On Wed, Oct 27, 2021 at 10:48:55AM -0600, Alex Williamson wrote: > Ok, I see. I didn't digest that contention on state_mutex can only > occur from a concurrent migration region access and the stale state is > resolved at the end of that concurrent access, not some subsequent > access. Ah, I see, yes, that is tricky - the spinlock around the mutex provides the guarentee: deferral cannot be set at mutex_lock() time. Jason
