Electronics, windows internals, cryptography, hardware, lasers, chemistry, demoscene, ADHD. I run @unsafe_warnings and hack stuff for a living, I guess (he/him)
Jan 4, 2018 • 4 tweets • 1 min read
It was known by Intel, AMD, Google Project Zero, and a few others during the multiparty responsible disclosure process, which took a couple of months. There's some speculation that Intel's CEO made his recent share divestment decision based on the disclosure timeline.
Now that it has been disclosed I fully expect others to focus on more microarchitectural vulnerability research on x86, ARM, and other architectures. I think a lot of this was spurred by recent developments in cache side-channel attacks, so we're likely to see a repeat pattern.
When a processor reaches a conditional branch in code (e.g. an 'if' clause), it tries to predict which branch will be taken before it actually knows the result. It executes that branch ahead of time - a feature called "speculative execution".
The idea is that if it gets the prediction right (which modern processors are quite good at) it'll already have executed the next bit of code by the time the actually-selected branch is known. If it gets it wrong, execution unwinds back and the correct branch is executed instead.
