path: root/net/ipv6/udp.c

/*
 *	UDP over IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	Based on linux/ipv4/udp.c
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 *      Kazunori MIYAZAWA @USAGI:       change process style to use ip6_append_data
 *      YOSHIFUJI Hideaki @USAGI:	convert /proc/net/udp6 to seq_file.
 *
 *	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/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/slab.h>
#include <asm/uaccess.h>

#include <net/addrconf.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/raw.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/xfrm.h>
#include <net/inet6_hashtables.h>
#include <net/busy_poll.h>
#include <net/sock_reuseport.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <trace/events/skb.h>
#include "udp_impl.h"

static u32 udp6_ehashfn(const struct net *net,
			const struct in6_addr *laddr,
			const u16 lport,
			const struct in6_addr *faddr,
			const __be16 fport)
{
	static u32 udp6_ehash_secret __read_mostly;
	static u32 udp_ipv6_hash_secret __read_mostly;

	u32 lhash, fhash;

	net_get_random_once(&udp6_ehash_secret,
			    sizeof(udp6_ehash_secret));
	net_get_random_once(&udp_ipv6_hash_secret,
			    sizeof(udp_ipv6_hash_secret));

	lhash = (__force u32)laddr->s6_addr32[3];
	fhash = __ipv6_addr_jhash(faddr, udp_ipv6_hash_secret);

	return __inet6_ehashfn(lhash, lport, fhash, fport,
			       udp_ipv6_hash_secret + net_hash_mix(net));
}

static u32 udp6_portaddr_hash(const struct net *net,
			      const struct in6_addr *addr6,
			      unsigned int port)
{
	unsigned int hash, mix = net_hash_mix(net);

	if (ipv6_addr_any(addr6))
		hash = jhash_1word(0, mix);
	else if (ipv6_addr_v4mapped(addr6))
		hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix);
	else
		hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix);

	return hash ^ port;
}

int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
	unsigned int hash2_nulladdr =
		udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
	unsigned int hash2_partial =
		udp6_portaddr_hash(sock_net(sk), &sk->sk_v6_rcv_saddr, 0);

	/* precompute partial secondary hash */
	udp_sk(sk)->udp_portaddr_hash = hash2_partial;
	return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
}

static void udp_v6_rehash(struct sock *sk)
{
	u16 new_hash = udp6_portaddr_hash(sock_net(sk),
					  &sk->sk_v6_rcv_saddr,
					  inet_sk(sk)->inet_num);

	udp_lib_rehash(sk, new_hash);
}

static int compute_score(struct sock *sk, struct net *net,
			 const struct in6_addr *saddr, __be16 sport,
			 const struct in6_addr *daddr, unsigned short hnum,
			 int dif)
{
	int score;
	struct inet_sock *inet;

	if (!net_eq(sock_net(sk), net) ||
	    udp_sk(sk)->udp_port_hash != hnum ||
	    sk->sk_family != PF_INET6)
		return -1;

	score = 0;
	inet = inet_sk(sk);

	if (inet->inet_dport) {
		if (inet->inet_dport != sport)
			return -1;
		score++;
	}

	if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
		if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
			return -1;
		score++;
	}

	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
			return -1;
		score++;
	}

	if (sk->sk_bound_dev_if) {
		if (sk->sk_bound_dev_if != dif)
			return -1;
		score++;
	}

	if (sk->sk_incoming_cpu == raw_smp_processor_id())
		score++;

	return score;
}

/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(struct net *net,
		const struct in6_addr *saddr, __be16 sport,
		const struct in6_addr *daddr, unsigned int hnum, int dif,
		struct udp_hslot *hslot2,
		struct sk_buff *skb)
{
	struct sock *sk, *result;
	int score, badness, matches = 0, reuseport = 0;
	u32 hash = 0;

