netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: David Miller <davem@davemloft.net>
To: eric.dumazet@gmail.com
Cc: hagen@jauu.net, netdev@vger.kernel.org, xiaosuo@gmail.com
Subject: Re: [PATCH net-next-2.6] filter: optimize sk_run_filter
Date: Fri, 19 Nov 2010 08:21:25 -0800 (PST)	[thread overview]
Message-ID: <20101119.082125.193710226.davem@davemloft.net> (raw)
In-Reply-To: <1290165472.3034.109.camel@edumazet-laptop>

From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Fri, 19 Nov 2010 12:17:52 +0100

> Le vendredi 19 novembre 2010 à 10:54 +0100, Eric Dumazet a écrit :
> 
>> I believe we should revert the u32 f_k = fentry->k; part
>> 
>> fentry->k as is fast as f_k if stored on stack, and avoids one
>> instruction if fentry->k is not needed.
>> 
>> 
> 
> A revert is not good on arches with decent number of registers (x86_64
> for example).

-EFIX_THE_DAMN_COMPILER

We never make calls out of this function or touch volatile memory or
create a full memory barrier between the assignment of f_k and it's
uses.

Therefore if common sub-expression elimination is working the compiler
will be able to decide properly whether to access things via memory or
use a register for the value.

Remember this is why we have that ACCESS_ONCE() thing.

We can't have it both ways, either ACCESS_ONCE() should be removed or
we should never make changes like your's and instead should submit
compiler bug reports :-)

  parent reply	other threads:[~2010-11-19 16:21 UTC|newest]

Thread overview: 27+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-19  2:04 [PATCH] net: reduce the lines of code Changli Gao
2010-11-19  6:35 ` Hagen Paul Pfeifer
2010-11-19  7:17   ` Changli Gao
2010-11-19  7:51     ` Eric Dumazet
2010-11-19  7:56       ` [PATCH net-next-2.6] filter: cleanup codes[] init Eric Dumazet
2010-11-19  8:04         ` [PATCH net-next-2.6] filter: use reciprocal divide Eric Dumazet
2010-11-19  8:18           ` Changli Gao
2010-11-19 18:07             ` David Miller
2010-11-19  8:38         ` [PATCH net-next-2.6] filter: cleanup codes[] init Changli Gao
2010-11-19  9:54           ` Eric Dumazet
2010-11-19 11:17             ` [PATCH net-next-2.6] filter: optimize sk_run_filter Eric Dumazet
2010-11-19 12:32               ` Changli Gao
2010-11-19 12:57                 ` Changli Gao
2010-11-19 13:16                   ` [PATCH net-next-2.6 v2] " Eric Dumazet
2010-11-19 14:13                     ` Changli Gao
2010-11-19 17:52                       ` David Miller
2010-11-19 14:17                     ` Tetsuo Handa
2010-11-19 14:35                       ` Eric Dumazet
2010-11-19 16:21               ` David Miller [this message]
2010-11-19 16:55                 ` [PATCH net-next-2.6] " Eric Dumazet
2010-11-19 17:05                   ` David Miller
2010-11-19 17:15                     ` Stephen Hemminger
2010-11-19 17:21                       ` David Miller
2010-11-19 17:16                     ` Eric Dumazet
2010-11-19 17:25                       ` David Miller
2010-11-19 12:21             ` [PATCH net-next-2.6] filter: cleanup codes[] init Changli Gao
2010-11-19 18:07               ` 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=20101119.082125.193710226.davem@davemloft.net \
    --to=davem@davemloft.net \
    --cc=eric.dumazet@gmail.com \
    --cc=hagen@jauu.net \
    --cc=netdev@vger.kernel.org \
    --cc=xiaosuo@gmail.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).