From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932214AbbHNQ22 (ORCPT ); Fri, 14 Aug 2015 12:28:28 -0400 Received: from mail-ig0-f176.google.com ([209.85.213.176]:36218 "EHLO mail-ig0-f176.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755104AbbHNQ20 convert rfc822-to-8bit (ORCPT ); Fri, 14 Aug 2015 12:28:26 -0400 MIME-Version: 1.0 In-Reply-To: <100D68C7BA14664A8938383216E40DE040915418@FMSMSX114.amr.corp.intel.com> References: <100D68C7BA14664A8938383216E40DE04091408C@FMSMSX114.amr.corp.intel.com> <100D68C7BA14664A8938383216E40DE0409144D9@FMSMSX114.amr.corp.intel.com> <55C855D5.1070001@plexistor.com> <55CC2BDA.3080906@plexistor.com> <55CCC8F8.6080204@hp.com> <55CCD94D.7040807@hp.com> <100D68C7BA14664A8938383216E40DE040915418@FMSMSX114.amr.corp.intel.com> Date: Fri, 14 Aug 2015 09:28:25 -0700 X-Google-Sender-Auth: ifTQ5U9y6McRX3vdQhmN8yxrrpE Message-ID: Subject: Re: regression introduced by "block: Add support for DAX reads/writes to block devices" From: Dan Williams To: "Wilcox, Matthew R" Cc: Jeff Moyer , Linda Knippers , Boaz Harrosh , "linux-kernel@vger.kernel.org" , "linux-fsdevel@vger.kernel.org" , "Verma, Vishal L" Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8BIT Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Aug 13, 2015 at 12:32 PM, Wilcox, Matthew R wrote: > I liked the patch you were pushing to request the *page* containing the requested bytes instead of the *block* containing the requested bytes. > > For the misaligned partition problem, I was thinking we should change the direct_access API to return a phys_addr_t instead of a pfn. That way we can return something that isn't actually page aligned, and DAX can take care of making sure it doesn't overshoot the end. If you go that route please make it __pfn_t + offset rather than phys_addr_t so we can communicate the PFN_DEV flag among others.