From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH rdma-next V2 3/6] IB/mlx5: Add support for QP with a given source QPN Date: Tue, 13 Jun 2017 13:21:55 -0600 Message-ID: <20170613192155.GD17727@obsidianresearch.com> References: <20170608131511.21040-1-leon@kernel.org> <20170608131511.21040-4-leon@kernel.org> <20170608163020.GA16857@obsidianresearch.com> <0ee2641a-4308-6b35-cd0a-e1a5b8b84a6a@dev.mellanox.co.il> <20170612160257.GA24829@obsidianresearch.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Alex Rosenbaum Cc: Yishai Hadas , Leon Romanovsky , Doug Ledford , linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Yishai Hadas , "Alex @ Mellanox" List-Id: linux-rdma@vger.kernel.org On Tue, Jun 13, 2017 at 06:58:39PM +0300, Alex Rosenbaum wrote: > On Mon, Jun 12, 2017 at 7:02 PM, Jason Gunthorpe > wrote: > > On Sun, Jun 11, 2017 at 09:51:49AM +0300, Yishai Hadas wrote: > >> On 6/8/2017 7:30 PM, Jason Gunthorpe wrote: > >> > > > > That doesn't even make sense. An API is an API, if the API does not > > require linkage then the hardware can't either. > > The API is well defined now and doesn't require the linkage. > But our current HW implementation requires creation of the internal > underlay object in order to support this. Well, so long as mlx5 takes the pkey/etc from the qp that has source_qpn set, and allows the source_qpn to be set to a QP that does not already exist, I have no objection.. Jason -- To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org More majordomo info at http://vger.kernel.org/majordomo-info.html