Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752631AbaBDHNX (ORCPT ); Tue, 4 Feb 2014 02:13:23 -0500 Received: from g1t0027.austin.hp.com ([15.216.28.34]:33728 "EHLO g1t0027.austin.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751810AbaBDHNP (ORCPT ); Tue, 4 Feb 2014 02:13:15 -0500 Message-ID: <1391497992.2774.17.camel@j-VirtualBox> Subject: Re: [RFC][PATCH v2 5/5] mutex: Give spinners a chance to spin_on_owner if need_resched() triggered while queued From: Jason Low To: Peter Zijlstra Cc: Ingo Molnar , Paul McKenney , Waiman Long , Linus Torvalds , Thomas Gleixner , Linux Kernel Mailing List , Rik van Riel , Andrew Morton , Davidlohr Bueso , "H. Peter Anvin" , Andi Kleen , "Chandramouleeswaran, Aswin" , "Norton, Scott J" , chegu_vinod@hp.com Date: Mon, 03 Feb 2014 23:13:12 -0800 In-Reply-To: <20140203192525.GN8874@twins.programming.kicks-ass.net> References: <20140128210753.GJ11314@laptop.programming.kicks-ass.net> <1390949495.2807.52.camel@j-VirtualBox> <20140129115142.GE9636@twins.programming.kicks-ass.net> <1391138977.6284.82.camel@j-VirtualBox> <20140131140941.GF4941@twins.programming.kicks-ass.net> <20140131200825.GS5002@laptop.programming.kicks-ass.net> <1391374883.3164.8.camel@j-VirtualBox> <20140202211230.GX5002@laptop.programming.kicks-ass.net> <1391452760.7498.26.camel@j-VirtualBox> <20140203192525.GN8874@twins.programming.kicks-ass.net> Content-Type: text/plain; charset="UTF-8" X-Mailer: Evolution 3.2.3-0ubuntu6 Content-Transfer-Encoding: 7bit Mime-Version: 1.0 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, 2014-02-03 at 20:25 +0100, Peter Zijlstra wrote: > +void m_spin_unlock(struct m_spinlock **lock) > +{ > + struct m_spinlock *node = this_cpu_ptr(&m_node); > + struct m_spinlock *next; > + > + if (likely(cmpxchg(lock, node, NULL) == node)) > + return; At this current point, (node->next != NULL) is a likely scenario. Perhaps we can also add the following code here: next = xchg(&node->next, NULL); if (next) { ACCESS_ONCE(next->locked) = 1; return; } > + next = m_spin_wait_next(lock, node, NULL); > + if (next) > + ACCESS_ONCE(next->locked) = 1; > +} -- 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/