	result = NULL;
	badness = -1;
	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
		score = compute_score(sk, net, saddr, sport,
				      daddr, hnum, dif);
		if (score > badness) {
			reuseport = sk->sk_reuseport;
			if (reuseport) {
				hash = udp6_ehashfn(net, daddr, hnum,
						    saddr, sport);

				result = reuseport_select_sock(sk, hash, skb,
							sizeof(struct udphdr));
				if (result)
					return result;
				matches = 1;
			}
			result = sk;
			badness = score;
		} else if (score == badness && reuseport) {
			matches++;
			if (reciprocal_scale(hash, matches) == 0)
				result = sk;
			hash = next_pseudo_random32(hash);
		}
	}
	return result;
}

/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(struct net *net,
				      const struct in6_addr *saddr, __be16 sport,
				      const struct in6_addr *daddr, __be16 dport,
				      int dif, struct udp_table *udptable,
				      struct sk_buff *skb)
{
	struct sock *sk, *result;
	unsigned short hnum = ntohs(dport);
	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
	int score, badness, matches = 0, reuseport = 0;
	u32 hash = 0;

	if (hslot->count > 10) {
		hash2 = udp6_portaddr_hash(net, daddr, hnum);
		slot2 = hash2 & udptable->mask;
		hslot2 = &udptable->hash2[slot2];
		if (hslot->count < hslot2->count)
			goto begin;

		result = udp6_lib_lookup2(net, saddr, sport,
					  daddr, hnum, dif,
					  hslot2, skb);
		if (!result) {
			unsigned int old_slot2 = slot2;
			hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum);
			slot2 = hash2 & udptable->mask;
			/* avoid searching the same slot again. */
			if (unlikely(slot2 == old_slot2))
				return result;

			hslot2 = &udptable->hash2[slot2];
			if (hslot->count < hslot2->count)
				goto begin;

			result = udp6_lib_lookup2(net, saddr, sport,
						  daddr, hnum, dif,
						  hslot2, skb);
		}
		return result;
	}
begin:
	result = NULL;
	badness = -1;
	sk_for_each_rcu(sk, &hslot->head) {
		score = compute_score(sk, net, saddr, sport, daddr, hnum, dif);
		if (score > badness) {
			reuseport = sk->sk_reuseport;
			if (reuseport) {
				hash = udp6_ehashfn(net, daddr, hnum,
						    saddr, sport);
				result = reuseport_select_sock(sk, hash, skb,
							sizeof(struct udphdr));
				if (result)
					return result;
				matches = 1;
			}
			result = sk;
			badness = score;
		} else if (score == badness && reuseport) {
			matches++;
			if (reciprocal_scale(hash, matches) == 0)
				result = sk;
			hash = next_pseudo_random32(hash);
		}
	}
	return result;
}
EXPORT_SYMBOL_GPL(__udp6_lib_lookup);

static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb,
					  __be16 sport, __be16 dport,
					  struct udp_table *udptable)
{
	const struct ipv6hdr *iph = ipv6_hdr(skb);
	struct sock *sk;

	sk = skb_steal_sock(skb);
	if (unlikely(sk))
		return sk;
	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
				 &iph->daddr, dport, inet6_iif(skb),
				 udptable, skb);
}

struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
				 __be16 sport, __be16 dport)
{
	const struct ipv6hdr *iph = ipv6_hdr(skb);

	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
				 &iph->daddr, dport, inet6_iif(skb),
				 &udp_table, skb);
}
EXPORT_SYMBOL_GPL(udp6_lib_lookup_skb);

/* Must be called under rcu_read_lock().
 * Does increment socket refcount.
 */
#if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
    IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport,
			     const struct in6_addr *daddr, __be16 dport, int dif)
{
	struct sock *sk;

	sk =  __udp6_lib_lookup(net, saddr, sport, daddr, dport,
				dif, &udp_table, NULL);
	if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
		sk = NULL;
	return sk;
}
EXPORT_SYMBOL_GP