Received-SPF: pass (google.com: domain of linux-crypto-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <20200806163551.14395-1-andrei.botila@oss.nxp.com>
 <20200806163551.14395-2-andrei.botila@oss.nxp.com> <20200821034651.GA25442@gondor.apana.org.au>
 <c360d691-8253-bd99-af92-83d9f8e86a2d@nxp.com> <20200908221019.GA23497@gondor.apana.org.au>
 <67159207-1082-48be-d085-971a84b525e0@nxp.com> <CAMj1kXGg7bSh57kwE57mKRocNRPZCeXifwjF53-3Jb6LYsfZTg@mail.gmail.com>
 <38f9904b-5bf7-ea99-ed8a-27cb49f405bd@nxp.com>
In-Reply-To: <38f9904b-5bf7-ea99-ed8a-27cb49f405bd@nxp.com>
From:   Ard Biesheuvel <ardb@kernel.org>
Date:   Mon, 14 Sep 2020 21:20:00 +0300
Message-ID: <CAMj1kXH0jOQms9y1MywORywoKjxQ2p8ttv+Xf9KTOkfORX5XWw@mail.gmail.com>
Subject: Re: [PATCH RESEND 1/9] crypto: caam/jr - add fallback for XTS with
 more than 8B IV
To:     =?UTF-8?Q?Horia_Geant=C4=83?= <horia.geanta@nxp.com>
Cc:     Herbert Xu <herbert@gondor.apana.org.au>,
        "Andrei Botila (OSS)" <andrei.botila@oss.nxp.com>,
        Aymen Sghaier <aymen.sghaier@nxp.com>,
        "David S. Miller" <davem@davemloft.net>,
        "linux-crypto@vger.kernel.org" <linux-crypto@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-crypto-owner@vger.kernel.org
Precedence: bulk

On Mon, 14 Sep 2020 at 20:12, Horia Geant=C4=83 <horia.geanta@nxp.com> wrot=
e:
>
> On 9/14/2020 7:28 PM, Ard Biesheuvel wrote:
> > On Mon, 14 Sep 2020 at 19:24, Horia Geant=C4=83 <horia.geanta@nxp.com> =
wrote:
> >>
> >> On 9/9/2020 1:10 AM, Herbert Xu wrote:
> >>> On Tue, Sep 08, 2020 at 01:35:04PM +0300, Horia Geant=C4=83 wrote:
> >>>>
> >>>>> Just go with the get_unaligned unconditionally.
> >>>>
> >>>> Won't this lead to sub-optimal code for ARMv7
> >>>> in case the IV is aligned?
> >>>
> >>> If this should be optimised in ARMv7 then that should be done
> >>> in get_unaligned itself and not open-coded.
> >>>
> >> I am not sure what's wrong with avoiding using the unaligned accessors
> >> in case data is aligned.
> >>
> >> Documentation/core-api/unaligned-memory-access.rst clearly states:
> >> These macros work for memory accesses of any length (not just 32 bits =
as
> >> in the examples above). Be aware that when compared to standard access=
 of
> >> aligned memory, using these macros to access unaligned memory can be c=
ostly in
> >> terms of performance.
> >>
> >> So IMO it makes sense to use get_unaligned() only when needed.
> >> There are several cases of users doing this, e.g. siphash.
> >>
> >
> > For ARMv7 code, using the unaligned accessors unconditionally is fine,
> > and it will not affect performance.
> >
> > In general, when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS is defined,
> > you can use the unaligned accessors. If it is not, it helps to have
> > different code paths.
> >
> arch/arm/include/asm/unaligned.h doesn't make use of
> linux/unaligned/access_ok.h, even if CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCE=
SS
> is set.
>
> I understand the comment in the file, however using get_unaligned()
> unconditionally takes away the opportunity to generate optimized code
> (using ldrd/ldm) when data is aligned.
>

But the minimal optimization that is possible here (one ldrd/ldm
instruction vs two ldr instructions) is defeated by the fact that you
are using a conditional branch to select between the two. And this is
not even a hot path to begin with,

> > This is a bit murky, and through the years, the interpretation of
> > unaligned-memory-access.rst has shifted a bit, but in this case, it
> > makes no sense to make the distinction.
> >
>
> Thanks,
> Horia