Re: [Xen-devel] [PATCH v2 3/4] xen/arm: clean and invalidate all guest caches by VMID after domain build.

[Ian Campbell <Ian.Campbell@xxxxxxxxxx>]

On Tue, 2014-02-04 at 15:55 +0000, Ian Jackson wrote:
> Ian Campbell writes ("Re: [PATCH v2 3/4] xen/arm: clean and invalidate all 
> guest caches by VMID after domain build."):
> > On Tue, 2014-02-04 at 15:32 +0000, Ian Jackson wrote:
> > > The approach you are taking here is that for pages explicitly mapped
> > > by some libxc caller, you do the flush on unmap.  But what about
> > > callers who don't unmap ?  Are there callers which don't unmap and
> > > which instead are relying on memory coherency assumptions which aren't
> > > true on arm ?
> > 
> > Callers which don't unmap would be leaking mappings and therefore buggy
> > in a long running toolstack.
> 
> What I mean is that they might map the guest pages, and expect to
> exchange data with the guest through the pages while they were still
> mapped ...
> 
> > Also after the initial start of day period we require that the guest
> > enable its caches.
> 
> ... but before the guest enables caching.

We basically rule that out in the ABI requirements.

The cases where this would happen are things like xenstore and
xenconsole but those are driven from the guest end, which requires the
caches to be on.

Ian.


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel