Messages in this thread | | | Date | Mon, 29 Jun 2015 08:42:43 +0200 | From | Ingo Molnar <> | Subject | Re: [PATCH] x86, msr: Allow read access to /dev/cpu/X/msr |
| |
* Henrique de Moraes Holschuh <hmh@hmh.eng.br> wrote:
> On Sun, 28 Jun 2015, Prarit Bhargava wrote: > > > Is it easier to blacklist MSRs we don't want generally exposed, or only expose > > the ones that we think are safe? That's sort of a devil's advocate sort of > > question ;) and I'm wondering what the shorter list is. > > The only way to make MSR access safe is to allow it only by whitelisting. The > x86 platform restricts all MSR access to ring 0 for a damn good reason.
Exactly.
We also want to document them along the way: just exposing all doesn't achieve that.
> Also, such a whitelist would most likely need to be vendor and model-aware, and > to differentiate "allow reads" from "allow writes"...
Initially it should only allow reads - which I believe fully meets turbostat's needs.
Thanks,
Ingo
| |