path: root/net/ipv4/inet_connection_sock.c

/*
 * 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/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>
#include <net/xfrm.h>
#include <net/tcp.h>
#include <net/sock_reuseport.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

void inet_get_local_port_range(struct net *net, int *low, int *high)
{
	unsigned int seq;

	do {
		seq = read_seqbegin(&net->ipv4.ip_local_ports.lock);

		*low = net->ipv4.ip_local_ports.range[0];
		*high = net->ipv4.ip_local_ports.range[1];
	} while (read_seqretry(&net->ipv4.ip_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, bool relax)
{
	struct sock *sk2;
	int reuse = sk->sk_reuse;
	int reuseport = sk->sk_reuseport;
	kuid_t uid = sock_i_uid((struct sock *)sk);

	/*
	 * 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, &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) &&
			    (!reuseport || !sk2->sk_reuseport ||
			     rcu_access_pointer(sk->sk_reuseport_cb) ||
			     (sk2->sk_state != TCP_TIME_WAIT &&
			     !uid_eq(uid, sock_i_uid(sk2))))) {

				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
					break;
			}
			if (!relax && reuse && sk2->sk_reuse &&
			    sk2->sk_state != TCP_LISTEN) {

				if (!sk2->sk_rcv_saddr || !sk->sk_rcv_saddr ||
				    sk2->sk_rcv_saddr == sk->sk_rcv_saddr)
					break;
			}
		}
	}
	return sk2 != NULL;
}
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.
 * We try to allocate an odd port (and leave even ports for connect())
 */
int inet_csk_get_port(struct sock *sk, unsigned short snum)
{
	bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN;
	struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo;
	int ret = 1, attempts = 5, port = snum;
	int smallest_size = -1, smallest_port;
	struct inet_bind_hashbucket *head;
	struct net *net = sock_net(sk);
	int i, low, high, attempt_half;
	struct inet_bind_bucket *tb;
	kuid_t uid = sock_i_uid(sk);
	u32 remaining, offset;

	if (port) {
have_port:
		head = &hinfo->bhash[inet_bhashfn(net, port,
						  hinfo->bhash_size)];
		spin_lock_bh(&head->lock);
		inet_bind_bucket_for_each(tb, &head->chain)
			if (net_eq(ib_net(tb), net) && tb->port == port)
				goto tb_found;

		goto tb_not_found;
	}
again:
	attempt_half = (sk->sk_reuse == SK_CAN_REUSE) ? 1 : 0;
other_half_scan:
	inet_get_local_port_range(net, &low, &high);
	high++; /* [32768, 60999] -> [32768, 61000[ */
	if (high - low < 4)
		attempt_half = 0;
	if (attempt_half) {
		int half = low + (((high - low) >> 2) << 1);

		if (attempt_half == 1)
			high = half;
		else
			low = half;
	}
	remaining = high - low;
	if (likely(remaining > 1))
		remaining &= ~1U;

	offset = prandom_u32() % remaining;
	/* __inet_hash_connect() favors ports having @low parity
	 * We do the opposite to not pollute connect() users.
	 */
	offset |= 1U;
	smallest_size = -1;
	smallest_port = low; /* avoid compiler warning */

other_parity_scan:
	port = low + offset;
	for (i = 0; i < remaining; i += 2, port += 2) {
		if (unlikely(port >= high))
			port -= remaining;
		if (inet_is_local_reserved_port(net, port))
			continue;
		head = &hinfo->bhash[inet_bhashfn(net, port,
						  hinfo->bhash_size)];
		spin_lock_bh(&head->lock);
		inet_bind_bucket_for_each(tb, &head->chain)
			if (net_eq(ib_net(tb), net) && tb->port == port) {
				if (((tb->fastreuse > 0 && reuse) ||
				     (tb->fastreuseport > 0 &&
				      sk->sk_reuseport &&
				      !rcu_access_pointer(sk->sk_reuseport_cb) &&
				      uid_eq(tb->fastuid, uid))) &&
				    (tb->num_owners < smallest_size || smallest_size == -1)) {
					smallest_size = tb->num_owners;
					smallest_port =