ipv6: use a stronger hash for tcp

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.

Change-Id: Ibd708e9d1d9d2bdb7bea6488c259edc576b98780
Reported-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Iliyan Malchev <malchev@google.com>

4 files changed, 26 insertions, 4 deletions

diff --git a/include/net/inet6_hashtables.h b/include/net/inet6_hashtables.h
index 40e022dc..f3a55a71 100644
--- a/include/net/inet6_hashtables.h
+++ b/include/net/inet6_hashtables.h
@@ -32,11 +32,12 @@ 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 ab149dec..7a7e6f80 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -180,6 +180,7 @@ 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 491fc9cf..8d59e1b4 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>
@@ -389,6 +390,17 @@ static inline int ipv6_addr_any(const struct in6_addr *a)
 		a->s6_addr32[2] | a->s6_addr32[3]) == 0;
 }
 
+/* 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 int ipv6_addr_loopback(const struct in6_addr *a)
 {
 	return (a->s6_addr32[0] | a->s6_addr32[1] |
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 9787fbc5..5894aeea 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -225,6 +225,13 @@ 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, and to a non nul value
+ * ipv6_hash_secret must be set exactly once.
+ */
 void build_ehash_secret(void)
 {
 	u32 rnd;
@@ -233,7 +240,8 @@ 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);