summaryrefslogtreecommitdiffstats
path: root/net/ipv6/inet6_connection_sock.c
diff options
context:
space:
mode:
authorTom Herbert <therbert@google.com>2013-01-22 10:50:39 +0100
committerDavid S. Miller <davem@davemloft.net>2013-01-23 19:44:01 +0100
commit5ba24953e9707387cce87b07f0d5fbdd03c5c11b (patch)
treec98e56f8a06f07ff585f85cbe6af8cd9c19f2ca6 /net/ipv6/inet6_connection_sock.c
parentsoreuseport: UDP/IPv4 implementation (diff)
downloadlinux-5ba24953e9707387cce87b07f0d5fbdd03c5c11b.tar.xz
linux-5ba24953e9707387cce87b07f0d5fbdd03c5c11b.zip
soreuseport: TCP/IPv6 implementation
Motivation for soreuseport would be something like a web server binding to port 80 running with multiple threads, where each thread might have it's own listener socket. This could be done as an alternative to other models: 1) have one listener thread which dispatches completed connections to workers. 2) accept on a single listener socket from multiple threads. In case #1 the listener thread can easily become the bottleneck with high connection turn-over rate. In case #2, the proportion of connections accepted per thread tends to be uneven under high connection load (assuming simple event loop: while (1) { accept(); process() }, wakeup does not promote fairness among the sockets. We have seen the disproportion to be as high as 3:1 ratio between thread accepting most connections and the one accepting the fewest. With so_reusport the distribution is uniform. Signed-off-by: Tom Herbert <therbert@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6/inet6_connection_sock.c')
-rw-r--r--net/ipv6/inet6_connection_sock.c19
1 files changed, 14 insertions, 5 deletions
diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c
index 30647857a375..e4297a393678 100644
--- a/net/ipv6/inet6_connection_sock.c
+++ b/net/ipv6/inet6_connection_sock.c
@@ -32,6 +32,9 @@ int inet6_csk_bind_conflict(const struct sock *sk,
{
const struct sock *sk2;
const struct hlist_node *node;
+ int reuse = sk->sk_reuse;
+ int reuseport = sk->sk_reuseport;
+ int uid = sock_i_uid((struct sock *)sk);
/* We must walk the whole port owner list in this case. -DaveM */
/*
@@ -42,11 +45,17 @@ int inet6_csk_bind_conflict(const struct sock *sk,
if (sk != sk2 &&
(!sk->sk_bound_dev_if ||
!sk2->sk_bound_dev_if ||
- sk->sk_bound_dev_if == sk2->sk_bound_dev_if) &&
- (!sk->sk_reuse || !sk2->sk_reuse ||
- sk2->sk_state == TCP_LISTEN) &&
- ipv6_rcv_saddr_equal(sk, sk2))
- break;
+ sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
+ if ((!reuse || !sk2->sk_reuse ||
+ sk2->sk_state == TCP_LISTEN) &&
+ (!reuseport || !sk2->sk_reuseport ||
+ (sk2->sk_state != TCP_TIME_WAIT &&
+ !uid_eq(uid,
+ sock_i_uid((struct sock *)sk2))))) {
+ if (ipv6_rcv_saddr_equal(sk, sk2))
+ break;
+ }
+ }
}
return node != NULL;