Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932098Ab0FDBbT (ORCPT ); Thu, 3 Jun 2010 21:31:19 -0400 Received: from rcsinet10.oracle.com ([148.87.113.121]:54223 "EHLO rcsinet10.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756856Ab0FDBbR (ORCPT ); Thu, 3 Jun 2010 21:31:17 -0400 To: Nick Piggin Cc: "Martin K. Petersen" , Chris Mason , James Bottomley , Matthew Wilcox , Christof Schmitt , Boaz Harrosh , linux-scsi@vger.kernel.org, linux-kernel@vger.kernel.org, linux-fsdevel@vger.kernel.org Subject: Re: Wrong DIF guard tag on ext2 write From: "Martin K. Petersen" Organization: Oracle References: <1275399637.21962.11.camel@mulgrave.site> <20100601134951.GM8980@think> <20100601162929.GC32708@parisc-linux.org> <20100601164750.GQ8980@think> <1275411293.21962.387.camel@mulgrave.site> <20100601180905.GR8980@think> <20100601184649.GE9453@laptop> <20100601193528.GV8980@think> <20100602032030.GF9453@laptop> <20100602134121.GD6152@laptop> Date: Thu, 03 Jun 2010 21:30:06 -0400 In-Reply-To: <20100602134121.GD6152@laptop> (Nick Piggin's message of "Wed, 2 Jun 2010 23:41:21 +1000") Message-ID: User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/23.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii X-Auth-Type: Internal IP X-Source-IP: acsinet15.oracle.com [141.146.126.227] X-CT-RefId: str=0001.0A090201.4C08575E.0049:SCFMA922111,ss=1,fgs=0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1271 Lines: 30 >>>>> "Nick" == Nick Piggin writes: Nick, >> Filesystems will inevitably have to be integrity-aware for that to >> work. And it will be their job to keep the data pages stable during >> DMA. Nick> Closing the while it is dirty, while it is being written back Nick> window still leaves a pretty big window. Also, how do you handle Nick> mmap writes? Write protect and checksum the destination page Nick> after every store? Or leave some window between when the pagecache Nick> is dirtied and when it is written back? So I don't know whether Nick> it's worth putting a lot of effort into this case. I'm mostly interested in the cases where the filesystem acts as a conduit for integrity metadata from user space. I agree the corruption windows inside the kernel are only of moderate interest. No filesystems have added support for explicitly protecting a bio because the block layer's function to do so automatically is just a few function calls away. -- Martin K. Petersen Oracle Linux Engineering -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/