From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Vrabel Subject: Re: [PATCH v2 3/4] xen/arm: introduce GNTTABOP_cache_flush Date: Wed, 8 Oct 2014 13:45:59 +0100 Message-ID: <54353207.8050702@citrix.com> References: <1412347845-27755-3-git-send-email-stefano.stabellini@eu.citrix.com> <5432B382.3040000@citrix.com> <1412770650.9247.27.camel@citrix.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <1412770650.9247.27.camel@citrix.com> List-Unsubscribe: , List-Post: List-Help: List-Subscribe: , Sender: xen-devel-bounces@lists.xen.org Errors-To: xen-devel-bounces@lists.xen.org To: Ian Campbell , Stefano Stabellini Cc: julien.grall@citrix.com, xen-devel@lists.xensource.com, David Vrabel List-Id: xen-devel@lists.xenproject.org On 08/10/14 13:17, Ian Campbell wrote: > On Wed, 2014-10-08 at 12:54 +0100, Stefano Stabellini wrote: >>> Instead of this hypercall, could the guest clean/invalidate by set/way? >>> I guess this would need a suitable IPA which could be obtained by some >>> (offset) 1:1 mapping in the stage 2 tables? >> >> I wish I could: as the clean/invalidate by set/way is implementation >> specific, there is now way to use it to clean a specific range of >> addresses. > > Clean by set/way is basically unusable except in very specific > circumstances (e.g. tearing down prior to a suspend). It's certainly not > usable on an active SMP system. > > http://lists.xen.org/archives/html/xen-devel/2014-10/msg00709.html Yeah, I saw that email after I made my suggestion. David