Re: [PATCH v5 2/3] cxl/edac: Skip event records marked NOT_REPAIRABLE

[Li Ming]

在 2026/11/8 10:20, Jongwon Lee 写道:
> Bit 1 of the DPA field in General Media and DRAM event records is the
> NOT_REPAIRABLE flag. The device sets it when the memory at that DPA
> cannot be repaired.
>
> cxl_find_rec_gen_media() and cxl_find_rec_dram() do not check this flag.
> A repair request that matches such a record passes the lookup and is
> sent to the device. Since the records are keyed by the raw DPA, this
> happens today when user space writes the DPA with bit 1 set.
>
> Skip these records in both lookups, so the repair request fails with
> -EINVAL. The trace events already show dpa_flags='NOT_REPAIRABLE' for
> them, so user space can tell before it asks for a repair.
>
> cxl_find_rec_gen_media() now reads the record, so take the xarray lock
> there too, as cxl_find_rec_dram() does. Also make it return bool, since
> its only caller just checks the result.
>
> Fixes: 0b5ccb0de1e2 ("cxl/edac: Support for finding memory operation attributes from the current boot")
> Signed-off-by: Jongwon Lee <ai@xxxxxxxxx>
Reviewed-by: Li Ming <ming.li@xxxxxxxxxxxx>

> ---
>   drivers/cxl/core/edac.c | 27 +++++++++++++++------------
>   1 file changed, 15 insertions(+), 12 deletions(-)
>
> diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
> index 4624ab4644..42683b7c54 100644
> --- a/drivers/cxl/core/edac.c
> +++ b/drivers/cxl/core/edac.c
> @@ -918,24 +918,27 @@ struct cxl_mem_repair_attrbs {
>   	enum cxl_mem_repair_type repair_type;
>   };
>   
> -static struct cxl_event_gen_media *
> -cxl_find_rec_gen_media(struct cxl_memdev *cxlmd,
> -		       struct cxl_mem_repair_attrbs *attrbs)
> +static inline bool cxl_rec_not_repairable(const struct cxl_event_media_hdr *hdr)
> +{
> +	return le64_to_cpu(hdr->phys_addr) & CXL_DPA_NOT_REPAIRABLE;
> +}
> +
> +static bool cxl_find_rec_gen_media(struct cxl_memdev *cxlmd,
> +				   struct cxl_mem_repair_attrbs *attrbs)
>   {
>   	struct cxl_mem_err_rec *array_rec = cxlmd->err_rec_array;
>   	struct cxl_event_gen_media *rec;
> +	bool found;
>   
> -	if (!array_rec)
> -		return NULL;
> +	if (!array_rec || attrbs->repair_type != CXL_PPR)
> +		return false;
>   
> +	xa_lock(&array_rec->rec_gen_media);
>   	rec = xa_load(&array_rec->rec_gen_media, attrbs->dpa);
> -	if (!rec)
> -		return NULL;
> -
> -	if (attrbs->repair_type == CXL_PPR)
> -		return rec;
> +	found = rec && !cxl_rec_not_repairable(&rec->media_hdr);
> +	xa_unlock(&array_rec->rec_gen_media);
>   
> -	return NULL;
> +	return found;
>   }
>   
>   /* Caller holds the xarray lock. The record may be freed once it is dropped. */
> @@ -949,7 +952,7 @@ __cxl_find_rec_dram(struct xarray *rec_xarray,
>   	lockdep_assert_held(&rec_xarray->xa_lock);
>   
>   	rec = xa_load(rec_xarray, attrbs->dpa);
> -	if (!rec)
> +	if (!rec || cxl_rec_not_repairable(&rec->media_hdr))
>   		return NULL;
>   
>   	validity_flags = get_unaligned_le16(rec->media_hdr.validity_flags);