From: Christoffer Dall <cdall@linaro.org>
To: Peter Maydell <peter.maydell@linaro.org>
Cc: Eric Auger <eric.auger@redhat.com>,
eric.auger.pro@gmail.com,
lkml - Kernel Mailing List <linux-kernel@vger.kernel.org>,
kvm-devel <kvm@vger.kernel.org>,
Marc Zyngier <marc.zyngier@arm.com>,
Andre Przywara <andre.przywara@arm.com>,
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
Date: Mon, 16 Oct 2017 12:01:18 +0200 [thread overview]
Message-ID: <20171016100118.GC1845@lvm> (raw)
In-Reply-To: <CAFEAcA9Rwxz5ddyr6P7SDF_-do7TPQrdKxSRKe8eY=JEeBWTgA@mail.gmail.com>
On Mon, Oct 16, 2017 at 10:47:35AM +0100, Peter Maydell wrote:
> On 16 October 2017 at 10:26, Christoffer Dall <cdall@linaro.org> wrote:
> > Hi Eric,
> >
> > On Mon, Sep 25, 2017 at 03:34:36PM +0200, Eric Auger wrote:
> >> When the GITS_BASER<n>.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
next prev parent reply other threads:[~2017-10-16 10:01 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-09-25 13:34 [PATCH 0/9] vITS Migration fixes and reset Eric Auger
2017-09-25 13:34 ` [PATCH 1/9] KVM: arm/arm64: vgic-its: fix return value for restore Eric Auger
2017-09-25 13:34 ` [PATCH 2/9] KVM: arm/arm64: vgic-its: Always allow clearing GITS_CREADR/CWRITER Eric Auger
2017-09-25 13:34 ` [PATCH 3/9] KVM: arm/arm64: vgic-its: Improve error reporting on device table save Eric Auger
2017-09-25 13:34 ` [PATCH 4/9] KVM: arm/arm64: vgic-its: Check GITS_BASER Valid bit before saving tables Eric Auger
2017-09-25 13:34 ` [PATCH 5/9] KVM: arm/arm64: vgic-its: Check GITS_CBASER validity before processing commands Eric Auger
2017-09-25 13:34 ` [PATCH 6/9] KVM: arm/arm64: vgic-its: new helper functions to free the caches Eric Auger
2017-09-25 13:34 ` [PATCH 7/9] KVM: arm/arm64: vgic-its: free caches when GITS_BASER Valid bit is cleared Eric Auger
2017-10-16 9:26 ` Christoffer Dall
2017-10-16 9:44 ` Auger Eric
2017-10-16 9:59 ` Christoffer Dall
2017-10-16 9:47 ` Peter Maydell
2017-10-16 10:01 ` Christoffer Dall [this message]
2017-09-25 13:34 ` [PATCH 8/9] KVM: arm/arm64: Document KVM_DEV_ARM_ITS_CTRL_RESET Eric Auger
2017-09-25 13:34 ` [PATCH 9/9] KVM: arm/arm64: vgic-its: Implement KVM_DEV_ARM_ITS_CTRL_RESET Eric Auger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20171016100118.GC1845@lvm \
--to=cdall@linaro.org \
--cc=andre.przywara@arm.com \
--cc=eric.auger.pro@gmail.com \
--cc=eric.auger@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=marc.zyngier@arm.com \
--cc=peter.maydell@linaro.org \
--cc=wanghaibin.wang@huawei.com \
--cc=wu.wubin@huawei.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox