[SOCK] proto: Add hashinfo member to struct proto

This way we can remove TCP and DCCP specific versions of

sk->sk_prot->get_port: both v4 and v6 use inet_csk_get_port
sk->sk_prot->hash:     inet_hash is directly used, only v6 need
                       a specific version to deal with mapped sockets
sk->sk_prot->unhash:   both v4 and v6 use inet_hash directly

struct inet_connection_sock_af_ops also gets a new member, bind_conflict, so
that inet_csk_get_port can find the per family routine.

Now only the lookup routines receive as a parameter a struct inet_hashtable.

With this we further reuse code, reducing the difference among INET transport
protocols.

Eventually work has to be done on UDP and SCTP to make them share this
infrastructure and get as a bonus inet_diag interfaces so that iproute can be
used with these protocols.

net-2.6/net/ipv4/inet_hashtables.c:
  struct proto			     |   +8
  struct inet_connection_sock_af_ops |   +8
 2 structs changed
  __inet_hash_nolisten               |  +18
  __inet_hash                        | -210
  inet_put_port                      |   +8
  inet_bind_bucket_create            |   +1
  __inet_hash_connect                |   -8
 5 functions changed, 27 bytes added, 218 bytes removed, diff: -191

net-2.6/net/core/sock.c:
  proto_seq_show                     |   +3
 1 function changed, 3 bytes added, diff: +3

net-2.6/net/ipv4/inet_connection_sock.c:
  inet_csk_get_port                  |  +15
 1 function changed, 15 bytes added, diff: +15

net-2.6/net/ipv4/tcp.c:
  tcp_set_state                      |   -7
 1 function changed, 7 bytes removed, diff: -7

net-2.6/net/ipv4/tcp_ipv4.c:
  tcp_v4_get_port                    |  -31
  tcp_v4_hash                        |  -48
  tcp_v4_destroy_sock                |   -7
  tcp_v4_syn_recv_sock               |   -2
  tcp_unhash                         | -179
 5 functions changed, 267 bytes removed, diff: -267

net-2.6/net/ipv6/inet6_hashtables.c:
  __inet6_hash |   +8
 1 function changed, 8 bytes added, diff: +8

net-2.6/net/ipv4/inet_hashtables.c:
  inet_unhash                        | +190
  inet_hash                          | +242
 2 functions changed, 432 bytes added, diff: +432

vmlinux:
 16 functions changed, 485 bytes added, 492 bytes removed, diff: -7

/home/acme/git/net-2.6/net/ipv6/tcp_ipv6.c:
  tcp_v6_get_port                    |  -31
  tcp_v6_hash                        |   -7
  tcp_v6_syn_recv_sock               |   -9
 3 functions changed, 47 bytes removed, diff: -47

/home/acme/git/net-2.6/net/dccp/proto.c:
  dccp_destroy_sock                  |   -7
  dccp_unhash                        | -179
  dccp_hash                          |  -49
  dccp_set_state                     |   -7
  dccp_done                          |   +1
 5 functions changed, 1 bytes added, 242 bytes removed, diff: -241

/home/acme/git/net-2.6/net/dccp/ipv4.c:
  dccp_v4_get_port                   |  -31
  dccp_v4_request_recv_sock          |   -2
 2 functions changed, 33 bytes removed, diff: -33

/home/acme/git/net-2.6/net/dccp/ipv6.c:
  dccp_v6_get_port                   |  -31
  dccp_v6_hash                       |   -7
  dccp_v6_request_recv_sock          |   +5
 3 functions changed, 5 bytes added, 38 bytes removed, diff: -33

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 60 insertions, 39 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index de5a41d..b189278 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -78,11 +78,9 @@ EXPORT_SYMBOL_GPL(inet_csk_bind_conflict);
 /* Obtain a reference to a local port for the given sock,
  * if snum is zero it means select any available local port.
  */
-int inet_csk_get_port(struct inet_hashinfo *hashinfo,
-		      struct sock *sk, unsigned short snum,
-		      int (*bind_conflict)(const struct sock *sk,
-					   const struct inet_bind_bucket *tb))
+int inet_csk_get_port(struct sock *sk, unsigned short snum)
 {
+	struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
 	struct inet_bind_hashbucket *head;
 	struct hlist_node *node;
 	struct inet_bind_bucket *tb;
@@ -142,7 +140,7 @@ tb_found:
 			goto success;
 		} else {
 			ret = 1;
-			if (bind_conflict(sk, tb))
+			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb))
 				goto fail_unlock;
 		}
 	}
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 48d4500..90f422c 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -66,8 +66,9 @@ void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb,
 /*
  * Get rid of any references to a local port held by the given sock.
  */
-static void __inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
+static void __inet_put_port(struct sock *sk)
 {
+	struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
 	const int bhash = inet_bhashfn(inet_sk(sk)->num, hashinfo->bhash_size);
 	struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash];
 	struct inet_bind_bucket *tb;
@@ -81,10 +82,10 @@ static void __inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
 	spin_unlock(&head->lock);
 }
 
