linux-kernel - Re: [patch 5/6] [RFD] timekeeping: Provide optional 128bit math

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20161209063847.GC15765@worktop.programming.kicks-ass.net>
Date:   Fri, 9 Dec 2016 07:38:47 +0100
From:   Peter Zijlstra <peterz@...radead.org>
To:     Thomas Gleixner <tglx@...utronix.de>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        John Stultz <john.stultz@...aro.org>,
        Ingo Molnar <mingo@...nel.org>,
        David Gibson <david@...son.dropbear.id.au>,
        Liav Rehana <liavr@...lanox.com>,
        Chris Metcalf <cmetcalf@...lanox.com>,
        Richard Cochran <richardcochran@...il.com>,
        Parit Bhargava <prarit@...hat.com>,
        Laurent Vivier <lvivier@...hat.com>,
        "Christopher S. Hall" <christopher.s.hall@...el.com>
Subject: Re: [patch 5/6] [RFD] timekeeping: Provide optional 128bit math

On Fri, Dec 09, 2016 at 06:26:38AM +0100, Peter Zijlstra wrote:
> On Thu, Dec 08, 2016 at 08:49:39PM -0000, Thomas Gleixner wrote:
> 
> > +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;
> > +}
> 
> Just for giggles, on tilegx the branch is actually slower than doing the
> mult unconditionally.
> 
> The problem is that the two multiplies would otherwise completely
> pipeline, whereas with the conditional you serialize them.

On my Haswell laptop the unconditional version is faster too.

> (came to light while talking about why the mul_u64_u32_shr() fallback
> didn't work right for them, which was a combination of the above issue
> and the fact that their compiler 'lost' the fact that these are
> 32x32->64 mults and did 64x64 ones instead).

Turns out using GCC-6.2.1 we have the same problem on i386, GCC doesn't
recognise the 32x32 mults and generates crap.

This used to work :/