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/include/net/sock.h b/include/net/sock.h
index 1621935aad5bc5b3e69299c136c685dd42dbff92..98398bdec57d04a4bef71b3d22d7aa0f79ed703d 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -504,6 +504,7 @@ enum sock_flags {
        SOCK_TIMESTAMPING_SOFTWARE,     /* %SOF_TIMESTAMPING_SOFTWARE */
        SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */
        SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
+       SOCK_FASYNC, /* fasync() active */
 };
 
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
@@ -1396,7 +1397,7 @@ static inline unsigned long sock_wspace(struct sock *sk)
 
 static inline void sk_wake_async(struct sock *sk, int how, int band)
 {
-       if (sk->sk_socket && sk->sk_socket->fasync_list)
+       if (sock_flag(sk, SOCK_FASYNC))
                sock_wake_async(sk->sk_socket, how, band);
 }
 

diff --git a/net/socket.c b/net/socket.c
index 75655365b5fd2041d9bdf97d936275b1f74b217e..d53ad11558c32ad13fb404e57a5e22f30bcc1022 100644 (file)
--- a/net/socket.c
+++ b/net/socket.c
@@ -1100,11 +1100,14 @@ static int sock_fasync(int fd, struct file *filp, int on)
                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);
                }