From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Message-ID: <42C275FB.40209@yahoo.com.au> Date: Wed, 29 Jun 2005 20:20:43 +1000 From: Nick Piggin MIME-Version: 1.0 Subject: Re: Remaining arch problems in cpu_idle References: <42C24874.8030702@yahoo.com.au> <20050629080058.GA2694@linux-sh.org> <42C26552.5020304@yahoo.com.au> <20050629101145.GB2694@linux-sh.org> In-Reply-To: <20050629101145.GB2694@linux-sh.org> Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit To: Paul Mundt Cc: linux-arch@vger.kernel.org, Andrew Morton List-ID: Paul Mundt wrote: > On Wed, Jun 29, 2005 at 07:09:38PM +1000, Nick Piggin wrote: >>Now this might introduce some power and heat penalty. What's more, >>your race isn't a fatal one: in the worst case, it should just >>stall until the next timer interrupt (aside, that might be fatal >>with a tickless kernel). >> > > After incorporating your changes, how about this? > So, just ignore the race, remove the irq disabling completely? (with the hlt_counter fallback for busy waiting). If you're happy with that then I think it looks good. Thanks Paul. I'll also update the Documentation/ file to point out that such a race isn't fatal. -- SUSE Labs, Novell Inc. Send instant messages to your online friends http://au.messenger.yahoo.com