netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jarek Poplawski <jarkao2@o2.pl>
To: Radu Rendec <radu.rendec@ines.ro>
Cc: netdev@vger.kernel.org, hadi@cyberus.ca, davem@davemloft.net
Subject: Re: [PATCH] [PKT_SCHED] CLS_U32: Use ffs() instead of C code on hash mask to get first set bit.
Date: Thu, 8 Nov 2007 12:37:52 +0100	[thread overview]
Message-ID: <20071108113752.GA1602@ff.dom.local> (raw)
In-Reply-To: <1194520067-20868-1-git-send-email-radu.rendec@ines.ro>

On Thu, Nov 08, 2007 at 01:07:47PM +0200, Radu Rendec wrote:
> Computing the rank of the first set bit in the hash mask (for using later
> in u32_hash_fold()) was done with plain C code. Using ffs() instead makes
> the code more readable and improves performance (since ffs() is better
> optimized in assembler).
> 
> Using the conditional operator on hash mask before applying ntohl() also
> saves one ntohl() call if mask is 0.
> 
> Signed-off-by: Radu Rendec <radu.rendec@ines.ro>

Signed-off-by: Jarek Poplawski <jarkao2@o2.pl>

> ---
>  net/sched/cls_u32.c |   12 +-----------
>  1 files changed, 1 insertions(+), 11 deletions(-)
> 
> diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
> index 5317102..c390082 100644
> --- a/net/sched/cls_u32.c
> +++ b/net/sched/cls_u32.c
> @@ -613,17 +613,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle,
>  	memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
>  	n->ht_up = ht;
>  	n->handle = handle;
> -{
> -	u8 i = 0;
> -	u32 mask = ntohl(s->hmask);
> -	if (mask) {
> -		while (!(mask & 1)) {
> -			i++;
> -			mask>>=1;
> -		}
> -	}
> -	n->fshift = i;
> -}
> +	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
>  
>  #ifdef CONFIG_CLS_U32_MARK
>  	if (tb[TCA_U32_MARK-1]) {
> -- 
> 1.5.3.2
> 

  reply	other threads:[~2007-11-08 11:34 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-01 17:55 Endianness problem with u32 classifier hash masks Radu Rendec
2007-11-02 17:31 ` Jarek Poplawski
2007-11-02 23:23   ` jamal
2007-11-03 23:39     ` Jarek Poplawski
2007-11-03 23:58       ` Jarek Poplawski
2007-11-04  0:30         ` Jarek Poplawski
2007-11-04  1:17           ` Jarek Poplawski
2007-11-04 23:58             ` jamal
2007-11-05  9:12               ` Jarek Poplawski
2007-11-05 12:59                 ` Radu Rendec
2007-11-05 13:43                   ` jamal
2007-11-05 14:49                     ` Jarek Poplawski
2007-11-05 16:12                       ` Radu Rendec
2007-11-05 13:52                   ` Jarek Poplawski
2007-11-05 14:06                     ` jamal
2007-11-05 17:31                       ` Radu Rendec
2007-11-05 21:06                         ` Jarek Poplawski
2007-11-05 21:28                           ` Jarek Poplawski
2007-11-05 22:27                           ` jamal
2007-11-06  0:02                             ` Jarek Poplawski
2007-11-06  0:12                               ` Jarek Poplawski
2007-11-06  8:09                               ` Radu Rendec
2007-11-06 13:34                                 ` jamal
2007-11-06 14:25                                   ` Jarek Poplawski
2007-11-06 14:43                                     ` jamal
2007-11-06 17:00                                       ` Radu Rendec
2007-11-06 20:28                                         ` Jarek Poplawski
2007-11-07  9:22                                         ` David Miller
2007-11-07 12:56                                           ` Jarek Poplawski
2007-11-07 13:42                                           ` jamal
2007-11-07 13:55                                             ` Radu Rendec
2007-11-07 14:35                                           ` Radu Rendec
2007-11-08 11:07                                           ` [PATCH] [PKT_SCHED] CLS_U32: Use ffs() instead of C code on hash mask to get first set bit Radu Rendec
2007-11-08 11:37                                             ` Jarek Poplawski [this message]
2007-11-08 13:45                                             ` jamal
2007-11-11  5:55                                               ` David Miller
2007-11-05 13:47                 ` Endianness problem with u32 classifier hash masks jamal
2007-11-05 14:35                   ` Jarek Poplawski

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=20071108113752.GA1602@ff.dom.local \
    --to=jarkao2@o2.pl \
    --cc=davem@davemloft.net \
    --cc=hadi@cyberus.ca \
    --cc=netdev@vger.kernel.org \
    --cc=radu.rendec@ines.ro \
    /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).