PortSmash CVE-2018-5407 - @RaptorEng @IBMPowerSystems
Any comments on how vulnerable #POWER9 is to this kind of attack?
Especially with regard to the Nimbus SMT4 core pairs being very similar to single SMT8 Cumulus cores.
@RaptorCompSys, your 8 & 4 core chips are unpaired, right?https://twitter.com/marcan42/status/1058405454999543808 …
There is no way around the fact that if you have two threads dynamically sharing compute resources, one thread will always be able to influence the other, and/or measure the other's influence. Otherwise they aren't really sharing resources, just partitioning them.
-
-
The obvious workaround is to only allow threads that "trust each other" to share resources, e.g. part of the same process so they can directly access each others' memory anyway. That's probably how it should've been done right from the start.
-
Yup. I don't know why nobody is rushing to get this implemented, it should've been obvious since the first batch of vulns.https://twitter.com/marcan42/status/1058415187672260608 …
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.