Linux 6.12-rc5 Disabling Intel's Linear Address Masking "LAM" Due To Security Concerns

[phoronix]

Phoronix: Linux 6.12-rc5 Disabling Intel's Linear Address Masking "LAM" Due To Security Concerns

Intel merged Linear Address Masking into the Linux kernel last year as a means of allowing user-space to store metadata within some bits of pointers without masking it out before use. LAM can be useful for virtual machines, sanitizers / profiling / memory tagging, and other uses. While the brand new Intel Arrow Lake and Lunar Lake CPUs support LAM, the Linux kernel is now disabling LAM out of security concerns...

https://www.phoronix.com/news/Linux-Disabling-Intel-LAM

[hf_139]

My next CPU will be a Chinese RISC-V.
And if it takes five to ten years till they get ready, i will wait.

[hamishmb]

It is disappointing how many CPU vulnerabilities there seem to be, and that's not even counting the ones we don't know about yet.

[loganj]

so intel put the cart before the horse?

[pWe00Iri3e7Z9lHOX2Qx]

I get that these features are more important on Xeons so things will probably be fine on Sierra Forest with LASS. But this is still quite embarrassing for Intel.

[skeevy420]

So a system can be exploited by a transient on the LAM? Y'all need social engineering training. Homeless criminals shouldn't have access to your systems that easily.

It's funny how once there's a LASS involved we don't have to worry about all of this. Goes to show that it really is the good woman behind the man that really matters.

[intelfx]

So a system can be exploited by a transient on the LAM? Y'all need social engineering training. Homeless criminals shouldn't have access to your systems that easily.

It's funny how once there's a LASS involved we don't have to worry about all of this. Goes to show that it really is the good woman behind the man that really matters.

You certainly tried hard, here's your award: 🤡🤡🤡

[npwx]

Once again, good job Intel, I wonder what they are doing professionally. At least the feature is DoA and doesn't cost you 50% performance six months down the road.

[ikoz]

My next CPU will be a Chinese RISC-V.
And if it takes five to ten years till they get ready, i will wait.

Remember the [GhostWrite](https://ghostwriteattack.com/) attack for RISC-V CPUs?

CPU vulnerabilities will exist as long as companies do 'smart tricks' to increase performance and rush to release them to catch up with rivals, without adequate testing.
Surely most are theoretical and there is only a PoC, but that doesn't stop them from being applicable.

[JEBjames]

@Michael

Typo

"But besides Linus Torvalds not liking Intel's "LAN" name" should be "LAM"