-void inet_put_port(struct inet_hashinfo *hashinfo, struct sock *sk)
+void inet_put_port(struct sock *sk)
 {
 	local_bh_disable();
-	__inet_put_port(hashinfo, sk);
+	__inet_put_port(sk);
 	local_bh_enable();
 }
 
@@ -317,8 +318,9 @@ static inline u32 inet_sk_port_offset(const struct sock *sk)
 					  inet->dport);
 }
 
-void __inet_hash_nolisten(struct inet_hashinfo *hashinfo, struct sock *sk)
+void __inet_hash_nolisten(struct sock *sk)
 {
+	struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
 	struct hlist_head *list;
 	rwlock_t *lock;
 	struct inet_ehash_bucket *head;
@@ -337,13 +339,14 @@ void __inet_hash_nolisten(struct inet_hashinfo *hashinfo, struct sock *sk)
 }
 EXPORT_SYMBOL_GPL(__inet_hash_nolisten);
 
-void __inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
+static void __inet_hash(struct sock *sk)
 {
+	struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
 	struct hlist_head *list;
 	rwlock_t *lock;
 
 	if (sk->sk_state != TCP_LISTEN) {
-		__inet_hash_nolisten(hashinfo, sk);
+		__inet_hash_nolisten(sk);
 		return;
 	}
 
@@ -357,13 +360,48 @@ void __inet_hash(struct inet_hashinfo *hashinfo, struct sock *sk)
 	write_unlock(lock);
 	wake_up(&hashinfo->lhash_wait);
 }
-EXPORT_SYMBOL_GPL(__inet_hash);
+
+void inet_hash(struct sock *sk)
+{
+	if (sk->sk_state != TCP_CLOSE) {
+		local_bh_disable();
+		__inet_hash(sk);
+		local_bh_enable();
+	}
+}
+EXPORT_SYMBOL_GPL(inet_hash);
+
+void inet_unhash(struct sock *sk)
+{
+	rwlock_t *lock;
+	struct inet_hashinfo *hashinfo = sk->sk_prot->hashinfo;
+
+	if (sk_unhashed(sk))
+		goto out;
+
+	if (sk->sk_state == TCP_LISTEN) {
+		local_bh_disable();
+		inet_listen_wlock(hashinfo);
+		lock = &hashinfo->lhash_lock;
+	} else {
+		lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+		write_lock_bh(lock);
+	}
+
+	if (__sk_del_node_init(sk))
+		sock_prot_inuse_add(sk->sk_prot, -1);
+	write_unlock_bh(lock);
+out:
+	if (sk->sk_state == TCP_LISTEN)
+		wake_up(&hashinfo->lhash_wait);
+}
+EXPORT_SYMBOL_GPL(inet_unhash);
 
 int __inet_hash_connect(struct inet_timewait_death_row *death_row,
 		struct sock *sk,
 		int (*check_established)(struct inet_timewait_death_row *,
 			struct sock *, __u16, struct inet_timewait_sock **),
-		void (*hash)(struct inet_hashinfo *, struct sock *))
+		void (*hash)(struct sock *sk))
 {
 	struct inet_hashinfo *hinfo = death_row->hashinfo;
 	const unsigned short snum = inet_sk(sk)->num;
@@ -427,7 +465,7 @@ ok:
 		inet_bind_hash(sk, tb, port);
 		if (sk_unhashed(sk)) {
 			inet_sk(sk)->sport = htons(port);
-			hash(hinfo, sk);
+			hash(sk);
 		}
 		spin_unlock(&head->lock);
 
