Messages in this thread | | | Date | Wed, 30 Jun 2010 09:52:02 +0100 | From | "Jan Beulich" <> | Subject | Re: [PATCH 2/4, v2] x86: enlightenment for ticket spin locks - Xen implementation |
| |
>>> On 30.06.10 at 10:05, Peter Zijlstra <peterz@infradead.org> wrote: > On Tue, 2010-06-29 at 15:32 +0100, Jan Beulich wrote: >> +static DEFINE_PER_CPU(arch_rwlock_t, spinning_rm_lock) = > __ARCH_RW_LOCK_UNLOCKED; > > why is that an arch_ lock?
Because I don't think it is appropriate to use anything higher level in the callouts from the lock/unlock inline functions. The alternative would be an open coded lock, which seems much less desirable to me.
> why is that a rwlock?, those things are useless.
Because potentially each CPU's lock gets acquired for reading during unlock, while only the locking CPU's one needs to be acquired for writing during lock.
Jan
| |