: Alison Schofield <alison.schofield@xxxxxxxxx>

Reviewed-by: Ira Weiny <ira.weiny@xxxxxxxxx>

> ---
>  Documentation/ABI/testing/sysfs-bus-cxl | 13 ++++++++++
>  drivers/cxl/core/memdev.c               | 32 +++++++++++++++++++++++++
>  2 files changed, 45 insertions(+)
> 
> diff --git a/Documentation/ABI/testing/sysfs-bus-cxl b/Documentation/ABI/testing/sysfs-bus-cxl
> index 7c2b846521f3..9d0c3988fdd2 100644
> --- a/Documentation/ABI/testing/sysfs-bus-cxl
> +++ b/Documentation/ABI/testing/sysfs-bus-cxl
> @@ -163,3 +163,16 @@ Description:
>  		memory (type-3). The 'target_type' attribute indicates the
>  		current setting which may dynamically change based on what
>  		memory regions are activated in this decode hierarchy.
> +
> +What:		/sys/bus/cxl/devices/memX/get_poison
> +Date:		June, 2022
> +KernelVersion:	v5.20
> +Contact:	linux-cxl@xxxxxxxxxxxxxxx
> +Description:
> +		(WO) When a '1' 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_list.
> diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
> index f7cdcd33504a..5ef9ffaa934a 100644
> --- a/drivers/cxl/core/memdev.c
> +++ b/drivers/cxl/core/memdev.c
> @@ -106,12 +106,34 @@ static ssize_t numa_node_show(struct device *dev, struct device_attribute *attr,
>  }
>  static DEVICE_ATTR_RO(numa_node);
>  
> +static ssize_t get_poison_store(struct device *dev,
> +				struct device_attribute *attr,
> +				const char *buf, size_t len)
> +
> +{
> +	int rc;
> +
> +	if (!sysfs_streq(buf, "1")) {
> +		dev_err(dev, "%s: unknown value: %s\n", attr->attr.name, buf);
> +		return -EINVAL;
> +	}
> +
> +	rc = cxl_mem_get_poison_list(dev);
> +	if (rc) {
> +		dev_err(dev, "Failed to retrieve poison list %d\n", rc);
> +		return rc;
> +	}
> +	return len;
> +}
> +static DEVICE_ATTR_WO(get_poison);
> +
>  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_get_poison.attr,
>  	NULL,
>  };
>  
> @@ -130,6 +152,16 @@ 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_get_poison.attr) {
> +		struct device *dev = container_of(kobj, struct device, kobj);
> +		struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
> +		struct cxl_dev_state *cxlds = cxlmd->cxlds;
> +
> +		if (!test_bit(CXL_MEM_COMMAND_ID_GET_POISON,
> +			      cxlds->enabled_cmds))
> +			return 0;
> +	}
>  	return a->mode;
>  }
>  
> -- 
> 2.31.1
>