From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1758071Ab2EAPVG (ORCPT ); Tue, 1 May 2012 11:21:06 -0400 Received: from mx1.redhat.com ([209.132.183.28]:16742 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757101Ab2EAPVE (ORCPT ); Tue, 1 May 2012 11:21:04 -0400 From: Jeff Moyer To: KOSAKI Motohiro Cc: Jan Kara , Michael Kerrisk , LKML , linux-man@vger.kernel.org, linux-mm@kvack.org, mgorman@suse.de, npiggin@gmail.com Subject: Re: [PATCH] Describe race of direct read and fork for unaligned buffers References: <1335778207-6511-1-git-send-email-jack@suse.cz> X-PGP-KeyID: 1F78E1B4 X-PGP-CertKey: F6FE 280D 8293 F72C 65FD 5A58 1FF8 A7CA 1F78 E1B4 X-PCLoadLetter: What the f**k does that mean? Date: Tue, 01 May 2012 11:11:26 -0400 In-Reply-To: (KOSAKI Motohiro's message of "Tue, 1 May 2012 10:37:20 -0400") Message-ID: User-Agent: Gnus/5.110011 (No Gnus v0.11) Emacs/23.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org KOSAKI Motohiro writes: >> Hello, >> >> Thank you revisit this. But as far as my remember is correct, this issue is NOT >> unaligned access issue. It's just get_user_pages(_fast) vs fork race issue. i.e. >> DIRECT_IO w/ multi thread process should not use fork(). > > The problem is, fork (and its COW logic) assume new access makes cow break, > But page table protection can't detect a DMA write. Therefore DIO may override > shared page data. Hm, I've only seen this with misaligned or multiple sub-page-sized reads in the same page. AFAIR, aligned, page-sized I/O does not get split. But, I could be wrong... Cheers, Jeff From mboxrd@z Thu Jan 1 00:00:00 1970 From: Jeff Moyer Subject: Re: [PATCH] Describe race of direct read and fork for unaligned buffers Date: Tue, 01 May 2012 11:11:26 -0400 Message-ID: References: <1335778207-6511-1-git-send-email-jack@suse.cz> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: In-Reply-To: (KOSAKI Motohiro's message of "Tue, 1 May 2012 10:37:20 -0400") Sender: owner-linux-mm@kvack.org To: KOSAKI Motohiro Cc: Jan Kara , Michael Kerrisk , LKML , linux-man@vger.kernel.org, linux-mm@kvack.org, mgorman@suse.de, npiggin@gmail.com List-Id: linux-man@vger.kernel.org KOSAKI Motohiro writes: >> Hello, >> >> Thank you revisit this. But as far as my remember is correct, this issue is NOT >> unaligned access issue. It's just get_user_pages(_fast) vs fork race issue. i.e. >> DIRECT_IO w/ multi thread process should not use fork(). > > The problem is, fork (and its COW logic) assume new access makes cow break, > But page table protection can't detect a DMA write. Therefore DIO may override > shared page data. Hm, I've only seen this with misaligned or multiple sub-page-sized reads in the same page. AFAIR, aligned, page-sized I/O does not get split. But, I could be wrong... Cheers, Jeff -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/ Don't email: email@kvack.org