Re: [uclinux-dist-devel] freezer: should barriers be smp ?

From: Mike Frysinger <vapier@gentoo.org>
To: Pavel Machek <pavel@ucw.cz>
Cc: uclinux-dist-devel@blackfin.uclinux.org,
	linux-pm@lists.linux-foundation.org,
	linux-kernel@vger.kernel.org
Subject: Re: [uclinux-dist-devel] freezer: should barriers be smp ?
Date: Fri, 15 Apr 2011 12:33:12 -0400	[thread overview]
Message-ID: <BANLkTikaymG-5-YoTnG2SPJCnBtXPpfHBQ__15909.1273825199$1302885351$gmane$org@mail.gmail.com> (raw)
In-Reply-To: <20110415162938.GA11454@atrey.karlin.mff.cuni.cz>

On Fri, Apr 15, 2011 at 12:29, Pavel Machek wrote:
>> > > I believe the code is correct as is.
>> >
>> > that isnt what the code / documentation says.  unless i'm reading them
>> > wrong, both seem to indicate that the proposed patch is what we
>> > actually want.
>>
>> The existing code is correct but it isn't optimal.
>>
>> wmb() and rmb() are heavy-duty operations, and you don't want to call
>> them when they aren't needed.  That's exactly what smp_wmb() and
>> smp_rmb() are for -- they call wmb() and rmb(), but only in SMP
>> kernels.
>>
>> Unless you need to synchronize with another processor (not necessarily
>> a CPU, it could be something embedded within a device), you should
>> always use smp_wmb() and smp_rmb() rather than wmb() and rmb().
>
> Maybe; but this code is not performance critical and I believe being
> obvious here is better...

isnt it though ?  especially when we talk about suspending/resuming on
embedded systems to get more savings over just cpu idle ?  we want
that latency to be as low as possible.
-mike
_______________________________________________
linux-pm mailing list
linux-pm@lists.linux-foundation.org
https://lists.linux-foundation.org/mailman/listinfo/linux-pm