X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=net%2Fipv4%2Finet_connection_sock.c;h=ee16475f8fc33619eea9c9e247f06501e6aad45b;hb=a83d8e8d099fc373a5ca7112ad08c553bb2c180f;hp=274b0b846c25cd5fed68b91333a884933e8080e3;hpb=6b72977bd6c6fefc6497d4f0275079f539eaf0ac;p=safe%2Fjmp%2Flinux-2.6

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 274b0b8..ee16475 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -30,20 +30,40 @@ EXPORT_SYMBOL(inet_csk_timer_bug_msg);
 #endif
 
 /*
- * This array holds the first and last local port number.
- * For high-usage systems, use sysctl to change this to
- * 32768-61000
+ * This struct holds the first and last local port number.
  */
-int sysctl_local_port_range[2] = { 1024, 4999 };
+struct local_ports sysctl_local_ports __read_mostly = {
+	.lock = SEQLOCK_UNLOCKED,
+	.range = { 32768, 61000 },
+};
+
+void inet_get_local_port_range(int *low, int *high)
+{
+	unsigned seq;
+	do {
+		seq = read_seqbegin(&sysctl_local_ports.lock);
+
+		*low = sysctl_local_ports.range[0];
+		*high = sysctl_local_ports.range[1];
+	} while (read_seqretry(&sysctl_local_ports.lock, seq));
+}
+EXPORT_SYMBOL(inet_get_local_port_range);
 
 int inet_csk_bind_conflict(const struct sock *sk,
 			   const struct inet_bind_bucket *tb)
 {
-	const u32 sk_rcv_saddr = inet_rcv_saddr(sk);
+	const __be32 sk_rcv_saddr = inet_rcv_saddr(sk);
 	struct sock *sk2;
 	struct hlist_node *node;
 	int reuse = sk->sk_reuse;
 
+	/*
+	 * Unlike other sk lookup places we do not check
+	 * for sk_net here, since _all_ the socks listed
+	 * in tb->owners list belong to the same net - the
+	 * one this bucket belongs to.
+	 */
+
 	sk_for_each_bound(sk2, node, &tb->owners) {
 		if (sk != sk2 &&
 		    !inet_v6_ipv6only(sk2) &&
@@ -52,7 +72,7 @@ int inet_csk_bind_conflict(const struct sock *sk,
 		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
 			if (!reuse || !sk2->sk_reuse ||
 			    sk2->sk_state == TCP_LISTEN) {
-				const u32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
+				const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
 				if (!sk2_rcv_saddr || !sk_rcv_saddr ||
 				    sk2_rcv_saddr == sk_rcv_saddr)
 					break;
@@ -67,29 +87,46 @@ 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->h.hashinfo;
 	struct inet_bind_hashbucket *head;
 	struct hlist_node *node;
 	struct inet_bind_bucket *tb;
-	int ret;
+	int ret, attempts = 5;
+	struct net *net = sock_net(sk);
+	int smallest_size = -1, smallest_rover;
 
 	local_bh_disable();
 	if (!snum) {
-		int low = sysctl_local_port_range[0];
-		int high = sysctl_local_port_range[1];
-		int remaining = (high - low) + 1;
-		int rover = net_random() % (high - low) + low;
+		int remaining, rover, low, high;
+
+again:
+		inet_get_local_port_range(&low, &high);
+		remaining = (high - low) + 1;
+		smallest_rover = rover = net_random() % remaining + low;
 
