Re: [PATCH 2/3] cxl/mbox: Add GET_POISON_LIST mailbox command support

[Jonathan Cameron <Jonathan.Cameron@Huawei.com>]

On Tue, 14 Jun 2022 17:10:27 -0700
alison.schofield@intel.com wrote:

> From: Alison Schofield <alison.schofield@intel.com>
> 
> CXL devices that support persistent memory maintain a list of locations
> that are poisoned or result in poison if the addresses are accessed by
> the host.
> 
> Per the spec (CXL 2.0 8.2.8.5.4.1), the device returns this Poison
> list as a set of  Media Error Records that include the source of the
> error, the starting device physical address and length. The length is
> the number of adjacent DPAs in the record and is in units of 64 bytes.
> 
> Retrieve the list and log each Media Error Record as a trace event of
> type cxl_poison_list.
> 
> Signed-off-by: Alison Schofield <alison.schofield@intel.com>
> ---
 
> +int cxl_mem_get_poison_list(struct device *dev)
> +{
> +	struct cxl_memdev *cxlmd = to_cxl_memdev(dev);
> +	struct cxl_dev_state *cxlds = cxlmd->cxlds;
> +	struct cxl_mbox_poison_payload_out *po;
> +	struct cxl_mbox_poison_payload_in pi;
> +	int nr_records = 0;
> +	int rc, i;
> +
> +	if (range_len(&cxlds->pmem_range)) {
> +		pi.offset = cpu_to_le64(cxlds->pmem_range.start);
> +		pi.length = cpu_to_le64(range_len(&cxlds->pmem_range));
> +	} else {
> +		return -ENXIO;
> +	}
> +
> +	po = kvmalloc(cxlds->payload_size, GFP_KERNEL);
> +	if (!po)
> +		return -ENOMEM;
> +
> +	do {
> +		rc = cxl_mbox_send_cmd(cxlds, CXL_MBOX_OP_GET_POISON, &pi,
> +				       sizeof(pi), po, cxlds->payload_size);
> +		if (rc)
> +			goto out;
> +
> +		if (po->flags & CXL_POISON_FLAG_OVERFLOW) {
> +			time64_t o_time = le64_to_cpu(po->overflow_timestamp);
> +
> +			dev_err(dev, "Poison list overflow at %ptTs UTC\n",
> +				&o_time);
> +			rc = -ENXIO;
> +			goto out;
> +		}
> +
> +		if (po->flags & CXL_POISON_FLAG_SCANNING) {
> +			dev_err(dev, "Scan Media in Progress\n");
> +			rc = -EBUSY;
> +			goto out;
> +		}
> +
> +		for (i = 0; i < le16_to_cpu(po->count); i++) {
> +			u64 addr = le64_to_cpu(po->record[i].address);
> +			u32 len = le32_to_cpu(po->record[i].length);
> +			int source = FIELD_GET(CXL_POISON_SOURCE_MASK, addr);
> +
> +			if (!CXL_POISON_SOURCE_VALID(source)) {
> +				dev_dbg(dev, "Invalid poison source %d",
> +					source);
> +				source = CXL_POISON_SOURCE_INVALID;
> +			}
> +
> +			trace_cxl_poison_list(dev, source, addr, len);
> +		}
> +
> +		/* Protect against an uncleared _FLAG_MORE */
> +		nr_records = nr_records + le16_to_cpu(po->count);
> +		if (nr_records >= cxlds->poison_max)

If this happens and _FLAG_MORE is set (it will occur anyway currently
if we happen to have poison_max records - I hit this in QEMU because
until now default of poison_max == 0)
then we should spit out an error message as I think that means the
hardware is broken.


> +			goto out;
> +
> +	} while (po->flags & CXL_POISON_FLAG_MORE);
> +
> +out:
> +	kvfree(po);
> +	return rc;
> +}
> +EXPORT_SYMBOL_NS_GPL(cxl_mem_get_poison_list, CXL);
> +
>  struct cxl_dev_state *cxl_dev_state_create(struct device *dev)
>  {
>  	struct cxl_dev_state *cxlds;