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

#include <linux/bpf-cgroup.h>
#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 <linux/uaccess.h>
#include <linux/indirect_call_wrapper.h>
#include <trace/events/udp.h>

#include <net/addrconf.h>
#include <net/aligned_data.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/seg6.h>
#include <net/tcp_states.h>
#include <net/ip6_checksum.h>
#include <net/ip6_tunnel.h>
#include <net/udp_tunnel.h>
#include <net/xfrm.h>
#include <net/inet_hashtables.h>
#include <net/inet6_hashtables.h>
#include <net/busy_poll.h>
#include <net/sock_reuseport.h>
#include <net/gro.h>

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

static void udpv6_destruct_sock(struct sock *sk)
{
	udp_destruct_common(sk);
	inet6_sock_destruct(sk);
}

static int udpv6_init_sock(struct sock *sk)
{
	int res = udp_lib_init_sock(sk);

	sk->sk_destruct = udpv6_destruct_sock;
	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
	return res;
}

INDIRECT_CALLABLE_SCOPE
u32 udp6_ehashfn(const struct net *net,
		 const struct in6_addr *laddr,
		 const u16 lport,
		 const struct in6_addr *faddr,
		 const __be16 fport)
{
	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,
			       udp6_ehash_secret + net_hash_mix(net));
}

static int udp_v6_get_port(struct sock *sk, unsigned short snum)
{
	unsigned int hash2_nulladdr =
		ipv6_portaddr_hash(sock_net(sk), &in6addr_any, snum);
	unsigned int hash2_partial =
		ipv6_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, hash2_nulladdr);
}

static void udp_v6_rehash(struct sock *sk)
{
	u16 new_hash = ipv6_portaddr_hash(sock_net(sk),
					  &sk->sk_v6_rcv_saddr,
					  inet_sk(sk)->inet_num);
	u16 new_hash4;

	if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) {
		new_hash4 = udp_ehashfn(sock_net(sk),
					sk->sk_rcv_saddr, sk->sk_num,
					sk->sk_daddr, sk->sk_dport);
	} else {
		new_hash4 = udp6_ehashfn(sock_net(sk),
					 &sk->sk_v6_rcv_saddr, sk->sk_num,
					 &sk->sk_v6_daddr, sk->sk_dport);
	}

	udp_lib_rehash(sk, new_hash, new_hash4);
}

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

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

	if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr))
		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_daddr)) {
		if (!ipv6_addr_equal(&sk->sk_v6_daddr, saddr))
			return -1;
		score++;
	}

	bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
	dev_match = udp_sk_bound_dev_eq(net, bound_dev_if, dif, sdif);
	if (!dev_match)
		return -1;
	if (bound_dev_if)
		score++;

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

	return score;
}

/**
 * udp6_lib_lookup1() - Simplified lookup using primary hash (destination port)
 * @net:	Network namespace
 * @saddr:	Source address, network order
 * @sport:	Source port, network order
 * @daddr:	Destination address, network order
 * @hnum:	Destination port, host order
 * @dif:	Destination interface index
 * @sdif:	Destination bridge port index, if relevant
 * @udptable:	Set of UDP hash tables
 *
 * Simplified lookup to be used as fallback if no sockets are found due to a
 * potential race between (receive) address change, and lookup happening before
 * the rehash operation. This function ignores SO_REUSEPORT groups while scoring
 * result sockets, because if we have one, we don't need the fallback at all.
 *
 * Called under rcu_read_lock().
 *
 * Return: socket with highest matching score if any, NULL if none
 */
static struct sock *udp6_lib_lookup1(const struct net *net,
				     const struct in6_addr *saddr, __be16 sport,
				     const struct in6_addr *daddr,
				     unsigned int hnum, int dif, int sdif,
				     const struct udp_table *udptable)
{
	unsigned int slot = udp_hashfn(net, hnum, udptable->mask);
	struct udp_hslot *hslot = &udptable->hash[slot];
	struct sock *sk, *result = NULL;
	int score, badness = 0;

