Re: [Xen-devel] [PATCH 4/7] xen/arm32: Add skeleton to harden branch predictor aliasing attacks

[Stefano Stabellini <sstabellini@xxxxxxxxxx>]

On Wed, 31 Jan 2018, Julien Grall wrote:
> On 26/01/18 16:21, Julien Grall wrote:
> > > "Therefore hypervisor code running with guest vectors table should be
> > > minimized and always have interrupts and async aborts masked to reduce
> > > the risk to use them."
> > > 
> > > Do you think that it is clearer?
> > 
> > Well, that was covered by "interrupts". If you look at the Arm Arm, A, I, F
> > are considered all interrupts.
> 
> I reworked the paragraph and it is now:
> 
> "However, on arm32, each vector contain a single instruction. This means that
> the hardened vector tables may rely on the state of registers that does not
> hold when in the hypervisor (e.g SP is 8 bytes aligned). Therefore hypervisor
> code running with guest vectors table should be
> minimized and always have IRQ and SError masked to reduce the risk to use
> them."

I think it's much better, thanks!

_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxxxxxxxxx
https://lists.xenproject.org/mailman/listinfo/xen-devel