+		smallest_size = -1;
 		do {
-			head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];
+			head = &hashinfo->bhash[inet_bhashfn(net, rover,
+					hashinfo->bhash_size)];
 			spin_lock(&head->lock);
 			inet_bind_bucket_for_each(tb, node, &head->chain)
-				if (tb->port == rover)
+				if (net_eq(ib_net(tb), net) && tb->port == rover) {
+					if (tb->fastreuse > 0 &&
+					    sk->sk_reuse &&
+					    sk->sk_state != TCP_LISTEN &&
+					    (tb->num_owners < smallest_size || smallest_size == -1)) {
+						smallest_size = tb->num_owners;
+						smallest_rover = rover;
+						if (atomic_read(&hashinfo->bsockets) > (high - low) + 1) {
+							spin_unlock(&head->lock);
+							snum = smallest_rover;
+							goto have_snum;
+						}
+					}
 					goto next;
+				}
 			break;
 		next:
 			spin_unlock(&head->lock);
@@ -104,38 +141,50 @@ int inet_csk_get_port(struct inet_hashinfo *hashinfo,
 		 * the top level, not from the 'break;' statement.
 		 */
 		ret = 1;
-		if (remaining <= 0)
+		if (remaining <= 0) {
+			if (smallest_size != -1) {
+				snum = smallest_rover;
+				goto have_snum;
+			}
 			goto fail;
-
+		}
 		/* OK, here is the one we will use.  HEAD is
 		 * non-NULL and we hold it's mutex.
 		 */
 		snum = rover;
 	} else {
-		head = &hashinfo->bhash[inet_bhashfn(snum, hashinfo->bhash_size)];
+have_snum:
+		head = &hashinfo->bhash[inet_bhashfn(net, snum,
+				hashinfo->bhash_size)];
 		spin_lock(&head->lock);
 		inet_bind_bucket_for_each(tb, node, &head->chain)
-			if (tb->port == snum)
+			if (net_eq(ib_net(tb), net) && tb->port == snum)
 				goto tb_found;
 	}
 	tb = NULL;
 	goto tb_not_found;
 tb_found:
 	if (!hlist_empty(&tb->owners)) {
-		if (sk->sk_reuse > 1)
-			goto success;
 		if (tb->fastreuse > 0 &&
-		    sk->sk_reuse && sk->sk_state != TCP_LISTEN) {
+		    sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+		    smallest_size == -1) {
 			goto success;
 		} else {
 			ret = 1;
-			if (bind_conflict(sk, tb))
+			if (inet_csk(sk)->icsk_af_ops->bind_conflict(sk, tb)) {
+				if (sk->sk_reuse && sk->sk_state != TCP_LISTEN &&
+				    smallest_size != -1 && --attempts >= 0) {
+					spin_unlock(&head->lock);
+					goto again;
+				}
 				goto fail_unlock;
+			}
 		}
 	}
 tb_not_found:
 	ret = 1;
-	if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep, head, snum)) == NULL)
+	if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep,
+					net, head, snum)) == NULL)
 		goto fail_unlock;
 	if (hlist_empty(&tb->owners)) {
 		if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
@@ -148,8 +197,8 @@ tb_not_found:
 success:
 	if (!inet_csk(sk)->icsk_bind_hash)
 		inet_bind_hash(sk, tb, snum);
-	BUG_TRAP(inet_csk(sk)->icsk_bind_hash == tb);
- 	ret = 0;
+	WARN_ON(inet_csk(sk)->icsk_bind_hash != tb);
+	ret = 0;
 
 fail_unlock:
 	spin_unlock(&head->lock);
@@ -241,7 +290,7 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
 	}
 
 	newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk);
-	BUG_TRAP(newsk->sk_state != TCP_SYN_RECV);
+	WARN_ON(newsk->sk_state == TCP_SYN_RECV);
 out:
 	release_sock(sk);
 	return newsk;
@@ -255,7 +304,7 @@ EXPORT_SYMBOL(inet_csk_accept);
 
 /*
  * Using different timers for retransmit, delayed acks and probes
- * We may wish use just one timer maintaining a list of expire jiffies 
+ * We may wish use just one timer maintaining a list of expire jiffies
  * to optimize.
  */
 void inet_csk_init_xmit_timers(struct sock *sk,
@@ -265,18 +314,11 @@ void inet_csk_init_xmit_timers(struct sock *sk,
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 
-	init_timer(&icsk->icsk_retransmit_timer);
-	init_timer(&icsk->icsk_delack_timer);
-	init_timer(&sk->sk_timer);
-
-	icsk->icsk_retransmit_timer.function = retransmit_handler;
-	icsk->icsk_delack_timer.function     = delack_handler;
-	sk->sk_timer.function		     = keepalive_handler;
-
-	icsk->icsk_retransmit_timer.data = 
-		icsk->icsk_delack_timer.data =
-			sk->sk_timer.data  = (unsigned long)sk;
-
+	setup_timer(&icsk->icsk_retransmit_timer, retransmit_handler,
+			(unsigned long)sk);
+	setup_timer(&icsk->icsk_delack_timer, delack_handler,
+			(unsigned long)sk);
+	setup_timer(&sk->sk_timer, keepalive_handler, (unsigned long)sk);
 	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
 }
 
