From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jason Gunthorpe Subject: Re: [RFC PATCH 2/4] uverbs: Add common ib_iomem_get service Date: Thu, 29 Jul 2010 14:13:17 -0600 Message-ID: <20100729201317.GA7920@obsidianresearch.com> References: <20100729162339.14674.15788.stgit@build.ogc.int> <20100729162509.14674.34237.stgit@build.ogc.int> <1280427723.6820.56.camel@chromite.mv.qlogic.com> <4C51D15F.8060708@opengridcomputing.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <4C51D15F.8060708-7bPotxP6k4+P2YhJcF5u+vpXobYPEAuW@public.gmane.org> Sender: linux-rdma-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org To: Tom Tucker Cc: Ralph Campbell , Tom Tucker , "rdreier-FYB4Gu1CFyUAvxtiuMwx3w@public.gmane.org" , "linux-rdma-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , "brandt-4OHPYypu0djtX7QSmKvirg@public.gmane.org" , "swise-/Yg/VP3ZvrM@public.gmane.org" List-Id: linux-rdma@vger.kernel.org On Thu, Jul 29, 2010 at 02:07:11PM -0500, Tom Tucker wrote: >>> Add an ib_iomem_get service that converts a vma to an array of >>> physical addresses. This makes it easier for each device driver to >>> add support for the reg_io_mr provider method. Tom, could you say a few words on what this is for? Also, I'd like to see a strong defence of this new user space API particularly: 1) Why can't this be done with the existing ibv_reg_mr, like huge pages are. 2) How is it possible for userspace to know when it should use ibv_reg_mr vs ibv_reg_io_mr? 3) Why can't ibv_dereg_io_mr be entirely handled by ibv_dereg_mr? On first glance, this seems like a hugely bad API to me :) Also, if new user space APIs are really needed, they do need man pages too ... 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