From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andy Lutomirski Subject: Re: [RFC PATCH 2/2] mm, fs: daxfile, an interface for byte-addressable updates to pmem Date: Tue, 20 Jun 2017 09:26:59 -0700 Message-ID: References: <149766213493.22552.4057048843646200083.stgit@dwillia2-desk3.amr.corp.intel.com> <20170619132107.GG11993@dastard> <20170620004653.GI17542@dastard> <20170620084924.GA9752@lst.de> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: linux-nvdimm-bounces-hn68Rpc1hR1g9hUCZPvPmw@public.gmane.org Sender: "Linux-nvdimm" To: Dan Williams Cc: Jan Kara , linux-nvdimm , Linux API , Dave Chinner , "linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org" , Christoph Hellwig , "linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org" , Andy Lutomirski , Linux FS Devel , Andrew Morton List-Id: linux-api@vger.kernel.org On Tue, Jun 20, 2017 at 9:17 AM, Dan Williams wrote: > On Tue, Jun 20, 2017 at 1:49 AM, Christoph Hellwig wrote: >> [stripped giant fullquotes] >> >> On Mon, Jun 19, 2017 at 10:53:12PM -0700, Andy Lutomirski wrote: >>> But that's my whole point. The kernel doesn't really need to prevent >>> all these background maintenance operations -- it just needs to block >>> .page_mkwrite until they are synced. I think that whatever new >>> mechanism we add for this should be sticky, but I see no reason why >>> the filesystem should have to block reflink on a DAX file entirely. >> >> Agreed - IFF we want to support write through semantics this is the >> only somewhat feasible way. It still has massive downsides of forcing >> the full sync machinery to run from the page fauly handler, which >> I'm rather scared off, but that's still better than creating a magic >> special case that isn't managable at all. > > An immutable-extent DAX-file and a reflink-capable DAX-file are not > mutually exclusive, and I have yet to hear a need for reflink support > without fsync/msync. Instead I have heard the need for an immutable > file for RDMA purposes, especially for hardware that can't trigger an > mmu fault. The special management of an immutable file is acceptable > to get these capabilities. I guess this applies to any user of get_user_pages() on a DAX-mapped file. Hmm.