This was very well known when the mitigations came out but I do wonder if they were too broad.
sure mitigation in place for a platform that run untrusted code like a browser make sense but should it affect every program running? I know trust is fickle but at least for power user there should be an option to disable mitigation on a per program basis.
> sure mitigation in place for a platform that run untrusted code like a browser make sense but should it affect every program running?
The issue is that mainstream OS's are simply not designed to protect against information disclosure vulns like Spectre in a principled way. https://en.wikipedia.org/wiki/Multilevel_security is a very well known approach academically but practical implementation is lacking. So we have to go with one-size-fits-all mitigations that treat all code as untrusted, and all data as potentially sensitive.
