diff options
author | Craig Gallek <kraig@google.com> | 2016-02-10 17:50:40 +0100 |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2016-02-11 09:54:15 +0100 |
commit | c125e80b88687b25b321795457309eaaee4bf270 (patch) | |
tree | d61eb6c67a62046691c8f354c0fad948ef298f99 /net/ipv4/inet_connection_sock.c | |
parent | soreuseport: Prep for fast reuseport TCP socket selection (diff) | |
download | linux-c125e80b88687b25b321795457309eaaee4bf270.tar.xz linux-c125e80b88687b25b321795457309eaaee4bf270.zip |
soreuseport: fast reuseport TCP socket selection
This change extends the fast SO_REUSEPORT socket lookup implemented
for UDP to TCP. Listener sockets with SO_REUSEPORT and the same
receive address are additionally added to an array for faster
random access. This means that only a single socket from the group
must be found in the listener list before any socket in the group can
be used to receive a packet. Previously, every socket in the group
needed to be considered before handing off the incoming packet.
This feature also exposes the ability to use a BPF program when
selecting a socket from a reuseport group.
Signed-off-by: Craig Gallek <kraig@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/inet_connection_sock.c')
-rw-r--r-- | net/ipv4/inet_connection_sock.c | 14 |
1 files changed, 10 insertions, 4 deletions
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 12c8d389dc18..c16a2e6273d9 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -24,6 +24,7 @@ #include <net/tcp_states.h> #include <net/xfrm.h> #include <net/tcp.h> +#include <net/sock_reuseport.h> #ifdef INET_CSK_DEBUG const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; @@ -67,7 +68,8 @@ int inet_csk_bind_conflict(const struct sock *sk, if ((!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) && (!reuseport || !sk2->sk_reuseport || - (sk2->sk_state != TCP_TIME_WAIT && + rcu_access_pointer(sk->sk_reuseport_cb) || + (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid(sk2))))) { if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr || @@ -132,6 +134,7 @@ again: sk->sk_state != TCP_LISTEN) || (tb->fastreuseport > 0 && sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && uid_eq(tb->fastuid, uid))) && (tb->num_owners < smallest_size || smallest_size == -1)) { smallest_size = tb->num_owners; @@ -193,15 +196,18 @@ tb_found: if (((tb->fastreuse > 0 && sk->sk_reuse && sk->sk_state != TCP_LISTEN) || (tb->fastreuseport > 0 && - sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && - smallest_size == -1) { + sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + uid_eq(tb->fastuid, uid))) && smallest_size == -1) { goto success; } else { ret = 1; if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb, true)) { if (((sk->sk_reuse && sk->sk_state != TCP_LISTEN) || (tb->fastreuseport > 0 && - sk->sk_reuseport && uid_eq(tb->fastuid, uid))) && + sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + uid_eq(tb->fastuid, uid))) && smallest_size != -1 && --attempts >= 0) { spin_unlock(&head->lock); goto again; |