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
>
next prev parent 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).