From mboxrd@z Thu Jan 1 00:00:00 1970 From: George Dunlap Subject: Re: [PATCHv3] QEMU(upstream): Disable xen's use of O_DIRECT by default as it results in crashes. Date: Mon, 11 Mar 2013 14:42:21 +0000 Message-ID: <513DED4D.9040004@eu.citrix.com> References: <5139C915.5080309@eu.citrix.com> <1362742844-6679-1-git-send-email-alex@alex.org.uk> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; Format="flowed" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Alex Bligh Cc: Ian Campbell , Stefano Stabellini , Konrad Rzeszutek Wilk , Ian Jackson , xen-devel , Jan Beulich , Anthony Perard List-Id: xen-devel@lists.xenproject.org On 11/03/13 14:02, Alex Bligh wrote: > > --On 8 March 2013 12:54:16 +0000 George Dunlap > wrote: > >> On Fri, Mar 8, 2013 at 11:40 AM, Alex Bligh wrote: >>> Due to what is almost certainly a kernel bug, writes with >>> O_DIRECT may continue to reference the page after the write >>> has been marked as completed, particularly in the case of >>> TCP retransmit. In other scenarios, this "merely" risks >>> data corruption on the write, but with Xen pages from domU >>> are only transiently mapped into dom0's memory, resulting >>> in kernel panics when they are subsequently accessed. >>> >>> This brings PV devices in line with emulated devices. Removing >>> O_DIRECT is safe as barrier operations are now correctly passed >>> through. >> Not qualified to comment on the technical merits of the patch, but re >> the commit message: >> >> Acked-by: George Dunlap > Any further thoughts on this one? I believe that Stefano is the person to commit it, but he's on holiday for two weeks. -George