Re: [PATCH] x86/refcount: Implement fast refcount_t handling

[PaX Team]

On 24 Apr 2017 at 10:32, Peter Zijlstra wrote:

> On Fri, Apr 21, 2017 at 03:09:39PM -0700, Kees Cook wrote:
> > This patch ports the x86-specific atomic overflow handling from PaX's
> > PAX_REFCOUNT to the upstream refcount_t API. This is an updated version
> > from PaX that eliminates the saturation race condition by resetting the
> > atomic counter back to the INT_MAX saturation value on both overflow and
> > underflow. To win a race, a system would have to have INT_MAX threads
> > simultaneously overflow before the saturation handler runs.

note that the above is wrong (and even contradicting itself and the code).

> And is this impossible? Highly unlikely I'll grant you, but absolutely
> impossible?

here's my analysis from a while ago:
http://www.openwall.com/lists/kernel-hardening/2017/01/05/19

> Also, you forgot nr_cpus in your bound. Afaict the worst case here is
> O(nr_tasks + 3*nr_cpus).

what does nr_cpus have to do with winning the race?

> Because PaX does it, is not a correctness argument. And this really
> wants one.

heh, do you want to tell me about how checking for a 0 refcount prevents
exploiting a bug?