@@ -444,7 +482,7 @@ ok:
 	tb  = inet_csk(sk)->icsk_bind_hash;
 	spin_lock_bh(&head->lock);
 	if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
-		hash(hinfo, sk);
+		hash(sk);
 		spin_unlock_bh(&head->lock);
 		return 0;
 	} else {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a0d373b..071e83a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1669,7 +1669,7 @@ void tcp_set_state(struct sock *sk, int state)
 		sk->sk_prot->unhash(sk);
 		if (inet_csk(sk)->icsk_bind_hash &&
 		    !(sk->sk_userlocks & SOCK_BINDPORT_LOCK))
-			inet_put_port(&tcp_hashinfo, sk);
+			inet_put_port(sk);
 		/* fall through */
 	default:
 		if (oldstate==TCP_ESTABLISHED)
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 77c1939..63414ea 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -108,22 +108,6 @@ struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
 	.lhash_wait  = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
 };
 
-static int tcp_v4_get_port(struct sock *sk, unsigned short snum)
-{
-	return inet_csk_get_port(&tcp_hashinfo, sk, snum,
-				 inet_csk_bind_conflict);
-}
-
-static void tcp_v4_hash(struct sock *sk)
-{
-	inet_hash(&tcp_hashinfo, sk);
-}
-
-void tcp_unhash(struct sock *sk)
-{
-	inet_unhash(&tcp_hashinfo, sk);
-}
-
 static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb)
 {
 	return secure_tcp_sequence_number(ip_hdr(skb)->daddr,
@@ -1478,8 +1462,8 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
 	}
 #endif
 
-	__inet_hash_nolisten(&tcp_hashinfo, newsk);
-	__inet_inherit_port(&tcp_hashinfo, sk, newsk);
+	__inet_hash_nolisten(newsk);
+	__inet_inherit_port(sk, newsk);
 
 	return newsk;
 
@@ -1827,6 +1811,7 @@ struct inet_connection_sock_af_ops ipv4_specific = {
 	.getsockopt	   = ip_getsockopt,
 	.addr2sockaddr	   = inet_csk_addr2sockaddr,
 	.sockaddr_len	   = sizeof(struct sockaddr_in),
+	.bind_conflict	   = inet_csk_bind_conflict,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt = compat_ip_setsockopt,
 	.compat_getsockopt = compat_ip_getsockopt,
@@ -1926,7 +1911,7 @@ int tcp_v4_destroy_sock(struct sock *sk)
 
 	/* Clean up a referenced TCP bind bucket. */
 	if (inet_csk(sk)->icsk_bind_hash)
-		inet_put_port(&tcp_hashinfo, sk);
+		inet_put_port(sk);
 
 	/*
 	 * If sendmsg cached page exists, toss it.
@@ -2435,9 +2420,9 @@ struct proto tcp_prot = {
 	.getsockopt		= tcp_getsockopt,
 	.recvmsg		= tcp_recvmsg,
 	.backlog_rcv		= tcp_v4_do_rcv,
-	.hash			= tcp_v4_hash,
-	.unhash			= tcp_unhash,
-	.get_port		= tcp_v4_get_port,
+	.hash			= inet_hash,
+	.unhash			= inet_unhash,
+	.get_port		= inet_csk_get_port,
 	.enter_memory_pressure	= tcp_enter_memory_pressure,
 	.sockets_allocated	= &tcp_sockets_allocated,
 	.orphan_count		= &tcp_orphan_count,
@@ -2450,6 +2435,7 @@ struct proto tcp_prot = {
 	.obj_size		= sizeof(struct tcp_sock),
 	.twsk_prot		= &tcp_timewait_sock_ops,
 	.rsk_prot		= &tcp_request_sock_ops,
+	.hashinfo		= &tcp_hashinfo,
 #ifdef CONFIG_COMPAT
 	.compat_setsockopt	= compat_tcp_setsockopt,
 	.compat_getsockopt	= compat_tcp_getsockopt,
@@ -2467,7 +2453,6 @@ void __init tcp_v4_init(struct net_proto_family *ops)
 EXPORT_SYMBOL(ipv4_specific);
 EXPORT_SYMBOL(tcp_hashinfo);
 EXPORT_SYMBOL(tcp_prot);
-EXPORT_SYMBOL(tcp_unhash);
 EXPORT_SYMBOL(tcp_v4_conn_request);
 EXPORT_SYMBOL(tcp_v4_connect);
 EXPORT_SYMBOL(tcp_v4_do_rcv);