On Wed, Apr 18, 2018 at 03:20:13AM -0700, muneendra.kumar@xxxxxxxxxxxx wrote:
> +#ifndef RXE_ABI_H
> +#define RXE_ABI_H
> +
> +#include <infiniband/kern-abi.h>
> +#include <rdma/rdma_user_rfc.h>
> +#include <kernel-abi/rdma_user_rfc.h>
> +
> +DECLARE_DRV_CMD(urfc_create_cq, IB_USER_VERBS_CMD_CREATE_CQ,
> + empty, rfc_create_cq_resp);
> +DECLARE_DRV_CMD(urfc_create_qp, IB_USER_VERBS_CMD_CREATE_QP,
> + empty, rfc_create_qp_resp);
> +DECLARE_DRV_CMD(urfc_create_srq, IB_USER_VERBS_CMD_CREATE_SRQ,
> + empty, rfc_create_srq_resp);
> +DECLARE_DRV_CMD(urfc_modify_srq, IB_USER_VERBS_CMD_MODIFY_SRQ,
> + rfc_modify_srq_cmd, empty);
> +DECLARE_DRV_CMD(urfc_resize_cq, IB_USER_VERBS_CMD_RESIZE_CQ,
> + empty, rfc_resize_cq_resp);
It looks like Christoph is NAK'ing this series, but wow, good job
keeping up with all the rdma-core churn lately, the various ABI part
might actually be right..
> +static const struct verbs_device_ops rfc_dev_ops = {
> + .name = "rfc",
> + /*
> + * For 64 bit machines ABI version 1 and 2 are the same. Otherwise 32
> + * bit machines require ABI version 2 which guarentees the user and
> + * kernel use the same ABI.
> + */
> + .match_min_abi_version = sizeof(void *) == 8?1:2,
Although it doesn't make sense to copy this of course.
Jason
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
