Date: Mon, 18 Apr 2016 15:24:34 +0800
From: Herbert Xu <herbert@gondor.apana.org.au>
To: Baolin Wang <baolin.wang@linaro.org>
Cc: David Miller <davem@davemloft.net>, Alasdair G Kergon <agk@redhat.com>,
        Mike Snitzer <snitzer@redhat.com>, Jens Axboe <axboe@fb.com>,
        dm-devel@redhat.com, Andrew Morton <akpm@linux-foundation.org>,
        david.s.gordon@intel.com, Tom Lendacky <thomas.lendacky@amd.com>,
        Robert Jarzmik <robert.jarzmik@free.fr>,
        Masahiro Yamada <yamada.masahiro@socionext.com>, smueller@chronox.de,
        tadeusz.struk@intel.com, Masanari Iida <standby24x7@gmail.com>,
        shli@kernel.org, Mark Brown <broonie@kernel.org>,
        Linus Walleij <linus.walleij@linaro.org>,
        Arnd Bergmann <arnd@arndb.de>, LKML <linux-kernel@vger.kernel.org>,
        linux-crypto@vger.kernel.org, linux-raid@vger.kernel.org
Subject: Re: [PATCH v2 0/4] Introduce bulk mode for crypto engine framework
Message-ID: <20160418072434.GA17954@gondor.apana.org.au>
References: <cover.1458023695.git.baolin.wang@linaro.org>
 <20160415134849.GA32694@gondor.apana.org.au>
 <CAMz4ku+hXbgx1+YcdJWbCBW7KoeFisk5qcquAAg0fD5Qw5XDFQ@mail.gmail.com>
 <20160418054511.GA17368@gondor.apana.org.au>
 <CAMz4ku+e=53jYJs0y03_catfWzE495sgiiQY_KsLy+v7YOdu+w@mail.gmail.com>
 <20160418070407.GA17760@gondor.apana.org.au>
 <CAMz4kuJvnbRBSiuStYeGkgOXFPVmPJmChd2Gz1aHP40Uh1VxbQ@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAMz4kuJvnbRBSiuStYeGkgOXFPVmPJmChd2Gz1aHP40Uh1VxbQ@mail.gmail.com>
User-Agent: Mutt/1.5.21 (2010-09-15)
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 819
Lines: 20

On Mon, Apr 18, 2016 at 03:21:16PM +0800, Baolin Wang wrote:
>
> I don't think so, the dm-crypt can not send maximal requests at some
> situations. For example, the 'cbc(aes)' cipher, it must be handled
> sector by sector (IV is dependency for each sector), so the dm-crypt
> can not send maximal requests, but must sector by sector in this
> situation.

If you can't merge them as requests, then how is the hardware going
to benefit from batching them? Or are you talking about parallel
processing similar to sha-mb?

Even with batching we should be involving the user because only the
user knows (if anyone does) whether more data will be forthcoming.

Cheers,
-- 
Email: Herbert Xu <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt