From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ingo Molnar Subject: Re: [PATCH 1/1] x86: replace cpu_up hard-coded mdelay with variable Date: Mon, 20 Apr 2015 09:13:06 +0200 Message-ID: <20150420071306.GA14315@gmail.com> References: <1429404795-23260-1-git-send-email-lenb@kernel.org> <87d69aab88c14d65ae1e7be55050d1b689b59b4b.1429402494.git.len.brown@intel.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Received: from mail-wi0-f181.google.com ([209.85.212.181]:34687 "EHLO mail-wi0-f181.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752641AbbDTHNL (ORCPT ); Mon, 20 Apr 2015 03:13:11 -0400 Content-Disposition: inline In-Reply-To: <87d69aab88c14d65ae1e7be55050d1b689b59b4b.1429402494.git.len.brown@intel.com> Sender: linux-pm-owner@vger.kernel.org List-Id: linux-pm@vger.kernel.org To: Len Brown Cc: x86@kernel.org, linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org, Len Brown , Borislav Petkov , "H. Peter Anvin" , Thomas Gleixner * Len Brown wrote: > +config X86_INIT_MDELAY > + int "Milliseconds to wait to de-assert INIT upon CPU startup" if SMP > + range 0 10 > + default "10" > + ---help--- > + This allows you to specify how long the BSP will delay > + between asserting INIT and de-asserting INIT when starting another CPU. > + This delay is paid on each cpu-online operation, including boot-time, > + resume from suspend, and resume from hibernate. The the value of > + 10 millisec was specified by Multi-Processor Spec 1.4 in 1997. > + But modern hardware does not require any delay. What's the cutoff for 'modern hardware' - which CPUs stopped requiring the delay? Also, is there any public document where the no-delay is specified for 'modern hardware'? Thanks, Ingo