	sk_for_each_rcu(sk, &hslot->head) {
		score = compute_score(sk, net,
				      saddr, sport, daddr, hnum, dif, sdif);
		if (score > badness) {
			result = sk;
			badness = score;
		}
	}

	return result;
}

/* called with rcu_read_lock() */
static struct sock *udp6_lib_lookup2(const struct net *net,
		const struct in6_addr *saddr, __be16 sport,
		const struct in6_addr *daddr, unsigned int hnum,
		int dif, int sdif, struct udp_hslot *hslot2,
		struct sk_buff *skb)
{
	struct sock *sk, *result;
	int score, badness;
	bool need_rescore;

	result = NULL;
	badness = -1;
	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
		need_rescore = false;
rescore:
		score = compute_score(need_rescore ? result : sk, net, saddr,
				      sport, daddr, hnum, dif, sdif);
		if (score > badness) {
			badness = score;

			if (need_rescore)
				continue;

			if (sk->sk_state == TCP_ESTABLISHED) {
				result = sk;
				continue;
			}

			result = inet6_lookup_reuseport(net, sk, skb, sizeof(struct udphdr),
							saddr, sport, daddr, hnum, udp6_ehashfn);
			if (!result) {
				result = sk;
				continue;
			}

			/* Fall back to scoring if group has connections */
			if (!reuseport_has_conns(sk))
				return result;

			/* Reuseport logic returned an error, keep original score. */
			if (IS_ERR(result))
				continue;

			/* compute_score is too long of a function to be
			 * inlined twice here, and calling it uninlined
			 * here yields measurable overhead for some
			 * workloads. Work around it by jumping
			 * backwards to rescore 'result'.
			 */
			need_rescore = true;
			goto rescore;
		}
	}
	return result;
}

#if IS_ENABLED(CONFIG_BASE_SMALL)
static struct sock *udp6_lib_lookup4(const struct net *net,
				     const struct in6_addr *saddr, __be16 sport,
				     const struct in6_addr *daddr,
				     unsigned int hnum, int dif, int sdif,
				     struct udp_table *udptable)
{
	return NULL;
}

static void udp6_hash4(struct sock *sk)
{
}
#else /* !CONFIG_BASE_SMALL */
static struct sock *udp6_lib_lookup4(const struct net *net,
				     const struct in6_addr *saddr, __be16 sport,
				     const struct in6_addr *daddr,
				     unsigned int hnum, int dif, int sdif,
				     struct udp_table *udptable)
{
	const __portpair ports = INET_COMBINED_PORTS(sport, hnum);
	const struct hlist_nulls_node *node;
	struct udp_hslot *hslot4;
	unsigned int hash4, slot;
	struct udp_sock *up;
	struct sock *sk;

	hash4 = udp6_ehashfn(net, daddr, hnum, saddr, sport);
	slot = hash4 & udptable->mask;
	hslot4 = &udptable->hash4[slot];

begin:
	udp_lrpa_for_each_entry_rcu(up, node, &hslot4->nulls_head) {
		sk = (struct sock *)up;
		if (inet6_match(net, sk, saddr, daddr, ports, dif, sdif))
			return sk;
	}

	/* if the nulls value we got at the end of this lookup is not the
	 * expected one, we must restart lookup. We probably met an item that
	 * was moved to another chain due to rehash.
	 */
	if (get_nulls_value(node) != slot)
		goto begin;

	return NULL;
}

static void udp6_hash4(struct sock *sk)
{
	struct net *net = sock_net(sk);
	unsigned int hash;

	if (ipv6_addr_v4mapped(&sk->sk_v6_rcv_saddr)) {
		udp4_hash4(sk);
		return;
	}

	if (sk_unhashed(sk) || ipv6_addr_any(&sk->sk_v6_rcv_saddr))
		return;

