1 files changed, 401 insertions, 0 deletions

diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
new file mode 100644
index 000000000000..2712400a8bb8
--- /dev/null
+++ b/net/ipv4/inet_connection_sock.c
@@ -0,0 +1,401 @@
+/*
+ * INET		An implementation of the TCP/IP protocol suite for the LINUX
+ *		operating system.  INET is implemented using the  BSD Socket
+ *		interface as the means of communication with the user level.
+ *
+ *		Support for INET connection oriented protocols.
+ *
+ * Authors:	See the TCP sources
+ *
+ *		This program is free software; you can redistribute it and/or
+ *		modify it under the terms of the GNU General Public License
+ *		as published by the Free Software Foundation; either version
+ *		2 of the License, or(at your option) any later version.
+ */
+
+#include <linux/config.h>
+#include <linux/module.h>
+#include <linux/jhash.h>
+
+#include <net/inet_connection_sock.h>
+#include <net/inet_hashtables.h>
+#include <net/inet_timewait_sock.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/tcp_states.h>
+
+#ifdef INET_CSK_DEBUG
+const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n";
+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
+ */
+int sysctl_local_port_range[2] = { 1024, 4999 };
+
+static inline int inet_csk_bind_conflict(struct sock *sk, struct inet_bind_bucket *tb)
+{
+	const u32 sk_rcv_saddr = inet_rcv_saddr(sk);
+	struct sock *sk2;
+	struct hlist_node *node;
+	int reuse = sk->sk_reuse;
+
+	sk_for_each_bound(sk2, node, &tb->owners) {
+		if (sk != sk2 &&
+		    !inet_v6_ipv6only(sk2) &&
+		    (!sk->sk_bound_dev_if ||
+		     !sk2->sk_bound_dev_if ||
+		     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);
+				if (!sk2_rcv_saddr || !sk_rcv_saddr ||
+				    sk2_rcv_saddr == sk_rcv_saddr)
+					break;
+			}
+		}
+	}
+	return node != NULL;
+}
+
+/* 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)
+{
+	struct inet_bind_hashbucket *head;
+	struct hlist_node *node;
+	struct inet_bind_bucket *tb;
+	int ret;
+
+	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;
+
+		spin_lock(&hashinfo->portalloc_lock);
+		if (hashinfo->port_rover < low)
+			rover = low;
+		else
+			rover = hashinfo->port_rover;
+		do {
+			rover++;
+			if (rover > high)
+				rover = low;
+			head = &hashinfo->bhash[inet_bhashfn(rover, hashinfo->bhash_size)];
+			spin_lock(&head->lock);
+			inet_bind_bucket_for_each(tb, node, &head->chain)
+				if (tb->port == rover)
+					goto next;
+			break;
+		next:
+			spin_unlock(&head->lock);
+		} while (--remaining > 0);
+		hashinfo->port_rover = rover;
+		spin_unlock(&hashinfo->portalloc_lock);
+
+		/* Exhausted local port range during search?  It is not
+		 * possible for us to be holding one of the bind hash
+		 * locks if this test triggers, because if 'remaining'
+		 * drops to zero, we broke out of the do/while loop at
+		 * the top level, not from the 'break;' statement.
+		 */
+		ret = 1;
+		if (remaining <= 0)
+			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)];
+		spin_lock(&head->lock);
+		inet_bind_bucket_for_each(tb, node, &head->chain)
+			if (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) {
+			goto success;
+		} else {
+			ret = 1;
+			if (inet_csk_bind_conflict(sk, tb))
+				goto fail_unlock;
+		}
+	}
+tb_not_found:
+	ret = 1;
+	if (!tb && (tb = inet_bind_bucket_create(hashinfo->bind_bucket_cachep, head, snum)) == NULL)
+		goto fail_unlock;
+	if (hlist_empty(&tb->owners)) {
+		if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
+			tb->fastreuse = 1;
+		else
+			tb->fastreuse = 0;
+	} else if (tb->fastreuse &&
+		   (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
+		tb->fastreuse = 0;
+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;
+
+fail_unlock:
+	spin_unlock(&head->lock);
+fail:
+	local_bh_enable();
+	return ret;
+}
+
+EXPORT_SYMBOL_GPL(inet_csk_get_port);
+
+/*
+ * Wait for an incoming connection, avoid race conditions. This must be called
+ * with the socket locked.
+ */
+static int inet_csk_wait_for_connect(struct sock *sk, long timeo)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	DEFINE_WAIT(wait);
+	int err;
+
+	/*
+	 * True wake-one mechanism for incoming connections: only
+	 * one process gets woken up, not the 'whole herd'.
+	 * Since we do not 'race & poll' for established sockets
+	 * anymore, the common case will execute the loop only once.
+	 *
+	 * Subtle issue: "add_wait_queue_exclusive()" will be added
+	 * after any current non-exclusive waiters, and we know that
+	 * it will always _stay_ after any new non-exclusive waiters
+	 * because all non-exclusive waiters are added at the
+	 * beginning of the wait-queue. As such, it's ok to "drop"
+	 * our exclusiveness temporarily when we get woken up without
+	 * having to remove and re-insert us on the wait queue.
