> Yes, I saw Sean's comment, and I am glad we all understand there are
> only 3 callers. And looking at the callers there are only a small
> number of elements being used:
> 
> rdma cm:
>  IB_SA_PATH_REC_DGID | IB_SA_PATH_REC_SGID |
>                     IB_SA_PATH_REC_PKEY | IB_SA_PATH_REC_NUMB_PATH |
>                     IB_SA_PATH_REC_REVERSIBLE | IB_SA_PATH_REC_SERVICE_ID;
>  IB_SA_PATH_REC_QOS_CLASS;
>  IB_SA_PATH_REC_TRAFFIC_CLASS
> 
> ipoib:
>                                    IB_SA_PATH_REC_DGID          |
>                                    IB_SA_PATH_REC_SGID          |
>                                    IB_SA_PATH_REC_NUMB_PATH     |
>                                    IB_SA_PATH_REC_TRAFFIC_CLASS |
>                                    IB_SA_PATH_REC_PKEY,
> 
> srp:
>                                                IB_SA_PATH_REC_SERVICE_ID |
>                                                IB_SA_PATH_REC_DGID       |
>                                                IB_SA_PATH_REC_SGID       |
>                                                IB_SA_PATH_REC_NUMB_PATH  |
>                                                IB_SA_PATH_REC_PKEY,
> 
> So, rather than a SA mad in netlink, I'd suggest actually using
> extensible netlink here and define the query cleanly using nested
> attributes:
> 
> RDMA_OP_RESOLVE (request)
>   GIDS
>   SERVICE_ID
>   QOS/TCLASS
>   PKEY
>   QP TYPE (aka reversible)
> 
> RDMA_OP_RESOLVE (reply)
>   IB_PATH
>   IB_PATH
>   IB_PATH

I thought you were asking to move the hook site.  This approach seems 
reasonable.  We should just need to add a check against the compmask.
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Reply via email to