@@ -309,13 +351,14 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
 
 EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
 
-struct dst_entry* inet_csk_route_req(struct sock *sk,
+struct dst_entry *inet_csk_route_req(struct sock *sk,
 				     const struct request_sock *req)
 {
 	struct rtable *rt;
 	const struct inet_request_sock *ireq = inet_rsk(req);
 	struct ip_options *opt = inet_rsk(req)->opt;
 	struct flowi fl = { .oif = sk->sk_bound_dev_if,
+			    .mark = sk->sk_mark,
 			    .nl_u = { .ip4_u =
 				      { .daddr = ((opt && opt->srr) ?
 						  opt->faddr :
@@ -323,27 +366,30 @@ struct dst_entry* inet_csk_route_req(struct sock *sk,
 					.saddr = ireq->loc_addr,
 					.tos = RT_CONN_FLAGS(sk) } },
 			    .proto = sk->sk_protocol,
+			    .flags = inet_sk_flowi_flags(sk),
 			    .uli_u = { .ports =
-				       { .sport = inet_sk(sk)->sport,
+				       { .sport = inet_sk(sk)->inet_sport,
 					 .dport = ireq->rmt_port } } };
+	struct net *net = sock_net(sk);
 
 	security_req_classify_flow(req, &fl);
-	if (ip_route_output_flow(&rt, &fl, sk, 0)) {
-		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
-		return NULL;
-	}
-	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) {
-		ip_rt_put(rt);
-		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
-		return NULL;
-	}
+	if (ip_route_output_flow(net, &rt, &fl, sk, 0))
+		goto no_route;
+	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
+		goto route_err;
 	return &rt->u.dst;
+
+route_err:
+	ip_rt_put(rt);
+no_route:
+	IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES);
+	return NULL;
 }
 
 EXPORT_SYMBOL_GPL(inet_csk_route_req);
 
 static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport,
-				 const u32 rnd, const u16 synq_hsize)
+				 const u32 rnd, const u32 synq_hsize)
 {
 	return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1);
 }
@@ -373,7 +419,7 @@ struct request_sock *inet_csk_search_req(const struct sock *sk,
 		    ireq->rmt_addr == raddr &&
 		    ireq->loc_addr == laddr &&
 		    AF_INET_FAMILY(req->rsk_ops->family)) {
-			BUG_TRAP(!req->sk);
+			WARN_ON(req->sk);
 			*prevp = prev;
 			break;
 		}
@@ -401,6 +447,28 @@ extern int sysctl_tcp_synack_retries;
 
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
+/* Decide when to expire the request and when to resend SYN-ACK */
+static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
+				  const int max_retries,
+				  const u8 rskq_defer_accept,
+				  int *expire, int *resend)
+{
+	if (!rskq_defer_accept) {
+		*expire = req->retrans >= thresh;
+		*resend = 1;
+		return;
+	}
+	*expire = req->retrans >= thresh &&
+		  (!inet_rsk(req)->acked || req->retrans >= max_retries);
+	/*
+	 * Do not resend while waiting for data after ACK,
+	 * start to resend on end of deferring period to give
+	 * last chance for data or ACK to create established socket.
+	 */
+	*resend = !inet_rsk(req)->acked ||
+		  req->retrans >= rskq_defer_accept - 1;
+}
+
 void inet_csk_reqsk_queue_prune(struct sock *parent,
 				const unsigned long interval,
 				const unsigned long timeout,
@@ -456,9 +524,15 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
 		reqp=&lopt->syn_table[i];
 		while ((req = *reqp) != NULL) {
 			if (time_after_eq(now, req->expires)) {
-				if ((req->retrans < thresh ||
-				     (inet_rsk(req)->acked && req->retrans < max_retries))
-				    && !req->rsk_ops->rtx_syn_ack(parent, req, NULL)) {
+				int expire = 0, resend = 0;
+
+				syn_ack_recalc(req, thresh, max_retries,
+					       queue->rskq_defer_accept,
+					       &expire, &resend);
+				if (!expire &&
+				    (!resend ||
+				     !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
+				     inet_rsk(req)->acked)) {
 					unsigned long timeo;
 
 					if (req->retrans++ == 0)
@@ -501,7 +575,9 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req,
 		newsk->sk_state = TCP_SYN_RECV;
 		newicsk->icsk_bind_hash = NULL;
 
-		inet_sk(newsk)->dport = inet_rsk(req)->rmt_port;
+		inet_sk(newsk)->inet_dport = inet_rsk(req)->rmt_port;
+		inet_sk(newsk)->inet_num = ntohs(inet_rsk(req)->loc_port);
+		inet_sk(newsk)->inet_sport = inet_rsk(req)->loc_port;
 		newsk->sk_write_space = sk_stream_write_space;
 
 		newicsk->icsk_retransmits = 0;
@@ -526,14 +602,14 @@ EXPORT_SYMBOL_GPL(inet_csk_clone);
  */
 void inet_csk_destroy_sock(struct sock *sk)
 {
-	BUG_TRAP(sk->sk_state == TCP_CLOSE);
-	BUG_TRAP(sock_flag(sk, SOCK_DEAD));
+	WARN_ON(sk->sk_state != TCP_CLOSE);
+	WARN_ON(!sock_flag(sk, SOCK_DEAD));
 
