Live data from Hacker News

OpenBSD on Zenbleed

marc.info

31–40 of 64 posts

Re: OpenBSD on Zenbleed

#31
>"OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do"

While I love OpenBSD and what they do ... I have to admit, I get frustrated because many times OpenBSD is immune to security vulnerability simply because they don't implement modern tech advancements like AVX.

Not being as vulnerable doesn't make OpenBSD more "secure", it just makes them behind the times - like riding a horse & buggy in a world that's quickly evolving to electric vehicles.

Re: OpenBSD on Zenbleed

#32
"OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do, so this is not as important.

On Linux, glibc has AVX-based optimizations for simple functions (string and memory copies) which will store secrets into the register file which can be extracted trivially, so the impact on glibc-based systems is HUGE."

Perhaps I missed something, but it appears musl does not use AVX instructions much if at all.

Re: OpenBSD on Zenbleed

#33
post #30
post #27

Earlier quoted context omitted.

Incorrect. They had explicit permission from the researcher involved to commit when they did. Here's the full discussion, if you want to read it yourself. https://marc.info/?l=openbsd-tech&m=152909822107104&w=2 More directly, from the KRACK FAQ: As a compromise, I allowed them to silently patch the vulnerability. https://www.krackattacks.com/#openbsd It's also worth noting that Microsoft violated the embargo as well:…

I mean, I just disagree with that interpretation of 2018 events. The embargo deadline was extended, OpenBSD violated that. They refused to play ball with the coordinated extension. The researcher is orthogonal to that. Their actions in 2018 are certainly not universally celebrated as a good way to participate in an embargo.

You don't get to extend an embargo unilaterally. Now that there's a new uniform 90 days the conversation looks different.

Re: OpenBSD on Zenbleed

#34

> "OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do" While I love OpenBSD and what they do ... I have to admit, I get frustrated because many times OpenBSD is immune to security vulnerability simply because they don't implement modern tech advancements like AVX. Not being as vulnerable doesn't make OpenBSD more "secure", it just makes them behind the times - like riding a horse…

More like a walkable city in a world that is quickly devolving into noisy, polluted, car-dependent cities. You may find that over a decade or a few hundred years negative externalities of a technical decision outweigh the benefits. When AVX dies a painful death in the next decade, projects like OpenBSD won't feel as much pain from it.

Having such lousy implementation bugs show that at least AMD doesn't care about it anymore, I'd wager there is something better coming round in the near future.

Re: OpenBSD on Zenbleed

#36

> "OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do" While I love OpenBSD and what they do ... I have to admit, I get frustrated because many times OpenBSD is immune to security vulnerability simply because they don't implement modern tech advancements like AVX. Not being as vulnerable doesn't make OpenBSD more "secure", it just makes them behind the times - like riding a horse…

You might need a box to be as safe as possible, but performance is secondary. Following your car example, some people prefer a safer car over a faster one.

If you chose Open BSD you make that explicit choice. Their promise is to avoid technologies unless they are rock solid, even at the cost of performance or convenience (like the forking to LibreSSL).

Re: OpenBSD on Zenbleed

#37
post #34

> "OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do" While I love OpenBSD and what they do ... I have to admit, I get frustrated because many times OpenBSD is immune to security vulnerability simply because they don't implement modern tech advancements like AVX. Not being as vulnerable doesn't make OpenBSD more "secure", it just makes them behind the times - like riding a horse…

More like a walkable city in a world that is quickly devolving into noisy, polluted, car-dependent cities. You may find that over a decade or a few hundred years negative externalities of a technical decision outweigh the benefits. When AVX dies a painful death in the next decade, projects like OpenBSD won't feel as much pain from it. Having such lousy implementation bugs show that at least AMD doesn't care about it…

I think this is a bit short sighted. In the end, x86 will be replaced entirely, should openbsd just ditch it altogether?

Re: OpenBSD on Zenbleed

#38

> On Linux, glibc has AVX-based optimizations for simple functions (string and memory copies) which will store secrets into the register file which can be extracted trivially, so the impact on glibc-based systems is HUGE. Interesting. I would have expected it to be some amount of worse performance not using AVX. Though perhaps the past throttling effects from AVX-512 and friends made it so it was too complex to manag…

Full pipe string copies are not a frequent task for any OS.

Large memory copies, however, are quite frequent.

Re: OpenBSD on Zenbleed

#39

> "OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do" While I love OpenBSD and what they do ... I have to admit, I get frustrated because many times OpenBSD is immune to security vulnerability simply because they don't implement modern tech advancements like AVX. Not being as vulnerable doesn't make OpenBSD more "secure", it just makes them behind the times - like riding a horse…

Or that just mean the rest of the industry is careless about their security and unrespectful of their users and prefer racing the marketing and performance arm race.

Re: OpenBSD on Zenbleed

#40
post #34

> "OpenBSD does not use the AVX instructions to the same extent that Linux and Microsoft do" While I love OpenBSD and what they do ... I have to admit, I get frustrated because many times OpenBSD is immune to security vulnerability simply because they don't implement modern tech advancements like AVX. Not being as vulnerable doesn't make OpenBSD more "secure", it just makes them behind the times - like riding a horse…

More like a walkable city in a world that is quickly devolving into noisy, polluted, car-dependent cities. You may find that over a decade or a few hundred years negative externalities of a technical decision outweigh the benefits. When AVX dies a painful death in the next decade, projects like OpenBSD won't feel as much pain from it. Having such lousy implementation bugs show that at least AMD doesn't care about it…

If you think AVX will die “a painful death in the next decade” you’re not really in a good position to call AMD’s implementation lousy.
Post reply on HN