path: root/net/ipv4/inet_connection_sock.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * 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
 */

#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>
#include <net/addrconf.h>

#if IS_ENABLED(CONFIG_IPV6)
/* match_sk*_wildcard == true:  IPV6_ADDR_ANY equals to any IPv6 addresses
 *				if IPv6 only, and any IPv4 addresses
 *				if not IPv6 only
 * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
 *				IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY,
 *				and 0.0.0.0 equals to 0.0.0.0 only
 */
static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6,
				 const struct in6_addr *sk2_rcv_saddr6,
				 __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
				 bool sk1_ipv6only, bool sk2_ipv6only,
				 bool match_sk1_wildcard,
				 bool match_sk2_wildcard)
{
	int addr_type = ipv6_addr_type(sk1_rcv_saddr6);
	int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED;

	/* if both are mapped, treat as IPv4 */
	if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) {
		if (!sk2_ipv6only) {
			if (sk1_rcv_saddr == sk2_rcv_saddr)
				return true;
			return (match_sk1_wildcard && !sk1_rcv_saddr) ||
				(match_sk2_wildcard && !sk2_rcv_saddr);
		}
		return false;
	}

	if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY)
		return true;

	if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard &&
	    !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED))
		return true;

	if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard &&
	    !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED))
		return true;

	if (sk2_rcv_saddr6 &&
	    ipv6_addr_equal(sk1_rcv_saddr6, sk2_rcv_saddr6))
		return true;

	return false;
}
#endif

/* match_sk*_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
 * match_sk*_wildcard == false: addresses must be exactly the same, i.e.
 *				0.0.0.0 only equals to 0.0.0.0
 */
static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr,
				 bool sk2_ipv6only, bool match_sk1_wildcard,
				 bool match_sk2_wildcard)
{
	if (!sk2_ipv6only) {
		if (sk1_rcv_saddr == sk2_rcv_saddr)
			return true;
		return (match_sk1_wildcard && !sk1_rcv_saddr) ||
			(match_sk2_wildcard && !sk2_rcv_saddr);
	}
	return false;
}

bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2,
			  bool match_wildcard)
{
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6)
		return ipv6_rcv_saddr_equal(&sk->sk_v6_rcv_saddr,
					    inet6_rcv_saddr(sk2),
					    sk->sk_rcv_saddr,
					    sk2->sk_rcv_saddr,
					    ipv6_only_sock(sk),
					    ipv6_only_sock(sk2),
					    match_wildcard,
					    match_wildcard);
#endif
	return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr,
				    ipv6_only_sock(sk2), match_wildcard,
				    match_wildcard);
}
EXPORT_SYMBOL(inet_rcv_saddr_equal);

bool inet_rcv_saddr_any(const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6)
		return ipv6_addr_any(&sk->sk_v6_rcv_saddr);
#endif
	return !sk->sk_rcv_saddr;
}

void inet_get_local_port_range(const 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);

void inet_sk_get_local_port_range(const struct sock *sk, int *low, int *high)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct net *net = sock_net(sk);
	int lo, hi, sk_lo, sk_hi;

	inet_get_local_port_range(net, &lo, &hi);

	sk_lo = inet->local_port_range.lo;
	sk_hi = inet->local_port_range.hi;

	if (unlikely(lo <= sk_lo && sk_lo <= hi))
		lo = sk_lo;
	if (unlikely(lo <= sk_hi && sk_hi <= hi))
		hi = sk_hi;

	*low = lo;
	*high = hi;
}
EXPORT_SYMBOL(inet_sk_get_local_port_range);

static bool inet_use_bhash2_on_bind(const struct sock *sk)
{
#if IS_ENABLED(CONFIG_IPV6)
	if (sk->sk_family == AF_INET6) {
		int addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr);

		return addr_type != IPV6_ADDR_ANY &&
			addr_type != IPV6_ADDR_MAPPED;
	}
#endif
	return sk->sk_rcv_saddr != htonl(INADDR_ANY);
}

static bool inet_bind_conflict(const struct sock *sk, struct sock *sk2,
			       kuid_t sk_uid, bool relax,
			       bool reuseport_cb_ok, bool reuseport_ok)
{
	int bound_dev_if2;

	if (sk == sk2)
		return false;

	bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if);

	if (!sk->sk_bound_dev_if || !bound_dev_if2 ||
	    sk->sk_bound_dev_if == bound_dev_if2) {
		if (sk->sk_reuse && sk2->sk_reuse &&
		    sk2->sk_state != TCP_LISTEN) {
			if (!relax || (!reuseport_ok && sk->sk_reuseport &&
				       sk2->sk_reuseport && reuseport_cb_ok &&
				       (sk2->sk_state == TCP_TIME_WAIT ||
					uid_eq(sk_uid, sock_i_uid(sk2)))))
				return true;
		} else if (!reuseport_ok || !sk->sk_reuseport ||
			   !sk2->sk_reuseport || !reuseport_cb_ok ||
			   (sk2->sk_state != TCP_TIME_WAIT &&
			    !uid_eq(sk_uid, sock_i_uid(sk2)))) {
			return true;
		}
	}
	return false;
}

static bool __inet_bhash2_conflict(const struct sock *sk, struct sock *sk2,
				   kuid_t sk_uid, bool relax,
				   bool reuseport_cb_ok, bool reuseport_ok)
{
	if (sk->sk_family == AF_INET && ipv6_only_sock(sk2))
		return false;

	return inet_bind_conflict(sk, sk2, sk_uid, relax,
				  reuseport_cb_ok, reuseport_ok);
}

static bool inet_bhash2_conflict(const struct sock *sk,
				 const struct inet_bind2_bucket *tb2,
				 kuid_t sk_uid,
				 bool relax, bool reuseport_cb_ok,
				 bool reuseport_ok)
{
	struct inet_timewait_sock *tw2;
	struct sock *sk2;

	sk_for_each_bound_bhash2(sk2, &tb2->owners) {
		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
					   reuseport_cb_ok, reuseport_ok))
			return true;
	}

	twsk_for_each_bound_bhash2(tw2, &tb2->deathrow) {
		sk2 = (struct sock *)tw2;

		if (__inet_bhash2_conflict(sk, sk2, sk_uid, relax,
					   reuseport_cb_ok, reuseport_ok))
			return true;
	}

	return false;
}

/* This should be called only when the tb and tb2 hashbuckets' locks are held */
static int inet_csk_bind_conflict(const struct sock *sk,
				  const struct inet_bind_bucket *tb,
				  const struct inet_bind2_bucket *tb2, /* may be null */
				  bool relax, bool reuseport_ok)
{
	bool reuseport_cb_ok;
	struct sock_reuseport *reuseport_cb;
	kuid_t uid = sock_i_uid((struct sock *)sk);

	rcu_read_lock();
	reuseport_cb = rcu_dereference(sk->sk_reuseport_cb);
	/* paired with WRITE_ONCE() in __reuseport_(add|detach)_closed_sock */
	reuseport_cb_ok = !reuseport_cb || READ_ONCE(reuseport_cb->num_closed_socks);
	rcu_read_unlock();

	/*
	 * Unlike other sk lookup places we do not check
	 * for sk_net here, since _all_ the socks listed
	 * in tb->owners and tb2->owners list belong
	 * to the same net -