TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Linux 5.8 Set to Optionally Flush the L1d Cache on Context Switch

164 pointsby blopeurabout 5 years ago

8 comments

rayinerabout 5 years ago
I'm not that old, but I've been closely following these trends since the late 1990s, and it seems to me like we are descending into madness now. We are wiping out years of single-core performance gains--which have been hard to come by over the last decade to begin with--through all of these mitigations. It seems to me like maybe the mental model is broken. If untrusted code is running on the same core/package/what have you, your security has already been breached.
评论 #23299904 未加载
评论 #23297820 未加载
评论 #23299241 未加载
评论 #23297688 未加载
评论 #23298062 未加载
评论 #23299868 未加载
评论 #23297658 未加载
评论 #23298380 未加载
评论 #23298844 未加载
评论 #23299441 未加载
评论 #23298182 未加载
评论 #23298318 未加载
评论 #23304220 未加载
评论 #23302235 未加载
评论 #23300146 未加载
saagarjhaabout 5 years ago
&gt; This flushing does address CVE-2020-0550 for snoop-assisted L1 data sampling but the main emphasis seems to be on the &quot;yet to be discovered vulnerabilities.&quot;<p>I am unsure if this is just idle speculation (heh) that there may be issues in this area or there are issues that have been disclosed to vendors but not the public yet?
评论 #23296307 未加载
评论 #23298281 未加载
评论 #23300976 未加载
enitihasabout 5 years ago
The performance implications of this would be huge, and I hope it remains opt in for long time.
评论 #23296005 未加载
评论 #23296015 未加载
评论 #23298985 未加载
Trellmorabout 5 years ago
Last week Microsoft also rereleased the Intel microcode updates package [1][2]. I kinda expect to see a new CPU flaw in the next few days.<p>[1]<a href="https:&#x2F;&#x2F;support.microsoft.com&#x2F;en-us&#x2F;help&#x2F;4497165&#x2F;kb4497165-intel-microcode-updates" rel="nofollow">https:&#x2F;&#x2F;support.microsoft.com&#x2F;en-us&#x2F;help&#x2F;4497165&#x2F;kb4497165-i...</a><p>[2]<a href="https:&#x2F;&#x2F;www.windowslatest.com&#x2F;2020&#x2F;05&#x2F;21&#x2F;windows-10-kb4497165-update-released&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.windowslatest.com&#x2F;2020&#x2F;05&#x2F;21&#x2F;windows-10-kb449716...</a>
Zenstabout 5 years ago
So with more cores and associated L1 cache, context switching would be potentially less I would of thought, small but maybe measurable.<p>Interestingly enough: <a href="https:&#x2F;&#x2F;www.theregister.co.uk&#x2F;2020&#x2F;05&#x2F;24&#x2F;linus_torvalds_adopts_amd_threadripper&#x2F;" rel="nofollow">https:&#x2F;&#x2F;www.theregister.co.uk&#x2F;2020&#x2F;05&#x2F;24&#x2F;linus_torvalds_adop...</a>
Zenstabout 5 years ago
Maybe time to redo the ring model with multi core cpu&#x27;s now the norm.<p>Why one or two CPU cores couldn&#x27;t be dedicated to the OS aspect and locked out of user-space of any form, certainly would be something worth exploring.
评论 #23301096 未加载
评论 #23303402 未加载
ajsnigrutinabout 5 years ago
So.... when will we get a part of our money back, due to performance losses? (i&#x27;m talking about a case like Volkswagen)
评论 #23296292 未加载
评论 #23296523 未加载
raszabout 5 years ago
Thanks Intel.