netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Stephen Hemminger <shemminger@vyatta.com>
To: "David S. Miller" <davem@davemloft.net>
Cc: netdev@vger.kernel.org
Subject: [PATCH 5/6] IPV4: route use jhash3
Date: Mon, 31 Mar 2008 17:47:13 -0700	[thread overview]
Message-ID: <20080401004724.752793269@vyatta.com> (raw)
In-Reply-To: 20080401004708.009204033@vyatta.com

[-- Attachment #1: route-jhash3 --]
[-- Type: text/plain, Size: 1047 bytes --]

Since route hash is a triple, use jhash_3words rather doing the mixing
directly. This should be as fast and give better distribution.

Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>

--- a/net/ipv4/route.c	2008-03-31 11:14:50.000000000 -0700
+++ b/net/ipv4/route.c	2008-03-31 11:15:20.000000000 -0700
@@ -259,16 +259,14 @@ static DEFINE_PER_CPU(struct rt_cache_st
 #define RT_CACHE_STAT_INC(field) \
 	(__raw_get_cpu_var(rt_cache_stat).field++)
 
-static unsigned int rt_hash_code(u32 daddr, u32 saddr)
+static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx)
 {
-	return jhash_2words(daddr, saddr, atomic_read(&rt_genid))
-		& rt_hash_mask;
+	return jhash_3words((__force u32)(__be32)(daddr),
+			    (__force u32)(__be32)(saddr),
+			    idx, atomic_read(&rt_genid))
+  		& rt_hash_mask;
 }
 
-#define rt_hash(daddr, saddr, idx) \
-	rt_hash_code((__force u32)(__be32)(daddr),\
-		     (__force u32)(__be32)(saddr) ^ ((idx) << 5))
-
 #ifdef CONFIG_PROC_FS
 struct rt_cache_iter_state {
 	struct seq_net_private p;

-- 


  parent reply	other threads:[~2008-04-01  2:31 UTC|newest]

Thread overview: 19+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20080401004708.009204033@vyatta.com>
2008-04-01  0:47 ` [PATCH 1/6] socket: sk_filter minor cleanups Stephen Hemminger
2008-04-10  8:39   ` David Miller
2008-04-01  0:47 ` [PATCH 2/6] socket: sk_filter deinline Stephen Hemminger
2008-04-10  8:49   ` David Miller
2008-04-01  0:47 ` [PATCH 3/6] IPV4 : use xor rather than multiple ands for route compare Stephen Hemminger
2008-04-01  5:52   ` Eric Dumazet
2008-04-01 20:08     ` Stephen Hemminger
2008-04-10  8:51       ` David Miller
2008-04-10  9:01         ` YOSHIFUJI Hideaki / 吉藤英明
2008-04-10 10:56           ` David Miller
2008-04-10 12:17             ` YOSHIFUJI Hideaki / 吉藤英明
2008-04-10  9:26         ` Eric Dumazet
2008-04-10 11:00           ` David Miller
2008-04-01  0:47 ` [PATCH 4/6] IPV4: route inline changes Stephen Hemminger
2008-04-10  8:53   ` David Miller
2008-04-01  0:47 ` Stephen Hemminger [this message]
2008-04-10  8:54   ` [PATCH 5/6] IPV4: route use jhash3 David Miller
2008-04-01  0:47 ` [PATCH 6/6] IPV4: route rekey timer can be deferrable Stephen Hemminger
2008-04-10  8:55   ` 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=20080401004724.752793269@vyatta.com \
    --to=shemminger@vyatta.com \
    --cc=davem@davemloft.net \
    --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 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).