[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-ID: <1361485132.17413.19.camel@edumazet-glaptop>
Date: Thu, 21 Feb 2013 14:18:52 -0800
From: Eric Dumazet <eric.dumazet@...il.com>
To: David Miller <davem@...emloft.net>
Cc: netdev <netdev@...r.kernel.org>,
Neal Cardwell <ncardwell@...gle.com>,
Yuchung Cheng <ycheng@...gle.com>
Subject: [PATCH] ipv6: use a stronger hash for tcp
From: Eric Dumazet <edumazet@...gle.com>
It looks like its possible to open thousands of TCP IPv6
sessions on a server, all landing in a single slot of TCP hash
table. Incoming packets have to lookup sockets in a very
long list.
We should hash all bits from foreign IPv6 addresses, using
a salt and hash mix, not a simple XOR.
inet6_ehashfn() can also separately use the ports, instead
of xoring them.
Reported-by: Neal Cardwell <ncardwell@...gle.com>
Signed-off-by: Eric Dumazet <edumazet@...gle.com>
Cc: Yuchung Cheng <ycheng@...gle.com>
---
include/net/inet6_hashtables.h | 8 ++++----
include/net/inet_sock.h | 1 +
include/net/ipv6.h | 12 ++++++++++++
net/ipv4/af_inet.c | 9 +++++++--
4 files changed, 24 insertions(+), 6 deletions(-)
diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 7ca75cb..fd4ee01 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -28,16 +28,16 @@
struct inet_hashinfo;
-/* I have no idea if this is a good hash for v6 or not. -DaveM */
static inline unsigned int inet6_ehashfn(struct net *net,
const struct in6_addr *laddr, const u16 lport,
const struct in6_addr *faddr, const __be16 fport)
{
- u32 ports = (lport ^ (__force u16)fport);
+ u32 ports = (((u32)lport) << 16) | (__force u32)fport;
return jhash_3words((__force u32)laddr->s6_addr32[3],
- (__force u32)faddr->s6_addr32[3],
- ports, inet_ehash_secret + net_hash_mix(net));
+ ipv6_addr_jhash(faddr),
+ ports,
+ inet_ehash_secret + net_hash_mix(net));
}
static inline int inet6_sk_ehashfn(const struct sock *sk)
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index a4196cb..7235ae7 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -203,6 +203,7 @@ static inline void inet_sk_copy_descendant(struct sock *sk_to,
extern int inet_sk_rebuild_header(struct sock *sk);
extern u32 inet_ehash_secret;
+extern u32 ipv6_hash_secret;
extern void build_ehash_secret(void);
static inline unsigned int inet_ehashfn(struct net *net,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 851d541..d772f99 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -15,6 +15,7 @@
#include <linux/ipv6.h>
#include <linux/hardirq.h>
+#include <linux/jhash.h>
#include <net/if_inet6.h>
#include <net/ndisc.h>
#include <net/flow.h>
@@ -514,6 +515,17 @@ static inline u32 ipv6_addr_hash(const struct in6_addr *a)
#endif
}
+/* more secured version of ipv6_addr_hash() */
+static inline u32 ipv6_addr_jhash(const struct in6_addr *a)
+{
+ u32 v = (__force u32)a->s6_addr32[0] ^ (__force u32)a->s6_addr32[1];
+
+ return jhash_3words(v,
+ (__force u32)a->s6_addr32[2],
+ (__force u32)a->s6_addr32[3],
+ ipv6_hash_secret);
+}
+
static inline bool ipv6_addr_loopback(const struct in6_addr *a)
{
#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e225a4e..9cbcb94 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -248,8 +248,12 @@ EXPORT_SYMBOL(inet_listen);
u32 inet_ehash_secret __read_mostly;
EXPORT_SYMBOL(inet_ehash_secret);
+u32 ipv6_hash_secret __read_mostly;
+EXPORT_SYMBOL(ipv6_hash_secret);
+
/*
- * inet_ehash_secret must be set exactly once
+ * inet_ehash_secret must be set exactly once, and to a non nul value
+ * ipv6_hash_secret must be set exactly once.
*/
void build_ehash_secret(void)
{
@@ -259,7 +263,8 @@ void build_ehash_secret(void)
get_random_bytes(&rnd, sizeof(rnd));
} while (rnd == 0);
- cmpxchg(&inet_ehash_secret, 0, rnd);
+ if (cmpxchg(&inet_ehash_secret, 0, rnd) == 0)
+ get_random_bytes(&ipv6_hash_secret, sizeof(ipv6_hash_secret));
}
EXPORT_SYMBOL(build_ehash_secret);
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists