[dpdk-dev] Bit spinlocks in DPDK
Stephen Hemminger
stephen at networkplumber.org
Fri Dec 20 17:36:14 CET 2013
On Fri, 20 Dec 2013 17:00:43 +0100
François-Frédéric Ozog <ff at ozog.com> wrote:
>
>
> > -----Message d'origine-----
> > De : Thomas Monjalon [mailto:thomas.monjalon at 6wind.com]
> > Envoyé : vendredi 20 décembre 2013 16:39
> > À : François-Frédéric Ozog
> > Cc : dev at dpdk.org
> > Objet : Re: [dpdk-dev] Bit spinlocks in DPDK
> >
> > Hello,
> >
> > 07/12/2013 18:54, François-Frédéric Ozog :
> > > 1) If the critical section deals with weakly ordered loads then
> > > explicit fencing MUST be used: if not, out of order execution will
> > > just kill your idea of critical section.
> > [...]
> > > So use rte_mb() or rte_wmb() or rte_rmb() where appropriate. I
> > > recommend the rte_unlock code and documentation explains the out of
> > > order execution issues and the conditions they have to be mitigated
> > > with rte*mb(). I wonder if having an explicit mfence in
> > > rte_sinlock_unlock wouldn't be just necessary to avoid "hairy" bugs.
> > > In addition, we would have rte_sinlock_unlock_no_mb used internally
> > > for performance reasons, and usable externally by advanced users.
> >
> > Using lock prefix is lighter than using memory barrier and have the same
> > effects.
>
> Well, in general yes BUT Intel states "../.. locked operations serialize all
> outstanding load and store operations ../.. with one exception. Load
> operations that reference weakly ordered memory types (such as the WC memory
> type) may *not* be serialized" in 8.1.2.2 Software Controlled Bus Locking;
> particularly if streaming loads are used (may happen on certain devices
> memory mapped I/O accesses and the compiler generating streaming loads).
>
> So this comment is essentially for the PMD writers: use the fencing where
> appropriate, even if the lock prefix is there. As I will be the one
> forgetting the rule, I like to have that in the documentation/comments as
> reminders to keep things neat.
>
> François-Frédéric
I recommend anyone who needs more information read:
Documentation/memory-barriers.txt
in the Linux kernel source.
More information about the dev
mailing list