From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yinghai Lu Subject: Re: [PATCH 17/35] x86, lmb: Add x86 version of __lmb_find_area() Date: Fri, 14 May 2010 09:41:52 -0700 Message-ID: <4BED7D50.5070004@oracle.com> References: <1273796396-29649-1-git-send-email-yinghai@kernel.org> <1273796396-29649-18-git-send-email-yinghai@kernel.org> <1273804466.21352.400.camel@pasglop> <4BECF21C.7030006@oracle.com> <1273825884.21352.603.camel@pasglop> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Return-path: Received: from rcsinet10.oracle.com ([148.87.113.121]:59044 "EHLO rcsinet10.oracle.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755985Ab0ENQh6 (ORCPT ); Fri, 14 May 2010 12:37:58 -0400 In-Reply-To: <1273825884.21352.603.camel@pasglop> Sender: linux-arch-owner@vger.kernel.org List-ID: To: Benjamin Herrenschmidt Cc: Ingo Molnar , Thomas Gleixner , "H. Peter Anvin" , Andrew Morton , David Miller , Linus Torvalds , Johannes Weiner , linux-kernel@vger.kernel.org, linux-arch@vger.kernel.org On 05/14/2010 01:31 AM, Benjamin Herrenschmidt wrote: > On Thu, 2010-05-13 at 23:47 -0700, Yinghai wrote: > > >> for safe, and there is any problem with top to down allocation, we can >> ask user to check if low to high works... >> >> not just make user to get broken kernel. >> > Hrm. That's a bit gross. But ok, I don't care that much as long as your > x86 variant doesn't differ in semantics with the core lmb one and I'll > let Peter and/or Thomas to scream at you if they think it's gross > (hint: the code is) > > > those bits are line by line translation from current early_res code, and have been used for a while. so should be good as a fallback. YH