From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754568Ab2AaNrd (ORCPT ); Tue, 31 Jan 2012 08:47:33 -0500 Received: from mx1.redhat.com ([209.132.183.28]:1025 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753368Ab2AaNrc (ORCPT ); Tue, 31 Jan 2012 08:47:32 -0500 Message-ID: <4F27F0E6.1040309@redhat.com> Date: Tue, 31 Jan 2012 15:47:18 +0200 From: Avi Kivity User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:9.0) Gecko/20111222 Thunderbird/9.0 MIME-Version: 1.0 To: Peter Zijlstra CC: "Paul E. McKenney" , Oleg Nesterov , linux-kernel , Marcelo Tosatti , KVM list Subject: Re: [RFC][PATCH] srcu: Implement call_srcu() References: <1328016724.2446.229.camel@twins> In-Reply-To: <1328016724.2446.229.camel@twins> Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 01/31/2012 03:32 PM, Peter Zijlstra wrote: > Subject: srcu: Implement call_srcu() > From: Peter Zijlstra > Date: Mon Jan 30 23:20:49 CET 2012 > > Implement call_srcu() by using a state machine driven by > call_rcu_sched() and timer callbacks. > > The state machine is a direct derivation of the existing > synchronize_srcu() code and replaces synchronize_sched() calls with a > call_rcu_sched() callback and the schedule_timeout() calls with simple > timer callbacks. > > It then re-implements synchronize_srcu() using a completion where we > send the complete through call_srcu(). > > It completely wrecks synchronize_srcu_expedited() which is only used > by KVM. 3 of the 5 2 of the 5 > use cases look like they really want to use > call_srcu() instead, the remaining 2 I don't know but hope they can, > which would let us remove it. They really need to return quickly to userspace, and they really need to perform some operation between rcu_assign_pointer() and returning, so no. > > Compile tested only!! :-) > How much did synchronize_srcu_expedited() regress? Presumably your compiler didn't tell you that. Can we get it back to speed by scheduling a work function on all cpus? wouldn't that force a quiescent state and allow call_srcu() to fire? In kvm's use case synchronize_srcu_expedited() is usually called when no thread is in a critical section, so we don't have to wait for anything except the srcu machinery. -- error compiling committee.c: too many arguments to function