MIME-Version: 1.0
References: <20211101044955.2295495-1-goldstein.w.n@gmail.com>
 <20211117210245.843374-1-goldstein.w.n@gmail.com> <bc0297a1b97a4b129fa3ea1b155f6062@AcuMS.aculab.com>
In-Reply-To: <bc0297a1b97a4b129fa3ea1b155f6062@AcuMS.aculab.com>
From:   Noah Goldstein <goldstein.w.n@gmail.com>
Date:   Wed, 17 Nov 2021 16:45:13 -0600
Message-ID: <CAFUsyfJTuFjVXHMgYi0uggVNW=1WW1uVYa7avVjW5VBb2cmAkQ@mail.gmail.com>
Subject: Re: [PATCH v4] arch/x86: Improve 'rep movs{b|q}' usage in memmove_64.S
To:     David Laight <David.Laight@aculab.com>
Cc:     "tglx@linutronix.de" <tglx@linutronix.de>,
        "mingo@redhat.com" <mingo@redhat.com>,
        "bp@alien8.de" <bp@alien8.de>, "x86@kernel.org" <x86@kernel.org>,
        "hpa@zytor.com" <hpa@zytor.com>,
        "luto@kernel.org" <luto@kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Wed, Nov 17, 2021 at 4:31 PM David Laight <David.Laight@aculab.com> wrote:
>
> From: Noah Goldstein
> > Sent: 17 November 2021 21:03
> >
> > Add check for "short distance movsb" for forwards FSRM usage and
> > entirely remove backwards 'rep movsq'. Both of these usages hit "slow
> > modes" that are an order of magnitude slower than usual.
> >
> > 'rep movsb' has some noticeable VERY slow modes that the current
> > implementation is either 1) not checking for or 2) intentionally
> > using.
>
> How does this relate to the decision that glibc made a few years
> ago to use backwards 'rep movs' for non-overlapping copies?

GLIBC doesn't use backwards `rep movs`.  Since the regions are
non-overlapping it just uses forward copy. Backwards `rep movs` is
from setting the direction flag (`std`) and is a very slow byte
copy. For overlapping regions where backwards copy is necessary GLIBC
uses 4x vec copy loop.

>
>
> Did they find a different corner case??
>
>         David
>
> -
> Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK
> Registration No: 1397386 (Wales)
>