From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-kernel-owner@vger.kernel.org>
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1751687AbdB0OpG (ORCPT <rfc822;w@1wt.eu>);
        Mon, 27 Feb 2017 09:45:06 -0500
Received: from merlin.infradead.org ([205.233.59.134]:45932 "EHLO
        merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1751611AbdB0OpF (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Mon, 27 Feb 2017 09:45:05 -0500
Date: Mon, 27 Feb 2017 15:05:00 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Wanpeng Li <kernellwp@gmail.com>
Cc: Mike Galbraith <efault@gmx.de>, LKML <linux-kernel@vger.kernel.org>,
        Ingo Molnar <mingo@elte.hu>, Thomas Gleixner <tglx@linutronix.de>,
        Borislav Petkov <bp@alien8.de>, Paolo Bonzini <pbonzini@redhat.com>
Subject: Re: tip.today - scheduler bam boom crash (cpu hotplug)
Message-ID: <20170227140500.GX6500@twins.programming.kicks-ass.net>
References: <1484811069.17751.14.camel@gmx.de>
 <20170119101924.GJ6485@twins.programming.kicks-ass.net>
 <20170119133633.GB6536@twins.programming.kicks-ass.net>
 <CANRm+CwH7mUkHGshKLJH5R28LUVHxfHiqfYP+CQYyhMUrnWo0g@mail.gmail.com>
 <20170227124349.GU6515@twins.programming.kicks-ass.net>
 <CANRm+Cy6yZtQcHx4K_S30RLjHgjze5JEFUBkziCVtUu9C4FfqQ@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CANRm+Cy6yZtQcHx4K_S30RLjHgjze5JEFUBkziCVtUu9C4FfqQ@mail.gmail.com>
User-Agent: Mutt/1.5.23.1 (2014-03-12)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Mon, Feb 27, 2017 at 09:48:35PM +0800, Wanpeng Li wrote:
> 2017-02-27 20:43 GMT+08:00 Peter Zijlstra <peterz@infradead.org>:
> > I have no clue what that tries to do.
> 
> The patch tries to mark sched clock stable if
> KVM_FEATURE_CLOCKSOURCE_STABLE_BIT / PVCLOCK_TSC_STABLE_BIT is set in
> kvm guest even if there is no invariant tsc cpuid bit.

I just ripped out the interface to 'set stable' for good reasons. Also,
the branch you add it to doesn't in fact do clear_stable -- so who does?

Also, the sched/clock.c code shouldn't know about hypervisor anything.

So whatever it is you're doing, you're doing it wrong.