Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20210615023812.50885-1-mcroce@linux.microsoft.com>
 <20210615023812.50885-2-mcroce@linux.microsoft.com> <6cff2a895db94e6fadd4ddffb8906a73@AcuMS.aculab.com>
 <CAEUhbmV+Vi0Ssyzq1B2RTkbjMpE21xjdj2MSKdLydgW6WuCKtA@mail.gmail.com> <1632006872b04c64be828fa0c4e4eae0@AcuMS.aculab.com>
In-Reply-To: <1632006872b04c64be828fa0c4e4eae0@AcuMS.aculab.com>
From:   Matteo Croce <mcroce@linux.microsoft.com>
Date:   Tue, 15 Jun 2021 15:44:48 +0200
Message-ID: <CAFnufp208bY29Zs9w7OtMtK0vcFOs1OosO2U6tJzm6ju-Awe4g@mail.gmail.com>
Subject: Re: [PATCH 1/3] riscv: optimized memcpy
To:     David Laight <David.Laight@aculab.com>
Cc:     Bin Meng <bmeng.cn@gmail.com>,
        "linux-riscv@lists.infradead.org" <linux-riscv@lists.infradead.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "linux-arch@vger.kernel.org" <linux-arch@vger.kernel.org>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Atish Patra <atish.patra@wdc.com>,
        Emil Renner Berthing <kernel@esmil.dk>,
        Akira Tsukamoto <akira.tsukamoto@gmail.com>,
        Drew Fustini <drew@beagleboard.org>
Content-Type: text/plain; charset="UTF-8"
Precedence: bulk

On Tue, Jun 15, 2021 at 3:18 PM David Laight <David.Laight@aculab.com> wrote:
>
> From: Bin Meng
> > Sent: 15 June 2021 14:09
> >
> > On Tue, Jun 15, 2021 at 4:57 PM David Laight <David.Laight@aculab.com> wrote:
> > >
> ...
> > > I'm surprised that the C loop:
> > >
> > > > +             for (; count >= bytes_long; count -= bytes_long)
> > > > +                     *d.ulong++ = *s.ulong++;
> > >
> > > ends up being faster than the ASM 'read lots' - 'write lots' loop.
> >
> > I believe that's because the assembly version has some unaligned
> > access cases, which end up being trap-n-emulated in the OpenSBI
> > firmware, and that is a big overhead.
>
> Ah, that would make sense since the asm user copy code
> was broken for misaligned copies.
> I suspect memcpy() was broken the same way.
>
> I'm surprised IP_NET_ALIGN isn't set to 2 to try to
> avoid all these misaligned copies in the network stack.
> Although avoiding 8n+4 aligned data is rather harder.
>

That's up to the network driver, indeed I have a patch already for the
BeagleV one:

https://lore.kernel.org/netdev/20210615012107.577ead86@linux.microsoft.com/T/

> Misaligned copies are just best avoided - really even on x86.
> The 'real fun' is when the access crosses TLB boundaries.
>

-- 
per aspera ad upstream