Re:Mitigations=off considered harmful or spurious SIGILL on ...
by vlovich123 on Sunday October 08, 2023 @07:10PM
(#37815260)
Is it likely the issue is within the Linux kernel itself or within the microcode for the CPU?
Re:Mitigations=off considered harmful or spurious SIGILL on ...
by AnotherGoodName on Sunday October 08, 2023 @07:31PM
(#37815379)
Pretty sure it'd be microcode. The OS can group threads from the same process onto the same CPU but that's very weak enforcement so should be occasionally hit even with process affinity set. So heavily suspecting microcode.
Re:Mitigations=off considered harmful or spurious SIGILL on ...
by AnotherGoodName on Sunday October 08, 2023 @08:43PM
(#37815735)
I'm going to say microcode until someone reproduces on a completely different architecture :).
Re:Mitigations=off considered harmful or spurious SIGILL on ...
by jdiff on Sunday October 08, 2023 @09:10PM
(#37815883)
A lot of these mitigations are joint efforts between the kernel and CPU, and the mitigations kernel parameter isn't a binary on/off, you can configure individual mitigations. It's not a single flag that does signals the microcode to do spooky proprietary things.
The mitigations work by making sure to clear everything they can when the CPU switches contexts. This includes clearing loaded local CPU cache, clearing the branch prediction table, clearing all speculative execution entries. The mitigations likely avoid a crash by clearing something that should be cleared between context switches in all cases. As in the mitigations likely accidentally fix this. Which is a good clue. It'd be nice if the mitigations were more fine grained than all or nothing so we could turn on the mitigations one by one but the microcode is not open so we can't do this :(.