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 S932789AbcLIFL2 (ORCPT <rfc822;w@1wt.eu>);
        Fri, 9 Dec 2016 00:11:28 -0500
Received: from bombadil.infradead.org ([198.137.202.9]:42031 "EHLO
        bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1752637AbcLIFL1 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Fri, 9 Dec 2016 00:11:27 -0500
Date: Fri, 9 Dec 2016 06:11:17 +0100
From: Peter Zijlstra <peterz@infradead.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: LKML <linux-kernel@vger.kernel.org>,
        John Stultz <john.stultz@linaro.org>, Ingo Molnar <mingo@kernel.org>,
        David Gibson <david@gibson.dropbear.id.au>,
        Liav Rehana <liavr@mellanox.com>,
        Chris Metcalf <cmetcalf@mellanox.com>,
        Richard Cochran <richardcochran@gmail.com>,
        Parit Bhargava <prarit@redhat.com>,
        Laurent Vivier <lvivier@redhat.com>,
        "Christopher S. Hall" <christopher.s.hall@intel.com>
Subject: Re: [patch 5/6] [RFD] timekeeping: Provide optional 128bit math
Message-ID: <20161209051117.GZ3045@worktop.programming.kicks-ass.net>
References: <20161208202623.883855034@linutronix.de>
 <20161208204229.005418487@linutronix.de>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20161208204229.005418487@linutronix.de>
User-Agent: Mutt/1.5.22.1 (2013-10-16)
Sender: linux-kernel-owner@vger.kernel.org
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

On Thu, Dec 08, 2016 at 08:49:39PM -0000, Thomas Gleixner wrote:

> +/*
> + * Enabled when timekeeping is supposed to deal with virtualization keeping
> + * VMs long enough scheduled out that the 64 * 32 bit multiplication in
> + * timekeeping_delta_to_ns() overflows 64bit.
> + */
> +#ifdef CONFIG_TIMEKEEPING_USE_128BIT_MATH
> +
> +#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
> +static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
> +{
> +	unsigned __int128 nsec;
> +
> +	nsec = ((unsigned __int128)delta * tkr->mult) + tkr->xtime_nsec;
> +	return (u64) (nsec >> tkr->shift);
> +}
> +#else
> +static inline u64 timekeeping_delta_to_ns(struct tk_read_base *tkr, u64 delta)
> +{
> +	u32 dh, dl;
> +	u64 nsec;
> +
> +	dl = delta;
> +	dh = delta >> 32;
> +
> +	nsec = ((u64)dl * tkr->mult) + tkr->xtime_nsec;
> +	nsec >>= tkr->shift;
> +	if (unlikely(dh))
> +		nsec += ((u64)dh * tkr->mult) << (32 - tkr->shift);
> +	return nsec;
> +}
> +#endif
> +
> +#else /* CONFIG_TIMEKEEPING_USE_128BIT_MATH */

xtime_nsec confuses me, contrary to its name, its not actually in nsec,
its in shifted nsec units for some reason (and that might well be a good
reason, but I don't know).

In any case, it needing to be inside the shift is somewhat unfortunate
in that it doesn't allow you to use the existing mul_u64_u32_shr()