summaryrefslogtreecommitdiffstats
path: root/net/ipv4/inet_timewait_sock.c
diff options
context:
space:
mode:
authorEric Dumazet <dada1@cosmosbay.com>2008-11-16 19:40:17 -0800
committerDavid S. Miller <davem@davemloft.net>2008-11-16 19:40:17 -0800
commit3ab5aee7fe840b5b1b35a8d1ac11c3de5281e611 (patch)
tree468296b7be813643248d4ca67497d6ddb6934fc6 /net/ipv4/inet_timewait_sock.c
parent88ab1932eac721c6e7336708558fa5ed02c85c80 (diff)
downloadlinux-3ab5aee7fe840b5b1b35a8d1ac11c3de5281e611.tar.gz
linux-3ab5aee7fe840b5b1b35a8d1ac11c3de5281e611.tar.bz2
linux-3ab5aee7fe840b5b1b35a8d1ac11c3de5281e611.zip
net: Convert TCP & DCCP hash tables to use RCU / hlist_nulls
RCU was added to UDP lookups, using a fast infrastructure : - sockets kmem_cache use SLAB_DESTROY_BY_RCU and dont pay the price of call_rcu() at freeing time. - hlist_nulls permits to use few memory barriers. This patch uses same infrastructure for TCP/DCCP established and timewait sockets. Thanks to SLAB_DESTROY_BY_RCU, no slowdown for applications using short lived TCP connections. A followup patch, converting rwlocks to spinlocks will even speedup this case. __inet_lookup_established() is pretty fast now we dont have to dirty a contended cache line (read_lock/read_unlock) Only established and timewait hashtable are converted to RCU (bind table and listen table are still using traditional locking) Signed-off-by: Eric Dumazet <dada1@cosmosbay.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv4/inet_timewait_sock.c')
-rw-r--r--net/ipv4/inet_timewait_sock.c26
1 files changed, 15 insertions, 11 deletions
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 1c5fd38f8824..60689951ecdb 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -23,12 +23,12 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw,
rwlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
write_lock(lock);
- if (hlist_unhashed(&tw->tw_node)) {
+ if (hlist_nulls_unhashed(&tw->tw_node)) {
write_unlock(lock);
return;
}
- __hlist_del(&tw->tw_node);
- sk_node_init(&tw->tw_node);
+ hlist_nulls_del_rcu(&tw->tw_node);
+ sk_nulls_node_init(&tw->tw_node);
write_unlock(lock);
/* Disassociate with bind bucket. */
@@ -92,13 +92,17 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
write_lock(lock);
- /* Step 2: Remove SK from established hash. */
- if (__sk_del_node_init(sk))
- sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-
- /* Step 3: Hash TW into TIMEWAIT chain. */
- inet_twsk_add_node(tw, &ehead->twchain);
+ /*
+ * Step 2: Hash TW into TIMEWAIT chain.
+ * Should be done before removing sk from established chain
+ * because readers are lockless and search established first.
+ */
atomic_inc(&tw->tw_refcnt);
+ inet_twsk_add_node_rcu(tw, &ehead->twchain);
+
+ /* Step 3: Remove SK from established hash. */
+ if (__sk_nulls_del_node_init_rcu(sk))
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
write_unlock(lock);
}
@@ -416,7 +420,7 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
{
struct inet_timewait_sock *tw;
struct sock *sk;
- struct hlist_node *node;
+ struct hlist_nulls_node *node;
int h;
local_bh_disable();
@@ -426,7 +430,7 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo,
rwlock_t *lock = inet_ehash_lockp(hashinfo, h);
restart:
write_lock(lock);
- sk_for_each(sk, node, &head->twchain) {
+ sk_nulls_for_each(sk, node, &head->twchain) {
tw = inet_twsk(sk);
if (!net_eq(twsk_net(tw), net) ||