On 14/06/16 14:32, Peter Zijlstra wrote: > On Tue, Jun 14, 2016 at 01:08:13PM +0100, Juri Lelli wrote: > > > + postunlock = rt_mutex_futex_unlock(&pi_state->pi_mutex, &wake_q); > > > > > > /* > > > * First unlock HB so the waiter does not spin on it once he got woken > > > + * up. Then wakeup the waiter by calling rt_mutex_postunlock(). Priority > > > + * is already adjusted and preemption is disabled to avoid inversion. > > > */ > > > spin_unlock(&hb->lock); > > > > > > + if (postunlock) > > > + rt_mutex_postunlock(&wake_q); > > > > I'm most probably missing something, but don't we still need to call > > wake_up_q() even when postunlock is false? IIUC, we were always doing > > that, rt_mutex_postunlock(), before this change (only calling > > preempt_enable() was conditional). > > Note that rt_mutex_slowunlock() only uses wake_q on the true path. When > it returns false, it will not have placed a task to wake up. >
Right. But, I thought we were still ending up calling wake_up_q before this change. Which however looked fine, as it won't do anything if no task is queued I guess. So, no problem before and no problem now I'd say. :-)