	hash = udp6_ehashfn(net, &sk->sk_v6_rcv_saddr, sk->sk_num,
			    &sk->sk_v6_daddr, sk->sk_dport);

	udp_lib_hash4(sk, hash);
}
#endif /* CONFIG_BASE_SMALL */

/* rcu_read_lock() must be held */
struct sock *__udp6_lib_lookup(const struct net *net,
			       const struct in6_addr *saddr, __be16 sport,
			       const struct in6_addr *daddr, __be16 dport,
			       int dif, int sdif, struct sk_buff *skb)
{
	struct udp_table *udptable = net->ipv4.udp_table;
	unsigned short hnum = ntohs(dport);
	struct udp_hslot *hslot2;
	struct sock *result, *sk;
	unsigned int hash2;

	hash2 = ipv6_portaddr_hash(net, daddr, hnum);
	hslot2 = udp_hashslot2(udptable, hash2);

	if (udp_has_hash4(hslot2)) {
		result = udp6_lib_lookup4(net, saddr, sport, daddr, hnum,
					  dif, sdif, udptable);
		if (result) /* udp6_lib_lookup4 return sk or NULL */
			return result;
	}

	/* Lookup connected or non-wildcard sockets */
	result = udp6_lib_lookup2(net, saddr, sport,
				  daddr, hnum, dif, sdif,
				  hslot2, skb);
	if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED)
		goto done;

	/* Lookup redirect from BPF */
	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
		sk = inet6_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr),
						saddr, sport, daddr, hnum, dif,
						udp6_ehashfn);
		if (sk) {
			result = sk;
			goto done;
		}
	}

	/* Got non-wildcard socket or error on first lookup */
	if (result)
		goto done;

	/* Lookup wildcard sockets */
	hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum);
	hslot2 = udp_hashslot2(udptable, hash2);

	result = udp6_lib_lookup2(net, saddr, sport,
				  &in6addr_any, hnum, dif, sdif,
				  hslot2, skb);
	if (!IS_ERR_OR_NULL(result))
		goto done;

	/* Cover address change/lookup/rehash race: see __udp4_lib_lookup() */
	result = udp6_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif,
				  udptable);

done:
	if (IS_ERR(result))
		return NULL;
	return result;
}
EXPORT_SYMBOL_GPL(__udp6_lib_lookup);

static 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),
				 inet6_sdif(skb), skb);
}

struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
				 __be16 sport, __be16 dport)
{
	const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation];
	const struct ipv6hdr *iph = (struct ipv6hdr *)(skb->data + offset);
	int iif, sdif;

	inet6_get_iif_sdif(skb, &iif, &sdif);

	return __udp6_lib_lookup(dev_net(skb->dev), &iph->saddr, sport,
				 &iph->daddr, dport, iif, sdif, NULL);
}

/* Must be called under rcu_read_lock().
 * Does increment socket refcount.
 */
#if IS_ENABLED(CONFIG_NF_TPROXY_IPV6) || IS_ENABLED(CONFIG_NF_SOCKET_IPV6)
struct sock *udp6_lib_lookup(const 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, 0, NULL);
	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
		sk = NULL;
	return sk;
}
EXPORT_SYMBOL_GPL(udp6_lib_lookup);
#endif

/* do not use the scratch area len for jumbogram: their length exceeds the
 * scratch area space; note that the IP6CB flags is still in the first
 * cacheline, so checking for jumbograms is cheap
 */
static int udp6_skb_len(struct sk_buff *skb)
{
	return unlikely(inet6_is_jumbogram(skb)) ? skb->len : udp_skb_len(skb);
}

/*
 *	This should be easy, if there is something there we
 *	return it, otherwise we block.
 */

