Hi Roland,
That looks good to me.
Thanks for all help.
Nam
On Friday 10 October 2008 23:41, Roland Dreier wrote:
> thanks, applied -- it didn't apply to the latest tree, because of the
> flush CQE changes, so I merged it manually as below -- let me know if
> this is wrong:
>
> commit 0540bbbe455e123a1692d26205ad1a29983883b0
> Author: Hoang-Nam Nguyen <[EMAIL PROTECTED]>
> Date: Fri Oct 10 14:40:39 2008 -0700
>
> IB/ehca: Don't allow creating UC QP with SRQ
>
> This patch prevents a UC QP to be created attached to an SRQ, since
> current firmware does not support this feature.
>
> Signed-off-by: Michael Faath <[EMAIL PROTECTED]>
> Signed-off-by: Roland Dreier <[EMAIL PROTECTED]>
>
> diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c
> b/drivers/infiniband/hw/ehca/ehca_qp.c
> index 4dbe287..40b578d 100644
> --- a/drivers/infiniband/hw/ehca/ehca_qp.c
> +++ b/drivers/infiniband/hw/ehca/ehca_qp.c
> @@ -502,6 +502,12 @@ static struct ehca_qp *internal_create_qp(
> if (init_attr->srq) {
> my_srq = container_of(init_attr->srq, struct ehca_qp, ib_srq);
>
> + if (qp_type == IB_QPT_UC) {
> + ehca_err(pd->device, "UC with SRQ not supported");
> + atomic_dec(&shca->num_qps);
> + return ERR_PTR(-EINVAL);
> + }
> +
> has_srq = 1;
> parms.ext_type = EQPT_SRQBASE;
> parms.srq_qpn = my_srq->real_qp_num;
>
_______________________________________________
Linuxppc-dev mailing list
Linuxppc-dev@ozlabs.org
https://ozlabs.org/mailman/listinfo/linuxppc-dev
