On Mon, 19 Jun 2017 16:13:41 +0200 Sebastian Andrzej Siewior <[email protected]> wrote:
> > Hmm, it shouldn't affect futexes, as it's only called by rtmutex when > > waiter->savestate is true. And that should always be false for futex. > > you still have sleeping locks like the hb-lock (which might matter in > case the task blocks on the lock and does not continue for some reason). But then I'd expect this to be an issue with any spinlock in the kernel. -- Steve
