From: Stephen Hemminger <stephen@networkplumber.org>
To: "François-Frédéric Ozog" <ff@ozog.com>
Cc: dev@dpdk.org
Subject: Re: [dpdk-dev] Bit spinlocks in DPDK
Date: Fri, 20 Dec 2013 08:36:14 -0800 [thread overview]
Message-ID: <20131220083614.2a996421@nehalam.linuxnetplumber.net> (raw)
In-Reply-To: <04be01cefd9c$a3c36460$eb4a2d20$@com>
On Fri, 20 Dec 2013 17:00:43 +0100
François-Frédéric Ozog <ff@ozog.com> wrote:
>
>
> > -----Message d'origine-----
> > De : Thomas Monjalon [mailto:thomas.monjalon@6wind.com]
> > Envoyé : vendredi 20 décembre 2013 16:39
> > À : François-Frédéric Ozog
> > Cc : dev@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.
prev parent reply other threads:[~2013-12-20 16:35 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-12-06 21:04 Pashupati Kumar
2013-12-06 22:02 ` Thomas Monjalon
2013-12-06 22:12 ` Pashupati Kumar
2013-12-06 22:24 ` Thomas Monjalon
2013-12-06 22:54 ` Pashupati Kumar
2013-12-07 17:54 ` François-Frédéric Ozog
2013-12-19 16:41 ` Thomas Monjalon
2013-12-20 15:39 ` Thomas Monjalon
2013-12-20 16:00 ` François-Frédéric Ozog
2013-12-20 16:36 ` Stephen Hemminger [this message]
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20131220083614.2a996421@nehalam.linuxnetplumber.net \
--to=stephen@networkplumber.org \
--cc=dev@dpdk.org \
--cc=ff@ozog.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).