Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752123AbdDCWrN (ORCPT ); Mon, 3 Apr 2017 18:47:13 -0400 Received: from mail-oi0-f45.google.com ([209.85.218.45]:35097 "EHLO mail-oi0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751635AbdDCWrK (ORCPT ); Mon, 3 Apr 2017 18:47:10 -0400 MIME-Version: 1.0 In-Reply-To: References: <1490911959-5146-1-git-send-email-logang@deltatee.com> <1490911959-5146-6-git-send-email-logang@deltatee.com> <20170331070950.GA9059@infradead.org> <435d4471-436b-87e6-8827-c9fc6cbdde2c@deltatee.com> <445bc352-75d7-438f-96ef-c2411215628d@deltatee.com> From: Dan Williams Date: Mon, 3 Apr 2017 15:47:09 -0700 Message-ID: Subject: Re: [RFC 5/8] scatterlist: Modify SG copy functions to support io memory. To: Logan Gunthorpe Cc: Christoph Hellwig , Jens Axboe , Keith Busch , "James E.J. Bottomley" , linux-scsi , "Martin K. Petersen" , "linux-nvdimm@lists.01.org" , linux-rdma@vger.kernel.org, linux-pci@vger.kernel.org, Steve Wise , "linux-kernel@vger.kernel.org" , linux-nvme@lists.infradead.org, Jason Gunthorpe , Max Gurtovoy , Christoph Hellwig Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1982 Lines: 46 On Mon, Apr 3, 2017 at 3:10 PM, Logan Gunthorpe wrote: > > > On 03/04/17 03:44 PM, Dan Williams wrote: >> On Mon, Apr 3, 2017 at 2:20 PM, Logan Gunthorpe wrote: >>> Hi Christoph, >>> >>> What are your thoughts on an approach like the following untested >>> draft patch. >>> >>> The patch (if fleshed out) makes it so iomem can be used in an sgl >>> and WARN_ONs will occur in places where drivers attempt to access >>> iomem directly through the sgl. >>> >>> I'd also probably create a p2pmem_alloc_sgl helper function so driver >>> writers wouldn't have to mess with sg_set_iomem_page. >>> >>> With all that in place, it should be relatively safe for drivers to >>> implement p2pmem even though we'd still technically be violating the >>> __iomem boundary in some places. >> >> Just reacting to this mail, I still haven't had a chance to take a >> look at the rest of the series. >> >> The pfn_t type was invented to carry extra type and page lookup >> information about the memory behind a given pfn. At first glance that >> seems a more natural place to carry an indication that this is an >> "I/O" pfn. > > I agree... But what are the plans for pfn_t? Is anyone working on using > it in the scatterlist code? Currently it's not there yet and given the > assertion that we will continue to be using struct page for DMA is that > a direction we'd want to go? > I wouldn't necessarily conflate supporting pfn_t in the scatterlist with the stalled stuct-page-less DMA effor. A pfn_t_to_page() conversion will still work and be required. However you're right, the minute we use pfn_t for this we're into the realm of special case drivers that understand scatterlists with special "I/O-pfn_t" entries. However, maybe that's what we want? I think peer-to-peer DMA is not a general purpose feature unless/until we get it standardized in PCI. So maybe drivers with special case scatterlist support is exactly what we want for now. Thoughts?