if you use this source (https://docs.kernel.org/admin-guide/hw-vuln/) to interpret your output you will eventually come to the conclusion—well I can only speak for myself----I came to the conclusion I was well-protected on this end. I interpret my own output as everything is being done that can be done, and I have an older Intel quad core.
It was about 20 minutes of learning for me, thought it was cool. this post is just FYI. edit/added word
Gather data sampling: Not affected
Itlb multihit: Not affected
L1tf: Not affected
Mds: Not affected
Meltdown: Not affected
Mmio stale data: Not affected
Retbleed: Not affected
Spec rstack overflow: Vulnerable, no microcode
Spec store bypass: Vulnerable
Spectre v1: Vulnerable: __user pointer sanitization and usercopy barriers only; no swapgs barriers
Spectre v2: Vulnerable, IBPB: disabled, STIBP: disabled, PBRSB-eIBRS: Not affected
Srbds: Not affected
Tsx async abort: Not affected
Yeah maybe you shouldn’t, but I didn’t hear any widespread exploitation of these vulnerabilities and I’ve been turning off these mitigations for years now, even on windows.
If you don’t do anything too sensitive on your pc, like you only game and visit trusted sites, you’re probably safe. Just don’t visit sketchy sites and run random programs with mitigations turned off. Personally I’d rather turn off javascript first, only enable it for trustworthy sites, than kneecap my cpu.
thank you, not looking for a performance boost, I’m content and don’t game beyond quadrapassel anymore. or that weird game where rabbits stab each other to death and do jujitsu I forget the name.
The salmon banner with 2 linked articles (I read them both) saying how dangerous mitigation=off is enough to dissuade me. Even Arch says my old Intel would gain only “up to” a 5% boost.
I don’t always trust the people/orgs who tell me what ‘untrustworthy’ and ‘sketchy’ is more than I do my own instincts at this point. Weird times!
I wonder if the older CPU doesn’t have the vulnerability (yet) - as most of the mitigations are for backdoors in ‘speculative execution’ workflows. Did a Core 2 even indulge in speculation? (if so - why were they so slow? )