From owner-svn-src-all@FreeBSD.ORG Fri May 25 00:04:57 2012 Return-Path: Delivered-To: svn-src-all@freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [69.147.83.52]) by hub.freebsd.org (Postfix) with ESMTP id 06B74106566B; Fri, 25 May 2012 00:04:57 +0000 (UTC) (envelope-from marcel@xcllnt.net) Received: from mail.xcllnt.net (mail.xcllnt.net [70.36.220.4]) by mx1.freebsd.org (Postfix) with ESMTP id C02738FC18; Fri, 25 May 2012 00:04:51 +0000 (UTC) Received: from marcelm-sslvpn-nc.jnpr.net (natint3.juniper.net [66.129.224.36]) (authenticated bits=0) by mail.xcllnt.net (8.14.5/8.14.5) with ESMTP id q4P04c1g075837 (version=TLSv1/SSLv3 cipher=AES128-SHA bits=128 verify=NO); Thu, 24 May 2012 17:04:44 -0700 (PDT) (envelope-from marcel@xcllnt.net) Mime-Version: 1.0 (Apple Message framework v1278) Content-Type: text/plain; charset=us-ascii From: Marcel Moolenaar In-Reply-To: <4FBEBA30.6050901@freebsd.org> Date: Thu, 24 May 2012 17:04:33 -0700 Content-Transfer-Encoding: quoted-printable Message-Id: References: <201205242045.q4OKjipb059398@svn.freebsd.org> <4FBEA493.4020702@freebsd.org> <4FBEB2F3.4060405@freebsd.org> <358A54BA-6B8E-4685-8CDD-CCAC305ACA2B@xcllnt.net> <4FBEBA30.6050901@freebsd.org> To: Nathan Whitehorn X-Mailer: Apple Mail (2.1278) Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, Marcel Moolenaar , src-committers@freebsd.org Subject: Re: svn commit: r235931 - head/sys/powerpc/include X-BeenThere: svn-src-all@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: "SVN commit messages for the entire src tree \(except for " user" and " projects" \)" List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 25 May 2012 00:04:57 -0000 On May 24, 2012, at 3:46 PM, Nathan Whitehorn wrote: > On 05/24/12 17:22, Marcel Moolenaar wrote: >>=20 >> On May 24, 2012, at 3:15 PM, Nathan Whitehorn wrote: >>=20 >>>>> Summary: >>>>> 1. *mb() must be lwsync or sync on all machines, except for wmb() = which could be eieio >>>>> 2. __ATOMIC_ACQ() must be isync (though could be reduced to lwsync = with bus_space changes) >>>>> 3. __ATOMIC_REL() must be lwsync or sync >>>>=20 >>>> This is absolutely not what I concluded from our discussions. I = have no idea >>>> how we could end up so out of sync... >>>>=20 >>>=20 >>> Thanks for the quick change. No idea how we got out of sync. I find = all of this synchronization stuff a little mind-bending, so sorry for = any miscommunication. __ATOMIC_ACQ() needed to also be isync on ppc64, = so I've fixed that up. Things should be good now. >>=20 >> Ok. I didn't change wmb() to eieio as I wanted to avoid a pendulum = effect. >> I'll reread our emails and make sure wmb() is what we think it is and = if >> so I'll do a followup commit. >> FYI, >>=20 >=20 > I don't think it really makes a difference. Basically nothing uses = wmb(), and those things that do mostly use it wrong and need sync. So it = should probably stay as [lw]sync. Works for me. Thanks! --=20 Marcel Moolenaar marcel@xcllnt.net