On Wed, Oct 02, 2013 at 11:57:55PM +1000, Michael Ellerman wrote:

On Wed, 2013-10-02 at 13:02 +0300, Gleb Natapov wrote:

quoted

On Wed, Oct 02, 2013 at 11:50:50AM +0200, Alexander Graf wrote:

quoted

On 02.10.2013, at 11:11, Alexander Graf wrote:

So how do you solve live migration between a kernel that has this patch and one that doesn't?

Yes, I alluded to it in my email to Paul and Paolo asked also. How this
interface is disabled? 

Yes that is a valid point.

We can't disable the interface at runtime, the guest detects its
presence at boot.

What will happen is the hcall will come through to QEMU, which will
reject it with H_FUNCTION (~= ENOSYS).

The current pseries-rng driver does not handle that case well, which is
exactly why I sent patches to fix it recently.

The only other option would be to feed it with /dev/random.

What about other way, if guest migrates from kvm that has no this
hypercall to one that has? We try to not change HW under guest during
migration.

quoted

Also hwrnd is MMIO in a host why guest needs to
use hypercall instead of emulating the device (in kernel or somewhere
else?). 

Because PAPR is a platform specification and it specifies that the
interface is a hypervisor call. We can't just decide we want to do it
differently.

Any insights on why it was specified this what. What is special about
hwrnd device that hypercall is needed to access it? I got that you didn't
just decide to implement it that way :) Also what will happen if guest
will find emulated hwrnd device, will it use it?

quoted

Another things is that on a host hwrnd is protected from
direct userspace access by virtue of been a device, but guest code (event
kernel mode) is userspace as far as hosts security model goes, so by
implementing this hypercall in a way that directly access hwrnd you
expose hwrnd to a userspace unconditionally. Why is this a good idea? 

I'm not sure I follow you.

The hwrng is accessible by host userspace via /dev/mem.

Regular user has no access to /dev/mem, but he can start kvm guest and
gain access to the device.

--
			Gleb.