Mitigating imagined vulnerabilities with costly workarounds that nobody will turn on, what a time we're living in.
Now we're all speculating on speculative behavior. Any bets on whether Intel can fix this in microcode and at what performance cost? Kernel workaround looks like 5%-30% reportedly. https://lkml.org/lkml/2017/12/27/2 …
-
-
-
With al the hush-hush around this I doubt it's just a KASLR bypass.
- Show replies
New conversation -
-
-
The fact that they haven't released such a microcode update yet -- and that every OS vendor is (instead?) rushing to rewrite kernel memory management -- is evidence that they can't do so, I'd guess.
-
Oh, also: if AWS was offered the choice of applying a ucode update (can do that rebootless, right?) or rebooting every instance and taking a perf hit, they'd surely take the ucode option. But I think they've scheduled reboots. So perhaps that too suggests ucode's not coming.
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.