News for hackers. Stuff that matters.
Re:A one in a million bug in Switch kernel by Dylan16807 on Wednesday March 23, 2022 @06:35PM (#30784438)
The problem is very simple, isn't it? There are instructions that need a memory barrier after them. If the thread leaves the core, then from the view of that core no memory barrier happens.

And it's a particular kind of memory barrier that nothing else does incidentally.

There are no comments on this comment yet.