From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755950AbYGaRtR (ORCPT ); Thu, 31 Jul 2008 13:49:17 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1753144AbYGaRtB (ORCPT ); Thu, 31 Jul 2008 13:49:01 -0400 Received: from gw.goop.org ([64.81.55.164]:51596 "EHLO mail.goop.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752744AbYGaRtA (ORCPT ); Thu, 31 Jul 2008 13:49:00 -0400 Message-ID: <4891FB0A.907@goop.org> Date: Thu, 31 Jul 2008 10:48:58 -0700 From: Jeremy Fitzhardinge User-Agent: Thunderbird 2.0.0.14 (X11/20080501) MIME-Version: 1.0 To: Peter Zijlstra CC: Nick Piggin , Ingo Molnar , Jens Axboe , Andi Kleen , Linux Kernel Mailing List , Thomas Gleixner , "H. Peter Anvin" Subject: Re: x86: Is there still value in having a special tlb flush IPI vector? References: <488E534F.2030204@goop.org> <200807291430.08220.nickpiggin@yahoo.com.au> <1217325288.7563.2.camel@twins> <200807292000.30690.nickpiggin@yahoo.com.au> <1217328351.7563.12.camel@twins> In-Reply-To: <1217328351.7563.12.camel@twins> X-Enigmail-Version: 0.95.6 Content-Type: text/plain; charset=ISO-8859-15 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Peter Zijlstra wrote: > How about using just arch_send_call_function_single_ipi() to implement > smp_send_reschedule() ? > > The overhead of that is a smp_mb() and a list_empty() check in > generic_smp_call_function_single_interrupt() if there is indeed no work > to do. > Is doing a no-op interrupt sufficient on all architectures? Is there some change a function call IPI might not go through the normal reschedule interrupt exit path? J