On Thu, Mar 07, 2024 at 01:48:28PM -0800, Dave Hansen wrote: > On 3/7/24 13:08, Yosry Ahmed wrote: > > CPU 1 CPU 2 > > /* user thread running */ > > context_switch() /* to kthread */ > > /* user thread enables LAM */ > > context_switch() > > context_switch() /* to user thread */ > > > > In this case, there are no races, but the second context switch on CPU 1 > > may not write CR3 (if TLB is up-to-date), in which case we will run the > > user thread with CR3 having the wrong LAM mask. This could cause bigger > > problems, right? > > Yes, but this is precisely the kind of thing that we should solve with > mm generations. Its sole purpose is to thwart optimization where the > mm_prev==mm_next and might not rewrite CR3. I think it's clearer to have an explicit check for oudated LAM in switch_mm_irqs_off(), as I mentioned in my other reply.