+	 */
+	for (;;) {
+		prepare_to_wait_exclusive(sk->sk_sleep, &wait,
+					  TASK_INTERRUPTIBLE);
+		release_sock(sk);
+		if (reqsk_queue_empty(&icsk->icsk_accept_queue))
+			timeo = schedule_timeout(timeo);
+		lock_sock(sk);
+		err = 0;
+		if (!reqsk_queue_empty(&icsk->icsk_accept_queue))
+			break;
+		err = -EINVAL;
+		if (sk->sk_state != TCP_LISTEN)
+			break;
+		err = sock_intr_errno(timeo);
+		if (signal_pending(current))
+			break;
+		err = -EAGAIN;
+		if (!timeo)
+			break;
+	}
+	finish_wait(sk->sk_sleep, &wait);
+	return err;
+}
+
+/*
+ * This will accept the next outstanding connection.
+ */
+struct sock *inet_csk_accept(struct sock *sk, int flags, int *err)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct sock *newsk;
+	int error;
+
+	lock_sock(sk);
+
+	/* We need to make sure that this socket is listening,
+	 * and that it has something pending.
+	 */
+	error = -EINVAL;
+	if (sk->sk_state != TCP_LISTEN)
+		goto out_err;
+
+	/* Find already established connection */
+	if (reqsk_queue_empty(&icsk->icsk_accept_queue)) {
+		long timeo = sock_rcvtimeo(sk, flags & O_NONBLOCK);
+
+		/* If this is a non blocking socket don't sleep */
+		error = -EAGAIN;
+		if (!timeo)
+			goto out_err;
+
+		error = inet_csk_wait_for_connect(sk, timeo);
+		if (error)
+			goto out_err;
+	}
+
+	newsk = reqsk_queue_get_child(&icsk->icsk_accept_queue, sk);
+	BUG_TRAP(newsk->sk_state != TCP_SYN_RECV);
+out:
+	release_sock(sk);
+	return newsk;
+out_err:
+	newsk = NULL;
+	*err = error;
+	goto out;
+}
+
+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 
+ * to optimize.
+ */
+void inet_csk_init_xmit_timers(struct sock *sk,
+			       void (*retransmit_handler)(unsigned long),
+			       void (*delack_handler)(unsigned long),
+			       void (*keepalive_handler)(unsigned long))
+{
+	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;
+
+	icsk->icsk_pending = icsk->icsk_ack.pending = 0;
+}
+
+EXPORT_SYMBOL(inet_csk_init_xmit_timers);
+
+void inet_csk_clear_xmit_timers(struct sock *sk)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+
+	icsk->icsk_pending = icsk->icsk_ack.pending = icsk->icsk_ack.blocked = 0;
+
+	sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
+	sk_stop_timer(sk, &icsk->icsk_delack_timer);
+	sk_stop_timer(sk, &sk->sk_timer);
+}
+
+EXPORT_SYMBOL(inet_csk_clear_xmit_timers);
+
+void inet_csk_delete_keepalive_timer(struct sock *sk)
+{
+	sk_stop_timer(sk, &sk->sk_timer);
+}
+
+EXPORT_SYMBOL(inet_csk_delete_keepalive_timer);
+
+void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len)
+{
+	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
+}
+
+EXPORT_SYMBOL(inet_csk_reset_keepalive_timer);
+
+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,
+			    .nl_u = { .ip4_u =
+				      { .daddr = ((opt && opt->srr) ?
+						  opt->faddr :
+						  ireq->rmt_addr),
+					.saddr = ireq->loc_addr,
+					.tos = RT_CONN_FLAGS(sk) } },
+			    .proto = sk->sk_protocol,
+			    .uli_u = { .ports =
+				       { .sport = inet_sk(sk)->sport,
+					 .dport = ireq->rmt_port } } };
+
+	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;
+	}
+	return &rt->u.dst;
+}
+
+EXPORT_SYMBOL_GPL(inet_csk_route_req);
+
+static inline u32 inet_synq_hash(const u32 raddr, const u16 rport,
+				 const u32 rnd, const u16 synq_hsize)
+{
+	return jhash_2words(raddr, (u32)rport, rnd) & (synq_hsize - 1);
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+#define AF_INET_FAMILY(fam) ((fam) == AF_INET)
+#else
+#define AF_INET_FAMILY(fam) 1
+#endif
+
+struct request_sock *inet_csk_search_req(const struct sock *sk,
+					 struct request_sock ***prevp,
+					 const __u16 rport, const __u32 raddr,
+					 const __u32 laddr)
+{
+	const struct inet_connection_sock *icsk = inet_csk(sk);
+	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
+	struct request_sock *req, **prev;
+
+	for (prev = &lopt->syn_table[inet_synq_hash(raddr, rport, lopt->hash_rnd,
+						    lopt->nr_table_entries)];
+	     (req = *prev) != NULL;
+	     prev = &req->dl_next) {
+		const struct inet_request_sock *ireq = inet_rsk(req);
+
+		if (ireq->rmt_port == rport &&
+		    ireq->rmt_addr == raddr &&
+		    ireq->loc_addr == laddr &&
+		    AF_INET_FAMILY(req->rsk_ops->family)) {
+			BUG_TRAP(!req->sk);
+			*prevp = prev;
+			break;
+		}
+	}
+
+	return req;
+}
+
+EXPORT_SYMBOL_GPL(inet_csk_search_req);
+
+void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
+				   const unsigned timeout)
+{
+	struct inet_connection_sock *icsk = inet_csk(sk);
+	struct listen_sock *lopt = icsk->icsk_accept_queue.listen_opt;
+	const u32 h = inet_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port,
+				     lopt->hash_rnd, lopt->nr_table_entries);
+
+	reqsk_queue_hash_req(&icsk->icsk_accept_queue, h, req, timeout);
+	inet_csk_reqsk_queue_added(sk, timeout);
+}
+
+EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);