sock: avoid dirtying sk_stamp, if possible

sock_recv_ts_and_drops() unconditionally set sk->sk_stamp for
every packet, even if the SOCK_TIMESTAMP flag is not set in the
related socket.
If selinux is enabled, this cause a cache miss for every packet
since sk->sk_stamp and sk->sk_security share the same cacheline.
With this change sk_stamp is set only if the SOCK_TIMESTAMP
flag is set, and is cleared for the first packet, so that the user
perceived behavior is unchanged.

This gives up to 5% speed-up under udp-flood with small packets.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/sock.h b/include/net/sock.h
index cb241a0..8e53158 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2239,6 +2239,7 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
                              struct sk_buff *skb);
 
+#define SK_DEFAULT_STAMP (-1L * NSEC_PER_SEC)
 static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
                                          struct sk_buff *skb)
 {
@@ -2249,8 +2250,10 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 
        if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
                __sock_recv_ts_and_drops(msg, sk, skb);
-       else
+       else if (unlikely(sk->sk_flags & SOCK_TIMESTAMP))
                sk->sk_stamp = skb->tstamp;
+       else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+               sk->sk_stamp = 0;
 }
 
 void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);

diff --git a/net/core/sock.c b/net/core/sock.c
index 1a58a9d..392f9b6 100644 (file)
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2613,7 +2613,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
        sk->sk_rcvtimeo         =       MAX_SCHEDULE_TIMEOUT;
        sk->sk_sndtimeo         =       MAX_SCHEDULE_TIMEOUT;
 
-       sk->sk_stamp = ktime_set(-1L, 0);
+       sk->sk_stamp = SK_DEFAULT_STAMP;
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
        sk->sk_napi_id          =       0;