Re: [Xen-devel] The hypercall will fail and return EFAULT when the page becomes COW by forking process in linux

[Ian Campbell <Ian.Campbell@xxxxxxxxxx>]

On Wed, 2012-07-25 at 14:12 +0100, Ian Campbell wrote:
> On Wed, 2012-07-25 at 12:48 +0100, Wangzhenguo wrote:
> > > From: Ian Campbell [mailto:Ian.Campbell@xxxxxxxxxx]
> > > Sent: Tuesday, July 24, 2012 9:06 PM
> > > 
> > > Hrm. yes. This basically harks back to the use of mlock as a surrogate
> > > for the requirement to properly lock down memory for use as a hypercall
> > > argument. This is flawed in ways other than this (i.e. NUMA memory
> > > migration would also break it).
> > > 
> > > The correct answer here is a special device (e.g. /dev/xen/hypercall?)
> > > which can be mmap by libxc to provide memory specifically for this
> > > purspoe which is fully locked down (e.g. VM_DONTCOPY and whatever else
> > > is required).
> > 
> > Thanks for your reply. I see the madvise syscall can make the vma to
> > be VM_DONTCOPY by deliverying MADV_DONTFORK advice.
> 
> I didn't know about this MADV option, it sounds like the right idea to
> me.
> 
> >  I'll fixup and test it.

BTW, I think this would be a good fix to have for 4.2.0 if you are able
to produce a patch.

> 
> > > 
> > > The libxc "osdep" interface (see xenctrlosdep.h) provides a framework
> > > for doing this, it just doesn't actually implement the use of the
> > > special driver yet.
> > > 
> > > Is that something you might be interested in coding up?
> > > 
> > > Ian.
> > 
> 
> 
> 
> _______________________________________________
> Xen-devel mailing list
> Xen-devel@xxxxxxxxxxxxx
> http://lists.xen.org/xen-devel



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