wait, what said it didn't apply to AMD? The current kernel master applies it to all x86
-
-
Replying to @11rcombs @pwnallthethings1 reply 0 retweets 7 likes
-
Replying to @AndresFreundPol @pwnallthethings
ah, missed that as it hasn't landed yet. So, I wonder if the message tells us anything about the bug class? "speculative references, that access higher privileged data…"
1 reply 0 retweets 0 likes -
Replying to @11rcombs @pwnallthethings
It does seem to tell us some. I'm surprised that an AMD employee, who apparently was privy to details about the embargoed bug, disclosed this much...
2 replies 0 retweets 4 likes -
Is there any evidence he is? I don't see any, in fact him replying at so late a stage with a change that would have been known early on, and this change not being merged yet, suggests otherwise
1 reply 0 retweets 2 likes -
No hard evidence, no. But being able to determine that the underlying bug doesn't apply to any AMD CPUs seems to require more details than are public. And Dave Hansen replied, who seems likely to have been involved from the Intel side.
1 reply 0 retweets 1 like -
Could just be operating off the public KASLR claims, which FWIW, one of the generic attacks I had written up that worked on all my Intel systems isn't producing a clear kernel image range on my AMD EPYC system (only got it recently, but had never thought to test).
1 reply 1 retweet 5 likes
Possible, but I hope not. Wouldn't be a good look if disabling it based on some vague turned out to be wrong.
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.