net: sk_dst_cache RCUification

With latest CONFIG_PROVE_RCU stuff, I felt more comfortable to make this
work.

sk->sk_dst_cache is currently protected by a rwlock (sk_dst_lock)

This rwlock is readlocked for a very small amount of time, and dst
entries are already freed after RCU grace period. This calls for RCU
again :)

This patch converts sk_dst_lock to a spinlock, and use RCU for readers.

__sk_dst_get() is supposed to be called with rcu_read_lock() or if
socket locked by user, so use appropriate rcu_dereference_check()
condition (rcu_read_lock_held() || sock_owned_by_user(sk))

This patch avoids two atomic ops per tx packet on UDP connected sockets,
for example, and permits sk_dst_lock to be much less dirtied.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 5 insertions, 5 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index a0beb32beaa3..193dcd6ed64f 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -154,7 +154,7 @@ void inet_sock_destruct(struct sock *sk)
         WARN_ON(sk->sk_forward_alloc);
 
         kfree(inet->opt);
-        dst_release(sk->sk_dst_cache);
+        dst_release(rcu_dereference_check(sk->sk_dst_cache, 1));
         sk_refcnt_debug_dec(sk);
 }
 EXPORT_SYMBOL(inet_sock_destruct);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4000b10610b7..ae3ec15fb630 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3710,7 +3710,7 @@ static int tcp_ack(struct sock *sk, struct sk_buff *skb, int flag)
         }
 
         if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP))
-                dst_confirm(sk->sk_dst_cache);
+                dst_confirm(__sk_dst_get(sk));
 
         return 1;
 
@@ -5833,7 +5833,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
                         if (tp->snd_una == tp->write_seq) {
                                 tcp_set_state(sk, TCP_FIN_WAIT2);
                                 sk->sk_shutdown |= SEND_SHUTDOWN;
-                                dst_confirm(sk->sk_dst_cache);
+                                dst_confirm(__sk_dst_get(sk));
 
                                 if (!sock_flag(sk, SOCK_DEAD))
                                         /* Wake up lingering close() */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 8a0ab2977f1f..c732be00606b 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -172,14 +172,14 @@ static int tcp_write_timeout(struct sock *sk)
 
         if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
                 if (icsk->icsk_retransmits)
-                        dst_negative_advice(&sk->sk_dst_cache, sk);
+                        dst_negative_advice(sk);
                 retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
         } else {
                 if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
                         /* Black hole detection */
                         tcp_mtu_probing(icsk, sk);
 
-                        dst_negative_advice(&sk->sk_dst_cache, sk);
+                        dst_negative_advice(sk);
                 }
 
                 retry_until = sysctl_tcp_retries2;