Date: Mon, 3 Sep 2001 19:54:24 -0500 From: Alfred Perlstein <bright@mu.org> To: Jake Burkholder <jake@FreeBSD.org> Cc: cvs-committers@FreeBSD.org, cvs-all@FreeBSD.org Subject: Re: cvs commit: src/sys/sparc64/include atomic.h Message-ID: <20010903195424.T81307@elvis.mu.org> In-Reply-To: <200109032203.f83M3Pm95695@freefall.freebsd.org>; from jake@FreeBSD.org on Mon, Sep 03, 2001 at 03:03:25PM -0700 References: <200109032203.f83M3Pm95695@freefall.freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
* Jake Burkholder <jake@FreeBSD.org> [010903 17:03] wrote: > jake 2001/09/03 15:03:25 PDT > > Modified files: > sys/sparc64/include atomic.h > Log: > Add atomic_load and store functions without membars, fwiw. > > Revision Changes Path > 1.4 +25 -6 src/sys/sparc64/include/atomic.h My apologies, but these look wrong, my sparc v9 manual says that although the atomic ops will work atomically without membar... that if you don't use membar you don't know the sequencing of the stores and loads surrounding the atomic op, so if it is an atomic op to perform a lock, your memory sequencing may cause accesses to a locked object before the lock is aquired or at least allow memory accesses to bleed through after the lock is released. Of course I could be smoking the good crack today, so take this with a grain of salt. :-) -- -Alfred Perlstein [alfred@freebsd.org] 'Instead of asking why a piece of software is using "1970s technology," start asking why software is ignoring 30 years of accumulated wisdom.' To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe cvs-all" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20010903195424.T81307>