From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1760887Ab2J2UtN (ORCPT ); Mon, 29 Oct 2012 16:49:13 -0400 Received: from hrndva-omtalb.mail.rr.com ([71.74.56.122]:9739 "EHLO hrndva-omtalb.mail.rr.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752991Ab2J2Uiu (ORCPT ); Mon, 29 Oct 2012 16:38:50 -0400 X-Authority-Analysis: v=2.0 cv=KcBQQHkD c=1 sm=0 a=rXTBtCOcEpjy1lPqhTCpEQ==:17 a=mNMOxpOpBa8A:10 a=Ciwy3NGCPMMA:10 a=MNlvnKoIE-IA:10 a=5SG0PmZfjMsA:10 a=bbbx4UPp9XUA:10 a=meVymXHHAAAA:8 a=x_XpADtinfgA:10 a=pGLkceISAAAA:8 a=VwQbUJbxAAAA:8 a=Z4Rwk6OoAAAA:8 a=20KFwNOVAAAA:8 a=9AzMRrQhAAAA:8 a=NufY4J3AAAAA:8 a=KKAkSRfTAAAA:8 a=JfrnYn6hAAAA:8 a=ftUzEednAAAA:8 a=sozttTNsAAAA:8 a=EUspDBNiAAAA:8 a=VnNF1IyMAAAA:8 a=fh4mg5NFAAAA:8 a=c5n4SWRlhl7AJMFnYpUA:9 a=MSl-tDqOz04A:10 a=LI9Vle30uBYA:10 a=jbrJJM5MRmoA:10 a=jEp0ucaQiEUA:10 a=SxxB86fLhQ4A:10 a=re9sYKne76oA:10 a=WwgC8nHKvroA:10 a=3Rfx1nUSh_UA:10 a=QwxQZocgbLcA:10 a=x2szoZtqnggA:10 a=IG2fH9E8heMA:10 a=Im-eZXwrtqoA:10 a=jeBq3FmKZ4MA:10 a=Zh68SRI7RUMA:10 a=rXTBtCOcEpjy1lPqhTCpEQ==:117 X-Cloudmark-Score: 0 X-Originating-IP: 74.67.115.198 Message-Id: <20121029203848.400689448@goodmis.org> User-Agent: quilt/0.60-1 Date: Mon, 29 Oct 2012 16:27:23 -0400 From: Steven Rostedt To: linux-kernel@vger.kernel.org Cc: Andrew Morton , Thomas Gleixner , Peter Zijlstra , Clark Williams , Frederic Weisbecker , Li Zefan , Ingo Molnar , "Paul E. McKenney" , Mike Galbraith , Alessio Igor Bogani , Avi Kivity , Chris Metcalf , Christoph Lameter , Daniel Lezcano , Geoff Levand , Gilad Ben Yossef , Hakan Akkan , Kevin Hilman , Max Krasnyansky , Stephen Hemminger , Sven-Thorsten Dietrich Subject: [PATCH 12/32] rcu: Restart tick if we enqueue a callback in a nohz/cpuset CPU References: <20121029202711.062749374@goodmis.org> Content-Disposition: inline; filename=0012-rcu-Restart-tick-if-we-enqueue-a-callback-in-a-nohz-.patch Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org From: Frederic Weisbecker If we enqueue an rcu callback, we need the CPU tick to stay alive until we take care of those by completing the appropriate grace period. Thus, when we call_rcu(), send a self IPI that checks rcu_needs_cpu() so that we restore a periodic tick behaviour that can take care of everything. Signed-off-by: Frederic Weisbecker Cc: Alessio Igor Bogani Cc: Andrew Morton Cc: Avi Kivity Cc: Chris Metcalf Cc: Christoph Lameter Cc: Daniel Lezcano Cc: Geoff Levand Cc: Gilad Ben Yossef Cc: Hakan Akkan Cc: Ingo Molnar Cc: Kevin Hilman Cc: Max Krasnyansky Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Stephen Hemminger Cc: Steven Rostedt Cc: Sven-Thorsten Dietrich Cc: Thomas Gleixner Signed-off-by: Steven Rostedt --- kernel/rcutree.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/rcutree.c b/kernel/rcutree.c index 21664a3..7dce432 100644 --- a/kernel/rcutree.c +++ b/kernel/rcutree.c @@ -2081,6 +2081,13 @@ static void invoke_rcu_core(void) static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp, struct rcu_head *head, unsigned long flags) { + /* Restart the timer if needed to handle the callbacks */ + if (cpuset_adaptive_nohz()) { + /* Make updates on nxtlist visible to self IPI */ + barrier(); + smp_cpuset_update_nohz(smp_processor_id()); + } + /* * If called from an extended quiescent state, invoke the RCU * core in order to force a re-evaluation of RCU's idleness. -- 1.7.10.4