[openib-general] RMPP fixes for 2.6.14

[Hal Rosenstock]

On Wed, 2005-09-07 at 13:01, Roland Dreier wrote:
> I found this RMPP difference between the current kernel and our
> subversion tree.  Is there anything else that needs to be merged for
> the kernel 2.6.14 tree?
> 
>  - R.
> 
> --- old/drivers/infiniband/core/mad_rmpp.c	2005-09-07 09:48:48.232278654 -0700
> +++ new/drivers/infiniband/core/mad_rmpp.c	2005-08-30 20:26:41.989894000 -0700
> @@ -593,7 +593,8 @@
>  		rmpp_mad->rmpp_hdr.paylen_newwin =
>  			cpu_to_be32(mad_send_wr->total_seg *
>  				    (sizeof(struct ib_rmpp_mad) -
> -				       offsetof(struct ib_rmpp_mad, data)));
> +				       offsetof(struct ib_rmpp_mad, data)) -
> +				    mad_send_wr->pad);
>  		mad_send_wr->sg_list[0].length = sizeof(struct ib_rmpp_mad);
>  	} else {
>  		mad_send_wr->send_wr.num_sge = 2;
> @@ -602,6 +603,7 @@
>  		mad_send_wr->sg_list[1].length = sizeof(struct ib_rmpp_mad) -
>  						 mad_send_wr->data_offset;
>  		mad_send_wr->sg_list[1].lkey = mad_send_wr->sg_list[0].lkey;
> +		rmpp_mad->rmpp_hdr.paylen_newwin = 0;
>  	}
>  
>  	if (mad_send_wr->seg_num == mad_send_wr->total_seg) {

Yes, that looks like the RMPP change since last pushed upstream.

I will see if there is anything else which might be a candidate.

-- Hal