From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <linux-fsdevel-owner@vger.kernel.org>
Received: from Galois.linutronix.de ([146.0.238.70]:45127 "EHLO
        Galois.linutronix.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1753589AbdKPJxo (ORCPT
        <rfc822;linux-fsdevel@vger.kernel.org>);
        Thu, 16 Nov 2017 04:53:44 -0500
Date: Thu, 16 Nov 2017 10:53:41 +0100 (CET)
From: Thomas Gleixner <tglx@linutronix.de>
To: Quan Xu <quan.xu0@gmail.com>
cc: Peter Zijlstra <peterz@infradead.org>,
        Quan Xu <quan.xu03@gmail.com>, kvm@vger.kernel.org,
        linux-doc@vger.kernel.org, linux-fsdevel@vger.kernel.org,
        LKML <linux-kernel@vger.kernel.org>,
        virtualization@lists.linux-foundation.org, x86@kernel.org,
        xen-devel@lists.xenproject.org,
        Yang Zhang <yang.zhang.wz@gmail.com>,
        Ingo Molnar <mingo@redhat.com>,
        "H. Peter Anvin" <hpa@zytor.com>, Borislav Petkov <bp@alien8.de>,
        Kyle Huey <me@kylehuey.com>, Len Brown <len.brown@intel.com>,
        Andy Lutomirski <luto@kernel.org>,
        Tom Lendacky <thomas.lendacky@amd.com>,
        Tobias Klauser <tklauser@distanz.ch>,
        Daniel Lezcano <daniel.lezcano@linaro.org>
Subject: Re: [PATCH RFC v3 3/6] sched/idle: Add a generic poll before enter
 real idle path
In-Reply-To: <46086489-5a01-16e1-9314-70ae53c01952@gmail.com>
Message-ID: <alpine.DEB.2.20.1711161048000.2191@nanos>
References: <1510567565-5118-1-git-send-email-quan.xu0@gmail.com> <1510567565-5118-4-git-send-email-quan.xu0@gmail.com> <20171115121152.gqug5wzerlo3eimd@hirez.programming.kicks-ass.net> <alpine.DEB.2.20.1711152240010.2146@nanos>
 <46086489-5a01-16e1-9314-70ae53c01952@gmail.com>
MIME-Version: 1.0
Content-Type: multipart/mixed; BOUNDARY="8323329-2002752408-1510826021=:2191"
Sender: linux-fsdevel-owner@vger.kernel.org
List-ID: <linux-fsdevel.vger.kernel.org>

  This message is in MIME format.  The first part should be readable text,
  while the remaining parts are likely unreadable without MIME-aware tools.

--8323329-2002752408-1510826021=:2191
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 8BIT

On Thu, 16 Nov 2017, Quan Xu wrote:
> On 2017-11-16 06:03, Thomas Gleixner wrote:
> --- a/drivers/cpuidle/cpuidle.c
> +++ b/drivers/cpuidle/cpuidle.c
> @@ -210,6 +210,13 @@ int cpuidle_enter_state(struct cpuidle_device *dev,
> struct cpuidle_driver *drv,
>                 target_state = &drv->states[index];
>         }
> 
> +#ifdef CONFIG_PARAVIRT
> +       paravirt_idle_poll();
> +
> +       if (need_resched())
> +               return -EBUSY;
> +#endif

That's just plain wrong. We don't want to see any of this PARAVIRT crap in
anything outside the architecture/hypervisor interfacing code which really
needs it.

The problem can and must be solved at the generic level in the first place
to gather the data which can be used to make such decisions.

How that information is used might be either completely generic or requires
system specific variants. But as long as we don't have any information at
all we cannot discuss that.

Please sit down and write up which data needs to be considered to make
decisions about probabilistic polling. Then we need to compare and contrast
that with the data which is necessary to make power/idle state decisions.

I would be very surprised if this data would not overlap by at least 90%.

Thanks,

	tglx
--8323329-2002752408-1510826021=:2191--