Nebulet: A Rust Microkernel Running WebAssembly In Ring 0

[phoronix]

Phoronix: Nebulet: A Rust Microkernel Running WebAssembly In Ring 0

You should likely be familiar with WebAssembly as the binary format for executing code within web pages that can be nearly as fast as running native machine code -- and certainly much faster than JavaScript. A new research project has been exploring running WebAssembly in the CPU's Ring 0 -- yes, the highest privileged state of the processor -- in the name of better performance...

http://www.phoronix.com/scan.php?page=news_item&px=Nebulet-Ring-0-WebAssembly

[GunpowaderGuy]

This should be inmune to meltdown by default , how much performance do the orher vulnerabilities cost un Intel ? And in AMD ?

[FastCode]

Has threading and verifies if it accesses the memory region intended for it.
Show me this magic, I need it in my ring 3 code.

[GunpowaderGuy]

Funny how tecnlogy evolves , i was thinking that redox mayor be better off not using wayland , but that Is not the case in this even newer os where ipc will be dirt cheap

[anarki2]

<insert "I'm too old for this shit" meme here>

[trek]

This should be inmune to meltdown by default , how much performance do the orher vulnerabilities cost un Intel ? And in AMD ?

only intel cpus are affected by meltdown, anyway how this microkernel should be immune?
javascript can be an attack vector https://webkit.org/blog/8048/what-sp...an-for-webkit/

[bregma]

Just give an untrusted third party physical access to your hardware. Nothing could go wrong.

[speculatrix]

only intel cpus are affected by meltdown, anyway how this microkernel should be immune?
javascript can be an attack vector https://webkit.org/blog/8048/what-sp...an-for-webkit/

Intel, Power and Arm processors are all affected by meltdown.

https://meltdownattack.com/

however, it's only the Cortex A7x series which are affected, lesser processors don't have the same speculative execution that leads to this problem

[LubosD]

only intel cpus are affected by meltdown, anyway how this microkernel should be immune?
javascript can be an attack vector https://webkit.org/blog/8048/what-sp...an-for-webkit/

Because there is no userspace in this project.

[GunpowaderGuy]

metldown proved that hatdware memory protection in some cpus ( not amd but not only intel either ) is faulty , this os is not affected because it does not uses that feature