@yogthos who's taking betting odds on whether WebAssembly loses threading again over this
@yogthos ok so my reading of the paper is that the sky is *not* falling, and existing Spectre mitigations cover all the cases described.
It's a re-analysis of some earlier prefetch vulnerabilities as actually being Spectre variants, which caused prefetching in a syscall using bad data.
Some of the original mitigations for those vulns only worked by accident by shuffling registers, and can be retired in favor of using the Spectre mitigations which are already in use.
@mhoye This has seriously been my desktop background for at least a year.
Server run by the main developers of the project It is not focused on any particular niche interest - everyone is welcome as long as you follow our code of conduct!