Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Date:   Tue, 2 Oct 2018 14:13:14 +0200 (CEST)
From:   Thomas Gleixner <tglx@linutronix.de>
To:     Juergen Gross <jgross@suse.com>
cc:     linux-kernel@vger.kernel.org, mingo@kernel.org,
        sthemmin@microsoft.com, mikelley@microsoft.com, kys@microsoft.com,
        haiyangz@microsoft.com, yi.y.sun@linux.intel.com, hpa@zytor.com
Subject: Re: [tip:x86/hyperv] x86/hyperv: Enable PV qspinlock for Hyper-V
In-Reply-To: <0005fc50-4415-87a0-1954-fb15a1f8bd0b@suse.com>
Message-ID: <alpine.DEB.2.21.1810021412060.12704@nanos.tec.linutronix.de>
References: <1538028104-114050-3-git-send-email-yi.y.sun@linux.intel.com> <tip-aaa7fc34c003bd8133a49f7634480cef6288ad55@git.kernel.org> <0005fc50-4415-87a0-1954-fb15a1f8bd0b@suse.com>
User-Agent: Alpine 2.21 (DEB 202 2017-01-01)
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On Tue, 2 Oct 2018, Juergen Gross wrote:

> Sorry for noticing this only now, but I have been fighting with
> Xen PV qspinlocks last weekend:
> 
> > +	/*
> > +	 * Read HV_X64_MSR_GUEST_IDLE MSR can trigger the guest's
> > +	 * transition to the idle power state which can be exited
> > +	 * by an IPI even if IF flag is disabled.
> > +	 */
> 
> What if interrupts are enabled? Won't a kick happening here just
> interrupt and then the following rdmsr result in a hang?
> 
> I believe the correct way would be to:
> 
> - disable interrupts before above READ_ONCE() and restore them
>   after the rdmsrl()
> 
> - return early if in_nmi()
> 
> similar as the kvm specific variant is doing it.

Interesting question. I zapped the last commit for now until this is
clarified.

Thanks,

	tglx