From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail203.messagelabs.com (mail203.messagelabs.com [216.82.254.243]) by kanga.kvack.org (Postfix) with ESMTP id 58B576B0062 for ; Thu, 25 Jun 2009 00:37:11 -0400 (EDT) Date: Thu, 25 Jun 2009 06:38:18 +0200 From: Nick Piggin Subject: Re: [PATCH v2] slab,slub: ignore __GFP_WAIT if we're booting or suspending Message-ID: <20090625043818.GB23949@wotan.suse.de> References: <20090612091002.GA32052@elte.hu> <84144f020906120249y20c32d47y5615a32b3c9950df@mail.gmail.com> <20090612095206.GA13607@wotan.suse.de> <1244800774.7172.116.camel@pasglop> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1244800774.7172.116.camel@pasglop> Sender: owner-linux-mm@kvack.org To: Benjamin Herrenschmidt Cc: Pekka Enberg , Ingo Molnar , linux-mm@kvack.org, linux-kernel@vger.kernel.org, akpm@linux-foundation.org, cl@linux-foundation.org, torvalds@linux-foundation.org List-ID: On Fri, Jun 12, 2009 at 07:59:34PM +1000, Benjamin Herrenschmidt wrote: > > > Maybe if we just not make it a general "tweak gfpflag" bit (at > > least not until a bit more discussion), but a specific workaround > > for the local_irq_enable in early boot problem. > > > > Seems like it would not be hard to track things down if we add > > a warning if we have GFP_WAIT and interrupts are not enabled... > > But tweaking local_irq_enable() will have a lot more performance & bloat > impact overall on the normal case. (sorry for the late replies. I've been sick and missed a few things over the past week or two... not that this is a really urgent issue ;)) I was not proposing to put a branch in local_irq_enable ;) but to use local_irq_save/restore in the slab allocators rather than unconditional. -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org