Some features in NVIDIA chipsets, like changing the operating frequency, needs (hardware checked, I think) signed binary blobs. This prevents the open source nouveau driver from achieving good performance. Does this hack helps in this front?
That doesn't necessarily rule it out. Cryptography is one of those things that once you get it down, you stick with it. It is entirely possible this may give enough insight into Nvidia's SOP with cryptography to extend the PoC proven on Tegra to something like their firmware signing functionality in GM 204 cards. At least, I haven't seen anything that stands out enough to downright disclude the possibility from possibly nudging things down the road, in theory.
>Because this is a (unmitigable!) hardware issue in all Falcons which have SCP, not just TSEC -- we were also able to use the same attack on the Falcon unit used for GPU power management, recovering its (different) signing key as well.
In short, the same methodology, assuming you put a crap ton of time into reading this, and really grokking it, suggests this attack could be applied not just to Tegra, but any secretful Falcon.
