net: speedup sk_wake_async()
An incoming datagram must bring into cpu cache *lot* of cache lines,
in particular : (other parts omitted (hash chains, ip route cache...))
On 32bit arches :
offsetof(struct sock, sk_rcvbuf) =0x30 (read)
offsetof(struct sock, sk_lock) =0x34 (rw)
offsetof(struct sock, sk_sleep) =0x50 (read)
offsetof(struct sock, sk_rmem_alloc) =0x64 (rw)
offsetof(struct sock, sk_receive_queue)=0x74 (rw)
offsetof(struct sock, sk_forward_alloc)=0x98 (rw)
offsetof(struct sock, sk_callback_lock)=0xcc (rw)
offsetof(struct sock, sk_drops) =0xd8 (read if we add dropcount support, rw if frame dropped)
offsetof(struct sock, sk_filter) =0xf8 (read)
offsetof(struct sock, sk_socket) =0x138 (read)
offsetof(struct sock, sk_data_ready) =0x15c (read)
We can avoid sk->sk_socket and socket->fasync_list referencing on sockets
with no fasync() structures. (socket->fasync_list ptr is probably already in cache
because it shares a cache line with socket->wait, ie location pointed by sk->sk_sleep)
This avoids one cache line load per incoming packet for common cases (no fasync())
We can leave (or even move in a future patch) sk->sk_socket in a cold location
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/net/socket.c b/net/socket.c
index 7565536..d53ad11 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1100,11 +1100,14 @@
fna->fa_next = sock->fasync_list;
write_lock_bh(&sk->sk_callback_lock);
sock->fasync_list = fna;
+ sock_set_flag(sk, SOCK_FASYNC);
write_unlock_bh(&sk->sk_callback_lock);
} else {
if (fa != NULL) {
write_lock_bh(&sk->sk_callback_lock);
*prev = fa->fa_next;
+ if (!sock->fasync_list)
+ sock_reset_flag(sk, SOCK_FASYNC);
write_unlock_bh(&sk->sk_callback_lock);
kfree(fa);
}