AMD Errata: RDSEED failure on AMD Zen 5 Processors

(www.amd.com)
21 points jcalvinowens | 6 comments | 03 Nov 25 15:05 UTC | HN request time: 0.844s | source | bottom
1. jcalvinowens ◴[03 Nov 25 15:05 UTC] No.45799817[source]▶
See also: https://lore.kernel.org/lkml/20251103142800.GFaQi78AgT-qjY30...
2. rasz ◴[03 Nov 25 16:35 UTC] No.45800949[source]▶
again? https://arstechnica.com/gadgets/2019/10/how-a-months-old-amd... ZEN seems to have suspiciously a lot of those rdrand "bugs"
replies(1): >>45805064 #
3. jcalvinowens ◴[03 Nov 25 17:12 UTC] No.45801467[source]▶
I wrote a silly little testcase: https://gist.github.com/jcalvinowens/06530e6fc86f3b2c97a7027...

...but both affected znver5 machines I have "pass", so clearly there's more to it than AMD is telling us.

You should be able to get away with "-march=znver5 -mno-rdrnd -mno-rdseed" in CFLAGS if you care.

replies(1): >>45803822 #
4. jcalvinowens ◴[03 Nov 25 20:13 UTC] No.45803822[source]▶
Oh, actually the original report was very specific: https://lore.kernel.org/all/20251018024010.4112396-1-gourry@...
5. hulitu ◴[03 Nov 25 22:13 UTC] No.45805064[source]▶
CIA and NSA really need access to your data. /s