From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [PATCH WIP 28/43] IB/core: Introduce new fast registration API Date: Mon, 27 Jul 2015 14:29:57 -0600 Message-ID: <20150727202957.GA29619@obsidianresearch.com> References: <1437548143-24893-1-git-send-email-sagig@mellanox.com> <1437548143-24893-29-git-send-email-sagig@mellanox.com> <20150722180203.GI26909@obsidianresearch.com> <55B0BFA4.4060509@dev.mellanox.co.il> <20150723161436.GC25174@obsidianresearch.com> <55B11A92.9040406@dev.mellanox.co.il> <20150723185126.GA31346@obsidianresearch.com> <55B4AC26.20405@dev.mellanox.co.il> <20150727171441.GC18348@obsidianresearch.com> <55B69058.70403@opengridcomputing.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <55B69058.70403-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Steve Wise Cc: Sagi Grimberg , Sagi Grimberg , linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Liran Liss , Oren Duer List-Id: linux-rdma@vger.kernel.org On Mon, Jul 27, 2015 at 03:11:04PM -0500, Steve Wise wrote: > Well technically an MR with REMOTE_WRITE also has LOCAL_WRITE set. So you > are proposing the core disallow a ULP from using the lkey for this type of > MR? Say in a RECV sge? Yes, absolutely. It is wrong anyhow, RECV isn't special, if you RECV into memory that is exposed via a rkey MR, you have to invalidate that MR and fence DMA before you can touch the buffer. Only very special, carefully designed, cases could avoid that. We don't have those cases, so lets just ban it. The only exception is the iWarp RDMA READ thing. 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