From mboxrd@z Thu Jan  1 00:00:00 1970
From: Roland Dreier <rdreier@cisco.com>
Subject: Re: [PATCH 4/7] SMP: Implement on_one_cpu()
Date: Thu, 24 May 2007 06:43:32 -0700
Message-ID: <adaejl68hh7.fsf@cisco.com>
References: <1180008615579-git-send-email-avi@qumranet.com>
	<11800086152009-git-send-email-avi@qumranet.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: kvm-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org,
	shaohua.li@intel.com, lhcs-devel@lists.sourceforge.net
To: Avi Kivity <avi@qumranet.com>
Return-path: <linux-kernel-owner+glk-linux-kernel-3=40m.gmane.org-S1750911AbXEXNnu@vger.kernel.org>
In-Reply-To: <11800086152009-git-send-email-avi@qumranet.com> (Avi Kivity's message of "Thu, 24 May 2007 15:10:12 +0300")
Sender: linux-kernel-owner@vger.kernel.org
List-Id: kvm.vger.kernel.org

I don't see any documented restrictions about preemption being
disabled when this function is called, but...

 > +int on_one_cpu(int cpu, void (*func) (void *info), void *info,
 > +	       int retry, int wait)
 > +{
 > +	int ret;
 > +	int this_cpu;
 > +
 > +	this_cpu = get_cpu();

what if a preempt and reschedule to a different CPU happens right
here, after this_cpu is set?

 > +	if (this_cpu == cpu) {