Messages in this thread | | | Date | Wed, 14 Jan 2009 18:18:00 +0100 | From | Nick Piggin <> | Subject | Re: [PATCH -v11][RFC] mutex: implement adaptive spinning |
| |
On Wed, Jan 14, 2009 at 06:00:36PM +0100, Peter Zijlstra wrote: > Full series, including changelogs available at: > > http://programming.kicks-ass.net/kernel-patches/mutex-adaptive-spin/ > > and should shortly appear in a git tree near Ingo :-)
Linus is going to take a wholesale conversion of mutexes to adaptive mutexes? He's gone soft. I put on my asbestos underwear for no reason, then.
> @@ -173,21 +237,21 @@ __mutex_lock_common(struct mutex *lock, > spin_unlock_mutex(&lock->wait_lock, flags); > > debug_mutex_free_waiter(&waiter); > + preempt_enable(); > return -EINTR; > } > __set_task_state(task, state); > > /* didnt get the lock, go to sleep: */ > spin_unlock_mutex(&lock->wait_lock, flags); > - schedule(); > + __schedule();
Why does this need to do a preempt-disabled schedule? After we schedule away, the next task can do arbitrary things or reschedule itself, so if we have not anticipated such a condition here, then I can't see what __schedule protects. At least a comment is in order?
Pity to add the call overhead to schedule just for this case. BTW. __schedule shouldn't need to be asmlinkage?
> spin_lock_mutex(&lock->wait_lock, flags); > } >
| |