 	/* It cannot be in hash table! */
-	BUG_TRAP(sk_unhashed(sk));
+	WARN_ON(!sk_unhashed(sk));
 
-	/* If it has not 0 inet_sk(sk)->num, it must be bound */
-	BUG_TRAP(!inet_sk(sk)->num || inet_csk(sk)->icsk_bind_hash);
+	/* If it has not 0 inet_sk(sk)->inet_num, it must be bound */
+	WARN_ON(inet_sk(sk)->inet_num && !inet_csk(sk)->icsk_bind_hash);
 
 	sk->sk_prot->destroy(sk);
 
@@ -543,7 +619,7 @@ void inet_csk_destroy_sock(struct sock *sk)
 
 	sk_refcnt_debug_release(sk);
 
-	atomic_dec(sk->sk_prot->orphan_count);
+	percpu_counter_dec(sk->sk_prot->orphan_count);
 	sock_put(sk);
 }
 
@@ -568,8 +644,8 @@ int inet_csk_listen_start(struct sock *sk, const int nr_table_entries)
 	 * after validation is complete.
 	 */
 	sk->sk_state = TCP_LISTEN;
-	if (!sk->sk_prot->get_port(sk, inet->num)) {
-		inet->sport = htons(inet->num);
+	if (!sk->sk_prot->get_port(sk, inet->inet_num)) {
+		inet->inet_sport = htons(inet->inet_num);
 
 		sk_dst_reset(sk);
 		sk->sk_prot->hash(sk);
@@ -616,14 +692,14 @@ void inet_csk_listen_stop(struct sock *sk)
 
 		local_bh_disable();
 		bh_lock_sock(child);
-		BUG_TRAP(!sock_owned_by_user(child));
+		WARN_ON(sock_owned_by_user(child));
 		sock_hold(child);
 
 		sk->sk_prot->disconnect(child, O_NONBLOCK);
 
 		sock_orphan(child);
 
-		atomic_inc(sk->sk_prot->orphan_count);
+		percpu_counter_inc(sk->sk_prot->orphan_count);
 
 		inet_csk_destroy_sock(child);
 
@@ -634,7 +710,7 @@ void inet_csk_listen_stop(struct sock *sk)
 		sk_acceptq_removed(sk);
 		__reqsk_free(req);
 	}
-	BUG_TRAP(!sk->sk_ack_backlog);
+	WARN_ON(sk->sk_ack_backlog);
 }
 
 EXPORT_SYMBOL_GPL(inet_csk_listen_stop);
@@ -645,31 +721,12 @@ void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr)
 	const struct inet_sock *inet = inet_sk(sk);
 
 	sin->sin_family		= AF_INET;
-	sin->sin_addr.s_addr	= inet->daddr;
-	sin->sin_port		= inet->dport;
+	sin->sin_addr.s_addr	= inet->inet_daddr;
+	sin->sin_port		= inet->inet_dport;
 }
 
 EXPORT_SYMBOL_GPL(inet_csk_addr2sockaddr);
 
-int inet_csk_ctl_sock_create(struct socket **sock, unsigned short family,
-			     unsigned short type, unsigned char protocol)
-{
-	int rc = sock_create_kern(family, type, protocol, sock);
-
-	if (rc == 0) {
-		(*sock)->sk->sk_allocation = GFP_ATOMIC;
-		inet_sk((*sock)->sk)->uc_ttl = -1;
-		/*
-		 * Unhash it so that IP input processing does not even see it,
-		 * we do not wish this socket to see incoming packets.
-		 */
-		(*sock)->sk->sk_prot->unhash((*sock)->sk);
-	}
-	return rc;
-}
-
-EXPORT_SYMBOL_GPL(inet_csk_ctl_sock_create);
-
 #ifdef CONFIG_COMPAT
 int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 			       char __user *optval, int __user *optlen)
@@ -686,7 +743,7 @@ int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
 EXPORT_SYMBOL_GPL(inet_csk_compat_getsockopt);
 
 int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
-			       char __user *optval, int optlen)
+			       char __user *optval, unsigned int optlen)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);