Skip site navigation (1)Skip section navigation (2)
Date:      Thu, 31 Dec 2020 15:07:02 -0500
From:      Shawn Webb <shawn.webb@hardenedbsd.org>
To:        Allan Jude <allanjude@freebsd.org>
Cc:        FreeBSD Current <freebsd-current@freebsd.org>
Subject:   Re: Enabling AESNI by default
Message-ID:  <20201231200702.22gvepvlzfwncalz@mutt-hbsd>
In-Reply-To: <5d56280e-a8dd-b28d-7039-f8fe0bc0cd6f@freebsd.org>
References:  <5d56280e-a8dd-b28d-7039-f8fe0bc0cd6f@freebsd.org>

next in thread | previous in thread | raw e-mail | index | archive | help

--ji2eli3lbepfjcm2
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
Content-Transfer-Encoding: quoted-printable

On Thu, Dec 31, 2020 at 02:51:06PM -0500, Allan Jude wrote:
> We've had the AESNI module for quite a few years now, and it has not
> caused any problems.
>=20
> I am wondering if there are any objections to including it in GENERIC,
> so that users get the benefit without having to have the "tribal
> knowledge" that 'to accelerate kernel crypto (GELI, ZFS, IPSEC, etc),
> you need to load aesni.ko'
>=20
> Userspace crypto that uses openssl or similar libraries is already
> taking advantage of these CPU instructions if they are available, by
> excluding this feature from GENERIC we are just causing the "out of the
> box" experience to by very very slow for crypto.
>=20
> For example, writing 1MB blocks to a GELI encrypted swap-backed md(4)
> device:
>=20
> with 8 jobs on a 10 core Intel Xeon CPU E5-2630 v4 @ 2.20GHz
>=20
> fio --filename=3D/dev/md0.eli --device=3D1 --name=3Dgeli --rw=3Dwrite --b=
s=3D1m
> --numjobs=3D8 --iodepth=3D16 --end_fsync=3D1 --ioengine=3Dpvsync
> --group_reporting --fallocate=3Dnone --runtime=3D60 --time_based
>=20
>=20
> stock:
> write: IOPS=3D530, BW=3D530MiB/s (556MB/s) (31.1GiB/60012msec)
>=20
> with aesni.ko loaded:
> write: IOPS=3D2824, BW=3D2825MiB/s (2962MB/s) (166GiB/60002msec)
>=20
>=20
> Does anyone have a compelling reason to deny our users the 5x speedup?

Note: HardenedBSD has had AESNI enabled on amd64 for nearly six years.
Not a single complaint.

For reference, HardenedBSD commit:
a5aabd1c8dcc2a5097de56c54ec2a1c8d9352896

Thanks,

--=20
Shawn Webb
Cofounder / Security Engineer
HardenedBSD

GPG Key ID:          0xFF2E67A277F8E1FA
GPG Key Fingerprint: D206 BB45 15E0 9C49 0CF9  3633 C85B 0AF8 AB23 0FB2
https://git-01.md.hardenedbsd.org/HardenedBSD/pubkeys/src/branch/master/Sha=
wn_Webb/03A4CBEBB82EA5A67D9F3853FF2E67A277F8E1FA.pub.asc

--ji2eli3lbepfjcm2
Content-Type: application/pgp-signature; name="signature.asc"

-----BEGIN PGP SIGNATURE-----
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=1VhA
-----END PGP SIGNATURE-----

--ji2eli3lbepfjcm2--



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20201231200702.22gvepvlzfwncalz>