From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753203AbbHMOlf (ORCPT ); Thu, 13 Aug 2015 10:41:35 -0400 Received: from verein.lst.de ([213.95.11.211]:48834 "EHLO newverein.lst.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752090AbbHMOle (ORCPT ); Thu, 13 Aug 2015 10:41:34 -0400 Date: Thu, 13 Aug 2015 16:41:32 +0200 From: Christoph Hellwig To: Boaz Harrosh Cc: Dan Williams , "linux-kernel@vger.kernel.org" , Jens Axboe , Rik van Riel , "linux-nvdimm@lists.01.org" , Linux MM , Mel Gorman , "torvalds@linux-foundation.org" , Christoph Hellwig Subject: Re: [PATCH v5 2/5] allow mapping page-less memremaped areas into KVA Message-ID: <20150813144132.GC17375@lst.de> References: <20150813025112.36703.21333.stgit@otcpl-skl-sds-2.jf.intel.com> <20150813030109.36703.21738.stgit@otcpl-skl-sds-2.jf.intel.com> <55CC3222.5090503@plexistor.com> <55CC9A5A.1020209@plexistor.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <55CC9A5A.1020209@plexistor.com> User-Agent: Mutt/1.5.17 (2007-11-01) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Aug 13, 2015 at 04:23:38PM +0300, Boaz Harrosh wrote: > > DAX as is is races against pmem unbind. A synchronization cost must > > be paid somewhere to make sure the memremap() mapping is still valid. > > Sorry for being so slow, is what I asked. what is exactly "pmem unbind" ? > > Currently in my 4.1 Kernel the ioremap is done on modprobe time and > released modprobe --remove time. the --remove can not happen with a mounted > FS dax or not. So what is exactly "pmem unbind". And if there is a new knob > then make it refuse with a raised refcount. Surprise removal of a PCIe card which is mapped to provide non-volatile memory for example. Or memory hot swap.