Development discussion of WireGuard
 help / color / mirror / Atom feed
From: "Jason A. Donenfeld" <Jason@zx2c4.com>
To: Mathias Krause <minipli@grsecurity.net>
Cc: WireGuard mailing list <wireguard@lists.zx2c4.com>,
	Aymeric Fromherz <aymeric.fromherz@inria.fr>,
	 Karthik Bhargavan <karthikeyan.bhargavan@inria.fr>
Subject: Re: [PATCH 0/2] wireguard-linux-compat: grsecurity compat patches
Date: Mon, 13 Dec 2021 17:53:26 +0100	[thread overview]
Message-ID: <CAHmME9qhcdAZSzcWQ3fSFix+_66jKkdvPvs-JeCQevJYde_HXA@mail.gmail.com> (raw)
In-Reply-To: <d52c29d2-3530-e2e9-7096-77da1eb21078@grsecurity.net>

On Mon, Dec 13, 2021 at 5:39 PM Mathias Krause <minipli@grsecurity.net> wrote:
>
> Am 13.12.21 um 17:33 schrieb Jason A. Donenfeld:
> >> root@box:~# ./run.sh
> >> [+] Setting no-turbo to status 1
> >> [+] Setting non-boot CPUs to status 0
> >> [+] Inserting module to run tests
> >> insmod: ERROR: could not insert module kbench9000.ko: Unknown symbol in
> >> module
> >> [+] Gathering results
> >>                  ever64: 115100 cycles per call
> >>            ever64_out_r: 115080 cycles per call
> >>           ever64_out_rm: 113957 cycles per call
> >> [+] Setting non-boot CPUs to status 1
> >> [+] Setting no-turbo to status 0
> >>
> >> Slightly faster.
> >
> > Huh, that's actually a pretty nice speedup for just changing register
> > allocation... What CPU is this?
>
> It's an "Intel(R) Core(TM) i9-9900 CPU @ 3.10GHz" But shouldn't matter
> all that much, as the inline ASM is integer ops only.

Yet it does. Here are results on a tigerlake, i7-11850H:

[+] Setting no-turbo to status 1
[+] Setting non-boot CPUs to status 0
[+] Inserting module to run tests
[+] Gathering results
    donna64: 141081 cycles per call
     hacl64: 135645 cycles per call
     fiat64: 132547 cycles per call
    sandy2x: 126933 cycles per call
precomp_bmi2: 120276 cycles per call
precomp_adx: 113578 cycles per call
     ever64: 106943 cycles per call
    ever64r: 105924 cycles per call
   ever64rm: 108139 cycles per call
     fiat32: 297854 cycles per call
    donna32: 467667 cycles per call
  tweetnacl: 1195385 cycles per call
[+] Setting non-boot CPUs to status 1
[+] Setting no-turbo to status 0

https://xn--4db.cc/c4B65RUy/diff

Looks like Tigerlake is able to make use of free stack accesses thanks
to the new "fast forwarding" feature.

      reply	other threads:[~2021-12-13 16:55 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-07-06 13:27 Mathias Krause
2021-07-06 13:27 ` [PATCH 1/2] compat: better grsecurity compatibility Mathias Krause
2021-07-06 13:27 ` [PATCH 2/2] curve25519-x86_64: solve register constraints with reserved registers Mathias Krause
2021-08-08 20:53 ` [PATCH 0/2] wireguard-linux-compat: grsecurity compat patches Jason A. Donenfeld
2021-08-09 10:13   ` Mathias Krause
2021-12-03 22:20     ` Jason A. Donenfeld
2021-12-03 22:25       ` Jason A. Donenfeld
2021-12-06 14:04       ` Mathias Krause
2021-12-06 14:48         ` Jason A. Donenfeld
2021-12-06 16:24           ` Mathias Krause
2021-12-06 16:27             ` Jason A. Donenfeld
2021-12-06 18:18               ` Mathias Krause
2021-12-06 18:55                 ` Jason A. Donenfeld
2021-12-06 19:28                   ` Jason A. Donenfeld
2021-12-06 20:54                     ` Mathias Krause
2021-12-08 14:56                       ` Jason A. Donenfeld
2021-12-06 21:00                   ` Mathias Krause
2021-12-08 14:56                     ` Jason A. Donenfeld
2021-12-09  7:59                       ` Mathias Krause
2021-12-10 22:36                         ` Jason A. Donenfeld
2021-12-10 22:58                         ` Jason A. Donenfeld
2021-12-11 16:35                           ` Aymeric Fromherz
2021-12-12 21:43                             ` Jason A. Donenfeld
2021-12-13  7:54                               ` Mathias Krause
2021-12-13 11:36                                 ` Jason A. Donenfeld
2021-12-13 16:29                                   ` Jason A. Donenfeld
2021-12-13 16:46                                     ` Mathias Krause
2021-12-13  7:44                             ` Mathias Krause
2021-12-13 14:20                               ` Aymeric Fromherz
2021-12-13 14:33                                 ` Mathias Krause
2021-12-13 14:37                                   ` Jason A. Donenfeld
2021-12-13 16:32                                     ` Mathias Krause
2021-12-13 16:33                                       ` Jason A. Donenfeld
2021-12-13 16:39                                         ` Mathias Krause
2021-12-13 16:53                                           ` Jason A. Donenfeld [this message]

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=CAHmME9qhcdAZSzcWQ3fSFix+_66jKkdvPvs-JeCQevJYde_HXA@mail.gmail.com \
    --to=jason@zx2c4.com \
    --cc=aymeric.fromherz@inria.fr \
    --cc=karthikeyan.bhargavan@inria.fr \
    --cc=minipli@grsecurity.net \
    --cc=wireguard@lists.zx2c4.com \
    /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).