Re: ordered memory access

Benjamin Herrenschmidt (bh40@calva.net)
Thu, 30 Sep 1999 14:38:49 +0200


On Thu, Sep 30, 1999, Jes Sorensen <Jes.Sorensen@cern.ch> wrote:

>atomic_foo() should be ordered, at least that the idea behind it as
>far as I understand.
>
>Otherwise you want to look at mb(), rmb() and wmb(). mb() is a generic
>memory barrier, wmb() makes sure a write is issues before another
>write() and rmb() ... you get the idea ;-)

The last time I discussed this with Paul Mackerras, he told me that the
atomic_xxx functions were not expected to enforce ordering. (At this
time, the linuxppc versions didn't do a sync instruction for this
reason). I didn't check recent linuxppc versions however.

-- 
           Perso. e-mail: <mailto:bh40@calva.net>
           Work   e-mail: <mailto:benh@mipsys.com>
BenH.      Web   : <http://calvaweb.calvacom.fr/bh40/>

- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.rutgers.edu Please read the FAQ at http://www.tux.org/lkml/