All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andy Lutomirski <luto@amacapital.net>
To: Eric Dumazet <eric.dumazet@gmail.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>,
	David Miller <davem@davemloft.net>,
	Network Development <netdev@vger.kernel.org>
Subject: Re: [PATCH v2 net-next] tcp: md5: use kmalloc() backed scratch areas
Date: Wed, 29 Jun 2016 15:39:37 -0700	[thread overview]
Message-ID: <CALCETrWUOuwaUrwkU9ywcqTK6aqQn6yNESmR3fgz6VMhwAnQdg@mail.gmail.com> (raw)
In-Reply-To: <1467236646.6369.5.camel@edumazet-glaptop3.roam.corp.google.com>

On Wed, Jun 29, 2016 at 2:44 PM, Eric Dumazet <eric.dumazet@gmail.com> wrote:
> On Wed, 2016-06-29 at 09:41 -0700, Andy Lutomirski wrote:
>
>> Overall, it looks like there's overhead of something like 50ns for
>> each ahash invocation vs the shash equivalent.  It's not huge, but
>> it's there.  (This is cache-hot.  I bet it's considerably worse if
>> cache-cold, because ahash will require a lot more code cache lines as
>> well as the extra cache lines involved in the scatterlist and whatever
>> arch stuff is needed to map back and forth between virtual and
>> physical addresses.
>
> I am kind of mystified seeing someone caring about TCP MD5, other than
> just making sure it wont crash the host when it needs to be used ;)
>
> The real useful work would be to use a jump label so that we can avoid
> spending cycles for non TCP MD5 sessions, when a host never had to use
> any MD5 negotiation.
>
>
>

I don't care about TCP MD5 performance at all.  Ease of maintenance is
nice, though, and maybe there are other places in the kernel where
performance does matter.

--Andy

  reply	other threads:[~2016-06-29 22:40 UTC|newest]

Thread overview: 26+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2016-06-25  1:51 tcp md5: one more crypto-sg-on-the-stack instance Andy Lutomirski
2016-06-25  4:11 ` Eric Dumazet
2016-06-25  4:26   ` Eric Dumazet
2016-06-25  4:37     ` Eric Dumazet
2016-06-25 16:09       ` [PATCH net-next] tcp: md5: do not use stack storage in crypto operations Eric Dumazet
2016-06-25 19:35         ` Andy Lutomirski
2016-06-27 14:51         ` David Miller
2016-06-27 15:02           ` Andy Lutomirski
2016-06-27 15:22           ` Eric Dumazet
2016-06-27 16:51         ` [PATCH v2 net-next] tcp: md5: use kmalloc() backed scratch areas Eric Dumazet
2016-06-27 17:58           ` Andy Lutomirski
2016-06-27 21:22             ` Eric Dumazet
2016-06-28  3:41             ` Herbert Xu
2016-06-28 17:35               ` Andy Lutomirski
2016-06-29  2:23                 ` Herbert Xu
2016-06-29 14:59                   ` Andy Lutomirski
2016-06-29 15:02                     ` Herbert Xu
2016-06-29 15:26                       ` Andy Lutomirski
2016-06-29 15:38                         ` Herbert Xu
2016-06-29 16:41                           ` Andy Lutomirski
2016-06-29 21:44                             ` Eric Dumazet
2016-06-29 22:39                               ` Andy Lutomirski [this message]
2016-06-30  3:45                                 ` Herbert Xu
2016-06-27 18:31           ` Cong Wang
2016-06-27 21:25             ` Eric Dumazet
2016-07-01  8:03           ` David Miller

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=CALCETrWUOuwaUrwkU9ywcqTK6aqQn6yNESmR3fgz6VMhwAnQdg@mail.gmail.com \
    --to=luto@amacapital.net \
    --cc=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=herbert@gondor.apana.org.au \
    --cc=netdev@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.