Received-SPF: pass (google.com: domain of linux-wireless-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
MIME-Version: 1.0
References: <CALjTZvbLOr5zAYyp75Cs6Zo8mWNUVq3ZRJu56G1iHdiihFejWQ@mail.gmail.com>
 <3483242e-c2ad-ec83-0c2c-ce952bc9b638@lwfinger.net> <CALjTZvatxQ2BvUeZGcTFijBf1PiLizJuDdENxg2b=tPQL_NAzQ@mail.gmail.com>
 <CALjTZvYSJOx0xeMVkN6dHcGTdgW9O9NVbgXPKK4d6-31VX+0JQ@mail.gmail.com>
 <29f5e3de-a32c-6292-9197-19dcc57fa6a3@lwfinger.net> <CALjTZvaroTrgK9=W8uTwq9YcYayfuEU31BUc0qNYJr+08hevfg@mail.gmail.com>
 <CALjTZvaPi2FL-epk-Vd2wOLye2O0J8G5aZPsqzHXt2b7u=HyuQ@mail.gmail.com>
 <263e247c-3bf9-6d42-996b-bc513efe4b71@lwfinger.net> <CALjTZvauK0Hh+aoabcDX9kkQZ4zN2ZjPnB+aq7YrJ9+-4ihiAg@mail.gmail.com>
 <87fffd5d-242a-7195-c4cc-80260dbd53c5@lwfinger.net> <CALjTZvYCFNSQ6HMN4owkiGTVrYaiU8R-P1KXgvkwGqcOo8uMuw@mail.gmail.com>
 <CALjTZvYMF_ERBfzkhaHvsTu6kt7MW+L_979sOVs8hcH7zF_Nyg@mail.gmail.com> <20200521124608.4b5c78f2@wiggum>
In-Reply-To: <20200521124608.4b5c78f2@wiggum>
From:   Rui Salvaterra <rsalvaterra@gmail.com>
Date:   Thu, 21 May 2020 12:30:43 +0100
Message-ID: <CALjTZvan46UTwcUxOSN=RiE6XHm-29Ln8B6wiv40V_RVxWewtA@mail.gmail.com>
Subject: Re: [BUG?] b43: can't connect to WPA3 network (nohwcrypt=1)
To:     =?UTF-8?Q?Michael_B=C3=BCsch?= <m@bues.ch>
Cc:     Larry Finger <Larry.Finger@lwfinger.net>,
        linux-wireless@vger.kernel.org, b43-dev@lists.infradead.org
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Sender: linux-wireless-owner@vger.kernel.org
Precedence: bulk

Hi, Michael,

On Thu, 21 May 2020 at 11:46, Michael B=C3=BCsch <m@bues.ch> wrote:
>
> Great. Thank you for testing.
>
> Should we consider defaulting hwcrypto to off?

IMHO, not without testing. See below. :)

> I wonder what the performance penalty is, if any, on today's CPUs
> that have some HW-crypto embedded. Of course that depends on whether we
> actually use that here.
>
> Could we have some benchmarks (throughput and CPU load wise)?

I'm preparing to do some performance tests as we speak. Nothing too
elaborate, just transferring a file over NFS and having a look at the
CPU usage, with both hardware crypto enabled/disabled (while I
initially thought of doing it over SFTP, the crypto overhead will
surely overwhelm this system). Do you suggest a more scientifically
acceptable test?
Also note that this a PowerPC laptop (iBook G4). This means it's using
the generic C crypto algorithms, there are no SIMD (VMX/AltiVec)
implementations of AES and friends on PowerPC, at least from what I've
seen in the kconfig.

Thanks,
Rui