Patchwork [5/5] soreuseport: UDP/IPv6 implementation

login
register
mail settings
Submitter Tom Herbert
Date Jan. 14, 2013, 8 p.m.
Message ID <alpine.DEB.2.00.1301141139190.1968@pokey.mtv.corp.google.com>
Download mbox | patch
Permalink /patch/211877/
State Changes Requested
Delegated to: David Miller
Headers show

Comments

Tom Herbert - Jan. 14, 2013, 8 p.m.
Allow multiple UDP sockets to bind to the same port.

Motivation for soreuseport would be something like a DNS server.  An
alternative would be to recv on the same socket from multiple threads.
As in the case of TCP, the load across these threads tends to be
disproportionate and we also see a lot of contection on the socket lock.
Note that SO_REUSEADDR already allows multiple UDP sockets to bind to
the same port, however there is no provision to prevent hijacking and
nothing to distribute packets across all the sockets sharing the same
bound port.  This patch does not change the semantics of SO_REUSEADDR,
but provides usable functionality of it for unicast.

Signed-off-by: Tom Herbert <therbert@google.com>
---
 net/ipv6/udp.c |   30 +++++++++++++++++++++++++++---
 1 files changed, 27 insertions(+), 3 deletions(-)
YOSHIFUJI Hideaki / 吉藤英明 - Jan. 14, 2013, 8:27 p.m.
Tom Herbert wrote:
> +				hash = inet6_ehashfn(net, daddr, hnum,
> +				    saddr, sport);
:
> +				hash = inet6_ehashfn(net, daddr, hnum,
> +				    saddr, sport);

Ditto.

--yoshfuji
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1afb635..779d8c0 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -45,6 +45,7 @@ 
 #include <net/tcp_states.h>
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
+#include <net/inet6_hashtables.h>
 
 #include <linux/proc_fs.h>
 #include <linux/seq_file.h>
@@ -203,7 +204,8 @@  static struct sock *udp6_lib_lookup2(struct net *net,
 {
 	struct sock *sk, *result;
 	struct hlist_nulls_node *node;
-	int score, badness;
+	int score, badness, matches = 0, reuseport = 0;
+	u32 hash = 0;
 
 begin:
 	result = NULL;
@@ -214,8 +216,18 @@  begin:
 		if (score > badness) {
 			result = sk;
 			badness = score;
-			if (score == SCORE2_MAX)
+			reuseport = sk->sk_reuseport;
+			if (reuseport) {
+				hash = inet6_ehashfn(net, daddr, hnum,
+				    saddr, sport);
+				matches = 1;
+			} else if (score == SCORE2_MAX)
 				goto exact_match;
+		} else if (score == badness && reuseport) {
+			matches++;
+			if (((u64)hash * matches) >> 32 == 0)
+				result = sk;
+			hash = next_pseudo_random32(hash);
 		}
 	}
 	/*
@@ -249,7 +261,8 @@  struct sock *__udp6_lib_lookup(struct net *net,
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
 	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
-	int score, badness;
+	int score, badness, matches = 0, reuseport = 0;
+	u32 hash = 0;
 
 	rcu_read_lock();
 	if (hslot->count > 10) {
@@ -284,6 +297,17 @@  begin:
 		if (score > badness) {
 			result = sk;
 			badness = score;
+			reuseport = sk->sk_reuseport;
+			if (reuseport) {
+				hash = inet6_ehashfn(net, daddr, hnum,
+				    saddr, sport);
+				matches = 1;
+			}
+		} else if (score == badness && reuseport) {
+			matches++;
+			if (((u64)hash * matches) >> 32 == 0)
+				result = sk;
+			hash = next_pseudo_random32(hash);
 		}
 	}
 	/*