Messages in this thread | | | Subject | Re: [PATCH v5 2/4] MCS Lock: optimizations and extra comments | From | Tim Chen <> | Date | Tue, 19 Nov 2013 14:57:41 -0800 |
| |
On Tue, 2013-11-19 at 11:13 -0800, Paul E. McKenney wrote: > On Fri, Nov 08, 2013 at 11:52:05AM -0800, Tim Chen wrote: > > > > +/* > > + * Releases the lock. The caller should pass in the corresponding node that > > + * was used to acquire the lock. > > + */ > > static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node) > > { > > struct mcs_spinlock *next = ACCESS_ONCE(node->next); > > @@ -51,7 +60,7 @@ static void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *nod > > /* > > * Release the lock by setting it to NULL > > */ > > - if (cmpxchg(lock, node, NULL) == node) > > + if (likely(cmpxchg(lock, node, NULL) == node)) > > Agreed here as well. Takes a narrow race to hit this. > > So, did your testing exercise this path? If the answer is "yes",
Paul,
I did some instrumentation and confirmed that the path in question has been exercised. So this patch should be okay.
Tim
> and if the issues that I called out in patch #1 are resolved: > > Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> > > > return; > > /* Wait until the next pointer is set */ > > while (!(next = ACCESS_ONCE(node->next))) > >
| |