From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752127AbdJPKBX (ORCPT ); Mon, 16 Oct 2017 06:01:23 -0400 Received: from mail-wm0-f45.google.com ([74.125.82.45]:47905 "EHLO mail-wm0-f45.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751358AbdJPKBV (ORCPT ); Mon, 16 Oct 2017 06:01:21 -0400 X-Google-Smtp-Source: AOwi7QBIKnuEhRRZX33IQD+LdLjVAHgbak4DL0/Lm2hPoCT5zR8gABybTPTwwtY1BkS676GpzpldSg== Date: Mon, 16 Oct 2017 12:01:18 +0200 From: Christoffer Dall To: Peter Maydell Cc: Eric Auger , eric.auger.pro@gmail.com, lkml - Kernel Mailing List , kvm-devel , Marc Zyngier , Andre Przywara , wanghaibin.wang@huawei.com, wu.wubin@huawei.com Subject: Re: [PATCH 7/9] KVM: arm/arm64: vgic-its: free caches when GITS_BASER Valid bit is cleared Message-ID: <20171016100118.GC1845@lvm> References: <1506346478-1631-1-git-send-email-eric.auger@redhat.com> <1506346478-1631-8-git-send-email-eric.auger@redhat.com> <20171016092624.GA1845@lvm> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.5.24 (2015-08-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Oct 16, 2017 at 10:47:35AM +0100, Peter Maydell wrote: > On 16 October 2017 at 10:26, Christoffer Dall wrote: > > Hi Eric, > > > > On Mon, Sep 25, 2017 at 03:34:36PM +0200, Eric Auger wrote: > >> When the GITS_BASER.Valid gets cleared, the data structures in > >> guest RAM are not provisionned anymore. The device, collection > >> and LPI lists stored in the in-kernel ITS represent the same > >> information in some form of cache. So let's void the cache. > > > > Just a thought. What about the opposite case, if the BASERs were > > previously not valid, and then become valid, is the ITS expected restore > > the state from memory? > > Architecturally speaking, it's a cache. As soon as the guest > turns the GITS_CTLR.Enabled bit on, the ITS is permitted to > start reading from the tables. It's an implementation choice > whether it wants to preload a bunch of stuff, only load it > up when it becomes necessary or even leave it all in memory > and cache nothing. > > Eric wrote: > > Also the spec does not mandate clearing the cache when BASER > > moves to invalid (which this patch does), although this would > > have made sense to me. > > The spec says that messing with GITS_BASER while GITS_CTRL.Enabled > is set or GITS_CTLR.Quiescent is 0 is UNPREDICTABLE. And it > says that once the OS has done the Enabled/Quiescent handshake > then the ITS must have written out any dirty data to memory > and stopped doing anything. So the effect is that BASER > can't ever move to invalid while the caches are dirty. > Right, ok, so if we in fact clear the caches when the ITS is turned off and the BASER becomes invalid, and we load any data from memory as the ITS is turned on again (for the OS power management sequence) we should be good. And that means that software can't just 'move' a table location in memory by making the BASER invalid and then valid again, at least not without turning off the ITS. That makes sense to me, and so we don't need to do anything when the BASER becomes valid. Thanks, -Christoffer