On Fri, May 27, 2022 at 12:25:53PM +0200, Ingo Molnar wrote: > Turns out Boris just sent a competing optimization to clear_user() 3 days ago: > > https://lore.kernel.org/r/YozQZMyQ0NDdD8cH@xxxxxxx Yes, and that one needs to be properly measured and verified it doesn't impact any workload. I have been working on this for a while now so let's all relax ourselves - it'll get fixed properly eventually. What you could do in the meantime is, run it and see if your microbenchmarks are happy with it. Because clear_user() doesn't matter one whit in real workloads, as we realized upthread. Thx. -- Regards/Gruss, Boris. https://people.kernel.org/tglx/notes-about-netiquette
