path: root/net/ipv4/inet_hashtables.c
diff options
authorEric Dumazet <edumazet@google.com>2015-10-02 11:43:32 -0700
committerDavid S. Miller <davem@davemloft.net>2015-10-03 04:32:41 -0700
commit079096f103faca2dd87342cca6f23d4b34da8871 (patch)
treefa3fb0fdc064f1611c464384e70a7a402179808f /net/ipv4/inet_hashtables.c
parenttcp/dccp: remove inet_csk_reqsk_queue_added() timeout argument (diff)
tcp/dccp: install syn_recv requests into ehash table
In this patch, we insert request sockets into TCP/DCCP regular ehash table (where ESTABLISHED and TIMEWAIT sockets are) instead of using the per listener hash table. ACK packets find SYN_RECV pseudo sockets without having to find and lock the listener. In nominal conditions, this halves pressure on listener lock. Note that this will allow for SO_REUSEPORT refinements, so that we can select a listener using cpu/numa affinities instead of the prior 'consistent hash', since only SYN packets will apply this selection logic. We will shrink listen_sock in the following patch to ease code review. Signed-off-by: Eric Dumazet <edumazet@google.com> Cc: Ying Cai <ycai@google.com> Cc: Willem de Bruijn <willemb@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to '')
1 files changed, 12 insertions, 2 deletions
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 56742e995dd3..bed8886a4b6c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -398,14 +398,18 @@ static u32 inet_sk_port_offset(const struct sock *sk)
-void __inet_hash_nolisten(struct sock *sk, struct sock *osk)
+/* insert a socket into ehash, and eventually remove another one
+ * (The another one can be a SYN_RECV or TIMEWAIT
+ */
+int inet_ehash_insert(struct sock *sk, struct sock *osk)
struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
struct hlist_nulls_head *list;
struct inet_ehash_bucket *head;
spinlock_t *lock;
+ int ret = 0;
- WARN_ON(!sk_unhashed(sk));
+ WARN_ON_ONCE(!sk_unhashed(sk));
sk->sk_hash = sk_ehashfn(sk);
head = inet_ehash_bucket(hashinfo, sk->sk_hash);
@@ -419,6 +423,12 @@ void __inet_hash_nolisten(struct sock *sk, struct sock *osk)
+ return ret;
+void __inet_hash_nolisten(struct sock *sk, struct sock *osk)
+ inet_ehash_insert(sk, osk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);