On Thu, 01 Jun 2023 21:12:10 -0700 Stefan Roesch wrote: > The problem with checking need_resched in loop_end is that need_resched > can be false in loop_end, however the check for need_resched in > napi_busy_loop succeeds. This means that we unlock the rcu read lock and > call schedule. However the code in io_napi_blocking_busy_loop still > believes we hold the read lock. Ah, yes, now it makes sense. Yeah, that's a race, scratch the workaround idea then. Let's work on revising the patches, we'll see where we are in the development process when they're ready.
