Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755515Ab0ARSdN (ORCPT ); Mon, 18 Jan 2010 13:33:13 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1754234Ab0ARSdM (ORCPT ); Mon, 18 Jan 2010 13:33:12 -0500 Received: from tomts36-srv.bellnexxia.net ([209.226.175.93]:58777 "EHLO tomts36-srv.bellnexxia.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752157Ab0ARSdL (ORCPT ); Mon, 18 Jan 2010 13:33:11 -0500 X-IronPort-Anti-Spam-Filtered: true X-IronPort-Anti-Spam-Result: AhkFAAIzVEuuWOiG/2dsb2JhbACBRtQmhDME Date: Mon, 18 Jan 2010 13:33:09 -0500 From: Mathieu Desnoyers To: Masami Hiramatsu Cc: Arjan van de Ven , "H. Peter Anvin" , rostedt@goodmis.org, Jason Baron , linux-kernel@vger.kernel.org, mingo@elte.hu, tglx@linutronix.de, andi@firstfloor.org, roland@redhat.com, rth@redhat.com Subject: Re: [RFC PATCH 2/8] jump label v4 - x86: Introduce generic jump patching without stop_machine Message-ID: <20100118183309.GA12099@Krystal> References: <1263483139.28171.3857.camel@gandalf.stny.rr.com> <4B4F3A1A.2030906@zytor.com> <20100117185539.GF9008@Krystal> <20100117111608.35a98ee2@infradead.org> <4B548562.6030008@redhat.com> <20100118083129.675edb83@infradead.org> <20100118165443.GB29764@Krystal> <4B54A68E.4050409@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Disposition: inline In-Reply-To: <4B54A68E.4050409@redhat.com> X-Editor: vi X-Info: http://krystal.dyndns.org:8080 X-Operating-System: Linux/2.6.27.31-grsec (i686) X-Uptime: 13:30:22 up 33 days, 2:48, 5 users, load average: 0.26, 0.28, 0.19 User-Agent: Mutt/1.5.18 (2008-05-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1759 Lines: 59 * Masami Hiramatsu (mhiramat@redhat.com) wrote: > Mathieu Desnoyers wrote: > > * Arjan van de Ven (arjan@infradead.org) wrote: > >> On Mon, 18 Jan 2010 10:59:30 -0500 > >> Masami Hiramatsu wrote: > >> > >>> Yeah, so in the latest patch, I updated it to use int3 even if > >>> len == 1. :-) > >>> > >> > >> > >> int3 is not making a difference for your case; there is no guarantee > >> that the other processor even sees the "int3 inbetween state" at all; > >> if it's not safe without int3 then it won't be safe with int3 either. > > > > What Masami means is that he updated his patch to use the int3+IPI > > broadcast scheme. > > Right. > > > > > Therefore, the CPUs not seeing the int3 inbetween state will be forced > > to issue a serializing instruction while the int3 is in place anyway. > > By the way, in kprobes, we just use a text_poke() to put int3. > I assume that we'd better send IPI afterward, wouldn't it? Only if you need to ensure that you reached a state where all CPUs are seeing the int3. Note that kprobes already issues synchronize_sched() after breakpoint removal, which should have a similar effect. However, AFAIK, it does not synchronize after inserting the int3. Thanks, Mathieu > > Thank you, > > -- > Masami Hiramatsu > > Software Engineer > Hitachi Computer Products (America), Inc. > Software Solutions Division > > e-mail: mhiramat@redhat.com > -- Mathieu Desnoyers OpenPGP key fingerprint: 8CD5 52C3 8E3C 4140 715F BA06 3F25 A8FE 3BAE 9A68 -- 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/