From mboxrd@z Thu Jan  1 00:00:00 1970
From: Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: [PATCH] kvm: fix waitqueue_active without memory barrier in
 virt/kvm/async_pf.c
Date: Fri, 9 Oct 2015 12:24:11 +0200
Message-ID: <561795CB.30006@redhat.com>
References: <17EC94B0A072C34B8DCF0D30AD16044A028747C1@BPXM09GP.gisp.nec.co.jp>
 <56177EAC.2070601@redhat.com>
 <20151009085040.GZ7520@twins.programming.kicks-ass.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Cc: Kosuke Tatsukawa <tatsu@ab.jp.nec.com>,
	Gleb Natapov <gleb@kernel.org>,
	"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
To: Peter Zijlstra <peterz@infradead.org>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mail-wi0-f182.google.com ([209.85.212.182]:33369 "EHLO
	mail-wi0-f182.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1753524AbbJIKYP (ORCPT <rfc822;kvm@vger.kernel.org>);
	Fri, 9 Oct 2015 06:24:15 -0400
In-Reply-To: <20151009085040.GZ7520@twins.programming.kicks-ass.net>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>



On 09/10/2015 10:50, Peter Zijlstra wrote:
> Not having actually read or thought about the issue at hand, its
> perfectly valid to pair an smp_mb() with either spin_lock() or
> spin_unlock().
> 
> IOW. MB <-> {ACQUIRE, RELEASE} is a valid pairing.

In this case it's an smp_mb() (store-load barrier) being paired with
another smp_mb(), so spin_unlock()'s release is not enough.

Paolo