Live data from Hacker News

Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

redhat.com

11–20 of 119 posts

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#12
post #6
post #5

Earlier quoted context omitted.

Or just keep using AMD CPUs, because yet again they are unaffected https://www.amd.com/en/corporate/security-updates

I'm seriously thinking about getting an AMD CPU for my desktop when this i7 4770k finally needs replacing.

I upgraded from an i7-2600 to an 1800X over a year ago. Once the memory issues were solved (running at 3200 MHz vs ~2800 MHz), I've been happy with my purchase.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#13

We're at a stage where to be safe on x86 we need to have multiple microcode and kernel layers to be safe. At which point do we agree the performance increases over the last 20 years have been built on sand and move elsewhere?

Not all needs are driven by security.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#14

We're at a stage where to be safe on x86 we need to have multiple microcode and kernel layers to be safe. At which point do we agree the performance increases over the last 20 years have been built on sand and move elsewhere?

I think everyone can agree that CPU progress has been largely made from sand, yes.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#15

Earlier quoted context omitted.

Move where exactly? At this point x86 is the least of all evils that have respectable performance.

And this is why computing monocultures are bad, because the dominant architecture may have painted itself into a corner. That's why alternatives like Open POWER are important.

RISC-V is far more promising than OpenPOWER ever was.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#16

We're at a stage where to be safe on x86 we need to have multiple microcode and kernel layers to be safe. At which point do we agree the performance increases over the last 20 years have been built on sand and move elsewhere?

There is a lot of legacy cruft in x86, but it's the devil we know. After decades of use, we are still discovering vulnerabilities, in a platform thought to be well-understood.

The closest alternative would be ARM. In any case, it's a massive undertaking.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#17

We're at a stage where to be safe on x86 we need to have multiple microcode and kernel layers to be safe. At which point do we agree the performance increases over the last 20 years have been built on sand and move elsewhere?

It's probably time for a new architecture that isn't so convoluted with decades of optimizations and iterative improvements. It's also time for a computer system with one and only one general purpose processor (no tiny CPUs in storage or "system management" or every other device) Probably something like a programming language/OS/computer system written new with a CPU based on current GPU designs.

You won't make any CPU of reasonable performance without speculative execution and all the rest. Your limited by data dependencies and the only way to break them is to "cheat".

Unless your willing to run on the equivalent of a Cortex-M0 then you have to live with it.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#18

If helpful a few Cloud Providers Responses: Google Cloud - Google Cloud's protections against this new vulnerability: - https://cloud.google.com/blog/products/gcp/protecting-agains... ) - GCE Related information: - https://cloud.google.com/compute/docs/security-bulletins - GKE Related information: - https://cloud.google.com/kubernetes-engine/docs/security-bul... Oracle Cloud - https://blogs.oracle.com/oraclesecurity/…

For AWS: https://aws.amazon.com/security/security-bulletins/AWS-2018-...

(Disclaimer: I work at AWS, but I am not linking this in any sort of official capacity. I don't know any more details beyond what is listed in that bulletin, and can't answer any questions related to this, unfortunately.)

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#19

We're at a stage where to be safe on x86 we need to have multiple microcode and kernel layers to be safe. At which point do we agree the performance increases over the last 20 years have been built on sand and move elsewhere?

Or use the off-brand x86 (AMD) which has had very few of these vulnerabilities be useful on it.

Re: Understanding L1 Terminal Fault aka Foreshadow: What You Need to Know

#20
post #7

We're at a stage where to be safe on x86 we need to have multiple microcode and kernel layers to be safe. At which point do we agree the performance increases over the last 20 years have been built on sand and move elsewhere?

I'm pretty sure this attack doesn't apply to AMD, being built on the original Meltdown attack that was Intel specific. So what'll happen is Intel will change their chips to not do prefetching without also doing a permissions check like MAD does. Meltdown solved.

It's not built on meltdown. It's not about violating permissions, it's about treating the contents of a page table as valid even if the page is not present or (in the case of EPT, which is worse) also treating the physical address on the guest as a physical address on the host.

However, unlike meltdown it cannot access data that is not already in the L1 cache.

Post reply on HN