diff options
author | Eric Dumazet <eric.dumazet@gmail.com> | 2010-04-08 23:03:29 (GMT) |
---|---|---|
committer | David S. Miller <davem@davemloft.net> | 2010-04-13 08:41:33 (GMT) |
commit | b6c6712a42ca3f9fa7f4a3d7c40e3a9dd1fd9e03 (patch) | |
tree | 42032b4978874e8ffcf6c851d13324b8c8c7c113 /include/net/ip6_route.h | |
parent | 7a161ea92471087a1579239d7a58dd06eaa5601c (diff) | |
download | linux-b6c6712a42ca3f9fa7f4a3d7c40e3a9dd1fd9e03.tar.xz |
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>
Diffstat (limited to 'include/net/ip6_route.h')
-rw-r--r-- | include/net/ip6_route.h | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 68f67836..278312c 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -152,9 +152,9 @@ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, struct in6_addr *daddr, struct in6_addr *saddr) { - write_lock(&sk->sk_dst_lock); + spin_lock(&sk->sk_dst_lock); __ip6_dst_store(sk, dst, daddr, saddr); - write_unlock(&sk->sk_dst_lock); + spin_unlock(&sk->sk_dst_lock); } static inline int ipv6_unicast_destination(struct sk_buff *skb) |