Roland Dreier wrote:
> I believe the only thing I need to coordinate with is the XRC patch set.
I think the IBoE patches in the OFED branch also extend the ABI. We should try
to avoid stepping on that too.
I think the only (a part from the link type field in the port attr) ABI
change introduc
> > OK, but we should coordinate this with all the other ABI extensions
> > that OFED has already made
> I believe the only thing I need to coordinate with is the XRC patch
> set.
I think the IBoE patches in the OFED branch also extend the ABI. we
should try to avoid stepping on that too.
On Wednesday 27 January 2010 11:13, Or Gerlitz wrote:
> Roland Dreier wrote:
> > OK, but we should coordinate this with all the other ABI extensions that
> > OFED has already made
> I believe the only thing I need to coordinate with is the XRC patch set.
>
> Jack, can you please direct me to the
Roland Dreier wrote:
OK, but we should coordinate this with all the other ABI extensions that OFED
has already made
I believe the only thing I need to coordinate with is the XRC patch set.
Jack, can you please direct me to the patch set I should be setting the
modify_cq patches against? no pr
> > - IB_USER_VERBS_CMD_POST_SRQ_RECV
> > + IB_USER_VERBS_CMD_POST_SRQ_RECV,
> > + IB_USER_VERBS_CMD_CREATE_XRC_SRQ,
> > + IB_USER_VERBS_CMD_OPEN_XRCD,
> > + IB_USER_VERBS_CMD_CLOSE_XRCD
>
> Jack,Roland I believe that adding entries to this enum means ABI change
> towards libibverbs
Roland Dreier wrote:
> Add support for core userspace XRC operations (alloc/dealloc XRC domain,
> create XRC SRQ), including adding an ABI for marshalling requests and
> responses.
> +++ b/include/rdma/ib_user_verbs.h
> @@ -81,7 +81,10 @@ enum {
> - IB_USER_VERBS_CMD_POST_SRQ_RECV
> + IB_U
From: Jack Morgenstein
Add support for core userspace XRC operations (alloc/dealloc XRC
domain, create XRC SRQ), including adding an ABI for marshalling
requests and responses.
Signed-off-by: Jack Morgenstein
Signed-off-by: Roland Dreier
---
drivers/infiniband/core/uverbs.h |4 +
dri