From: Ard Biesheuvel <ardb@kernel.org>
To: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Linux Crypto Mailing List <linux-crypto@vger.kernel.org>,
Ben Greear <greearb@candelatech.com>,
Steve deRosier <derosier@cal-sierra.com>
Subject: Re: [PATCH v2] crypto: aesni - add ccm(aes) algorithm implementation
Date: Tue, 1 Dec 2020 23:12:32 +0100 [thread overview]
Message-ID: <CAMj1kXGO+kbZ+2VmUQKxLYos2nR5vqZKjengxPxPjSXudG-zLw@mail.gmail.com> (raw)
In-Reply-To: <20201201220431.GA32072@gondor.apana.org.au>
On Tue, 1 Dec 2020 at 23:04, Herbert Xu <herbert@gondor.apana.org.au> wrote:
>
> On Tue, Dec 01, 2020 at 11:01:57PM +0100, Ard Biesheuvel wrote:
> >
> > This is not the first time this has come up. The point is that CCMP in
> > the wireless stack is not used in 99% of the cases, given that any
> > wifi hardware built in the last ~10 years can do it in hardware. Only
> > in exceptional cases, such as Ben's, is there a need for exercising
> > this interface.
>
> Either it matters or it doesn't. If it doesn't matter why are we
> having this dicussion at all? If it does then fixing just one
> direction makes no sense.
>
What do you mean by just one direction? Ben just confirmed a
substantial speedup for his use case, which requires the use of
software encryption even on hardware that could support doing it in
hardware, and that software encryption currently only supports the
synchronous interface.
Even if it is nicer in theory, I don't see the point of implementing
support for the asynchronous interface, given that nobody is going to
wire up a AES accelerator to a wifi controller.
> > Also, care to explain why we have synchronous AEADs in the first place
> > if they are not supposed to be used?
>
> Sync AEADs would make sense if you were dealing with a very small
> amount of data, e.g., one block.
>
Why? The processing occurs in *exactly* the same way, given that the
wifi stack never calls into the AEAD from a context where the FPU is
unavailable. So we basically have to choose between a non-SIMD
fallback path that never gets exercised, or a SIMD async helper that
always relays the request directly, and never queues it for
asynchronous completion.
IOW, we are arguing a theoretical difference here, and the code paths
that actually get exercised are 100% the same.
next prev parent reply other threads:[~2020-12-01 22:13 UTC|newest]
Thread overview: 40+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-01 19:45 [PATCH v2] crypto: aesni - add ccm(aes) algorithm implementation Ard Biesheuvel
2020-12-01 21:40 ` Ben Greear
2020-12-01 21:57 ` Herbert Xu
2020-12-01 22:00 ` Ben Greear
2020-12-01 22:01 ` Herbert Xu
2020-12-01 22:01 ` Ard Biesheuvel
2020-12-01 22:04 ` Herbert Xu
2020-12-01 22:12 ` Ard Biesheuvel [this message]
2020-12-01 22:16 ` Herbert Xu
2020-12-01 22:27 ` Ard Biesheuvel
2020-12-01 23:11 ` Herbert Xu
2020-12-01 23:24 ` Ard Biesheuvel
2020-12-01 23:30 ` Herbert Xu
2020-12-01 23:41 ` Ard Biesheuvel
2020-12-01 23:48 ` Herbert Xu
2020-12-02 0:01 ` Ben Greear
2020-12-10 0:18 ` Ard Biesheuvel
2020-12-10 2:43 ` Herbert Xu
2020-12-10 3:01 ` Ben Greear
2020-12-10 7:30 ` Ard Biesheuvel
2020-12-10 11:14 ` Herbert Xu
2020-12-10 12:03 ` Ard Biesheuvel
2020-12-10 12:16 ` Herbert Xu
2020-12-10 12:19 ` Ard Biesheuvel
2020-12-15 8:55 ` Ard Biesheuvel
2020-12-15 9:19 ` Herbert Xu
2022-11-08 18:50 ` Ben Greear
2022-11-09 3:52 ` Herbert Xu
2022-11-09 10:05 ` Ard Biesheuvel
2022-11-09 14:12 ` Ben Greear
2022-11-11 22:29 ` Ben Greear
2022-11-12 14:59 ` Ard Biesheuvel
2023-10-16 20:50 ` Ben Greear
2023-10-17 3:16 ` Eric Biggers
2023-10-17 6:43 ` Ard Biesheuvel
2023-10-18 1:24 ` Herbert Xu
2024-08-03 17:20 ` Ben Greear
2024-08-28 16:04 ` Ard Biesheuvel
2020-12-10 14:40 ` Ben Greear
2020-12-01 22:12 ` Ben Greear
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CAMj1kXGO+kbZ+2VmUQKxLYos2nR5vqZKjengxPxPjSXudG-zLw@mail.gmail.com \
--to=ardb@kernel.org \
--cc=derosier@cal-sierra.com \
--cc=greearb@candelatech.com \
--cc=herbert@gondor.apana.org.au \
--cc=linux-crypto@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).