Live data from Hacker News

Disable SMT/Hyperthreading in all Intel BIOSes

marc.info

121–130 of 159 posts

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#121
post #11

Earlier quoted context omitted.

Thinking about this, they're probably gonna introduce "insecure but cheap" instances for customers that don't mind the chance of data leaks and takeovers...

That would be hard to market.

For private databases, sure, but I don't need that security if I am running an isolated server that only hosts public data.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#122

We have disabled Hyper Threading(HT) on all public facing servers(running OpenBSD). However, our compute nodes running Linux kernel are benefiting about 80 to near 100% boost for specific scientific workloads. So, we run our INTERNAL NETWORK ONLY compute nodes with HT on. In places where security is not primary concern, why not make use of HT for extra efficiency? Think and plan before you blanket disable HT on all s…

Agree. A personal computer could probably even risk it as long as they don't run untrusted javascript (which they shouldn't do anyways, or only under sandboxed/careful conditions).

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#123

It's not clear that he's using "SMT" to refer to AMD specifically as he goes on to talk about "Intel CPUs" and disabling it in "Intel BIOS". Does the Zen architecture have the same issue?

SMT is the generic name? Hyper-Threading is the name of Intel's 2 way SMT implementation. I don't think they call the Xeon Phi 4-way SMT Hyper-Threading, but I could be wrong there.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#124
post #87

Does this mean AMD hyperthreading has a performance + security advantage over currently shipping Intel processors? Edit: https://www.amd.com/en/corporate/security-updates > 8/14/18 – Updated: As in the case with Meltdown, we believe our processors are not susceptible to these new speculative execution attack variants: L1 Terminal Fault – SGX (also known as Foreshadow) CVE 2018-3615, L1 Terminal Fault – OS/SMM (also k…

With the newer AMD processors having as many real cores as they do, does the cost-benefit analysis of HT/SMT change? I read in a comment here a few weeks ago that turning it off on the newer AMD CPUs can yield better performance because of improved cache-coherency on some workloads (My memory of what I read might be totally wrong).

I'll defer to whatever the benchmarks say of course, but I don't see why HT would affect cache coherency for normal workloads. If you disable HT you'd still have the same number of threads/processes running on the system, so you still have to schedule the same amount of work and do the same number of context switches.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#125

Does that mean hyperthreading is effectively unpatchably insecure? Cloud Providers are gonna have a bad time if this is true.

Is there any risk this also impacts browsers executing JS?

Yes. you are executing JavaScript after all.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#126

Scary looking headline on a discussion forum with instructions to perform a task that the average user would not really understand, with no explanation of attack vector or even consequences for any user who doesn't want to take the time (and energy, frankly at this point) to follow security news. I'm pretty close to not caring anymore. I hope somebody figures out how to at least fix the security news infrastructure,…

This is not security news at all. This is Theo de Raadt's personal E-mail sent to the OpenBSD development mailing list for system developers. It is never intended for the consumption by the general public.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#128

Does anyone know the best way to disable hyperthreading on Linux?

Okay, I found it. A SMT knob was added alongside in the L1TF fixes.

    /sys/devices/system/cpu/smt

    /sys/devices/system/cpu/smt/active

    /sys/devices/system/cpu/smt/control

    active:  Tells whether SMT is active (enabled and siblings online)
    control: Read/write interface to control SMT. Possible

    values:

    "on"		SMT is enabled
    "off"		SMT is disabled
    "forceoff"   	SMT is force disabled. Cannot be changed.
    "notsupported"	SMT is not supported by the CPU

    If control status is "forceoff" or "notsupported" writes are rejected.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#129

Earlier quoted context omitted.

If you fully trust the software you're running, I see no reason to disable HT. At this point, I don't think I'd have it running on anything publicly facing, though. That said, I still have it enabled on my work PC & home PC.

Do you fully trust all the JavaScript you run?

Nope, which is why I generally have JS disabled.

Re: Disable SMT/Hyperthreading in all Intel BIOSes

#130
post #11

Earlier quoted context omitted.

That would be hard to market.

Indeed, the idea of "Security" is not negotiable when marketing. Imagine buying a car that says, "Save $5000 for a less safe version without airbags." Yes, I know Airbags are DOT requirement, just trying to make a point. Edit: I think people are missing my point. I am not saying they don't sell cheaper models that are less safe. My point is that they don't ACTIVELY market them as such. Point me to an advertisement th…

...and people still buy motorcycles (which are significantly cheaper), proving that "security" or "safety" is not an absolute, nor a must-have.
Post reply on HN