From mboxrd@z Thu Jan 1 00:00:00 1970 From: Linus Torvalds Subject: Re: mmu_notifiers: turn off lockdep around mm_take_all_locks Date: Tue, 7 Jul 2009 12:25:21 -0700 (PDT) Message-ID: References: <20090707180630.GA8008@amt.cnet> <1246990505.5197.2.camel@laptop> <4A53917C.6080208@redhat.com> <20090707183741.GA8393@amt.cnet> <1246993442.5197.15.camel@laptop> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: Marcelo Tosatti , Avi Kivity , Andrea Arcangeli , kvm , Ingo Molnar To: Peter Zijlstra Return-path: Received: from smtp1.linux-foundation.org ([140.211.169.13]:47589 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755659AbZGGT0F (ORCPT ); Tue, 7 Jul 2009 15:26:05 -0400 In-Reply-To: <1246993442.5197.15.camel@laptop> Sender: kvm-owner@vger.kernel.org List-ID: On Tue, 7 Jul 2009, Peter Zijlstra wrote: > > Another issue, at about >=256 vmas we'll overflow the preempt count. So > disabling lockdep will only 'fix' this for a short while, until you've > bloated beyond that ;-) We would? I don't think so. Sure, we'd "overflow" into the softirq bits, but it's all designed to faile very gracefully. Somebody who tests our "status" might think we're in softirq context, but that really doesn't matter: we still have preemption disabled. > Linus, Ingo, any opinions? I do think that if lockdep can't handle it, we probably should turn it off around it. I don't think it's broken wrt regular preempt, though. Linus