Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752965AbZK3I70 (ORCPT ); Mon, 30 Nov 2009 03:59:26 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1752274AbZK3I7Z (ORCPT ); Mon, 30 Nov 2009 03:59:25 -0500 Received: from hera.kernel.org ([140.211.167.34]:38621 "EHLO hera.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751503AbZK3I7X (ORCPT ); Mon, 30 Nov 2009 03:59:23 -0500 Message-ID: <4B138950.9040905@kernel.org> Date: Mon, 30 Nov 2009 17:58:56 +0900 From: Tejun Heo User-Agent: Mozilla/5.0 (X11; U; Linux x86_64; en-US; rv:1.9.1.4pre) Gecko/20090915 SUSE/3.0b4-3.6 Thunderbird/3.0b4 MIME-Version: 1.0 To: Avi Kivity CC: Thomas Gleixner , Peter Zijlstra , Jiri Slaby , linux-kernel@vger.kernel.org, akpm@linux-foundation.org, mm-commits@vger.kernel.org, Marcelo Tosatti , kvm@vger.kernel.org, the arch/x86 maintainers , Ingo Molnar Subject: Re: WARNING: kernel/smp.c:292 smp_call_function_single [Was: mmotm 2009-11-24-16-47 uploaded] References: <200911250111.nAP1BFg5030254@imap1.linux-foundation.org> <4B0FEA3E.5050108@gmail.com> <1259335036.6483.440.camel@laptop> <4B1113C0.30505@redhat.com> In-Reply-To: <4B1113C0.30505@redhat.com> X-Enigmail-Version: 0.97a Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1803 Lines: 46 Hello, On 11/28/2009 09:12 PM, Avi Kivity wrote: >> Hmm, commit 498657a moved the fire_sched_in_preempt_notifiers() call >> into the irqs disabled section recently. >> >> sched, kvm: Fix race condition involving sched_in_preempt_notifers >> >> In finish_task_switch(), fire_sched_in_preempt_notifiers() is >> called after finish_lock_switch(). >> >> However, depending on architecture, preemption can be enabled after >> finish_lock_switch() which breaks the semantics of preempt >> notifiers. >> >> So move it before finish_arch_switch(). This also makes the in- >> notifiers symmetric to out- notifiers in terms of locking - now >> both are called under rq lock. >> >> It's not a surprise that this breaks the existing code which does the >> smp function call. > > Yes, kvm expects preempt notifiers to be run with irqs enabled. Copying > patch author. Hmmm... then, it's broken both ways. The previous code may get preempted after scheduling but before the notifier is run (which breaks the semantics of the callback horribly), the current code doesn't satisfy kvm's requirement. Another thing is that in the previous implementation the context is different between the 'in' and 'out' callbacks, which is subtle and nasty. Can kvm be converted to not do smp calls directly? For the time being, maybe it's best to back out the fix given that the only architecture which may be affected by the original bug is ia64 which is the only one with both kvm and the unlocked context switch. Thanks. -- tejun -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/