INDIRECT_CALLABLE_SCOPE
int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
		  int flags)
{
	int off, is_udp4, err, peeking = flags & MSG_PEEK;
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct inet_sock *inet = inet_sk(sk);
	struct udp_mib __percpu *mib;
	bool checksum_valid = false;
	unsigned int ulen, copied;
	struct sk_buff *skb;

	if (flags & MSG_ERRQUEUE)
		return ipv6_recv_error(sk, msg, len);

	if (np->rxopt.bits.rxpmtu && READ_ONCE(np->rxpmtu))
		return ipv6_recv_rxpmtu(sk, msg, len);

try_again:
	off = sk_peek_offset(sk, flags);
	skb = __skb_recv_udp(sk, flags, &off, &err);
	if (!skb)
		return err;

	ulen = udp6_skb_len(skb);
	copied = len;
	if (copied > ulen - off)
		copied = ulen - off;
	else if (copied < ulen)
		msg->msg_flags |= MSG_TRUNC;

	is_udp4 = (skb->protocol == htons(ETH_P_IP));
	mib = __UDPX_MIB(sk, is_udp4);

	/* If checksum is needed at all, try to do it while copying the
	 * data.  If the data is truncated, do it before the copy.
	 */
	if (copied < ulen || peeking) {
		checksum_valid = udp_skb_csum_unnecessary(skb) ||
				!__udp_lib_checksum_complete(skb);
		if (!checksum_valid)
			goto csum_copy_err;
	}

	if (checksum_valid || udp_skb_csum_unnecessary(skb)) {
		if (udp_skb_is_linear(skb))
			err = copy_linear_skb(skb, copied, off, &msg->msg_iter);
		else
			err = skb_copy_datagram_msg(skb, off, msg, copied);
	} else {
		err = skb_copy_and_csum_datagram_msg(skb, off, msg);
		if (err == -EINVAL)
			goto csum_copy_err;
	}
	if (unlikely(err)) {
		if (!peeking) {
			udp_drops_inc(sk);
			SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
		}
		kfree_skb(skb);
		return err;
	}
	if (!peeking)
		SNMP_INC_STATS(mib, UDP_MIB_INDATAGRAMS);

	sock_recv_cmsgs(msg, sk, skb);

	/* Copy the address. */
	if (msg->msg_name) {
		DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
		sin6->sin6_family = AF_INET6;
		sin6->sin6_port = udp_hdr(skb)->source;
		sin6->sin6_flowinfo = 0;

		if (is_udp4) {
			ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr,
					       &sin6->sin6_addr);
			sin6->sin6_scope_id = 0;
		} else {
			sin6->sin6_addr = ipv6_hdr(skb)->saddr;
			sin6->sin6_scope_id =
				ipv6_iface_scope_id(&sin6->sin6_addr,
						    inet6_iif(skb));
		}
		msg->msg_namelen = sizeof(*sin6);

		BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk,
						      (struct sockaddr *)sin6,
						      &msg->msg_namelen);
	}

	if (udp_test_bit(GRO_ENABLED, sk))
		udp_cmsg_recv(msg, sk, skb);

	if (np->rxopt.all)
		ip6_datagram_recv_common_ctl(sk, msg, skb);

	if (is_udp4) {
		if (inet_cmsg_flags(inet))
			ip_cmsg_recv_offset(msg, sk, skb,
					    sizeof(struct udphdr), off);
	} else {
		if (np->rxopt.all)
			ip6_datagram_recv_specific_ctl(sk, msg, skb);
	}

	err = copied;
	if (flags & MSG_TRUNC)
		err = ulen;

	skb_consume_udp(sk, skb, peeking ? -err : err);
	return err;

csum_copy_err:
	if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags,
				 udp_skb_destructor)) {
		SNMP_INC_STATS(mib, UDP_MIB_CSUMERRORS);
		SNMP_INC_STATS(mib, UDP_MIB_INERRORS);
	}
	kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM);

	/* starting over for a new packet, but check if we need to yield */
	cond_resched();
	msg->msg_flags &= ~MSG_TRUNC;
	goto try_again;
}

DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
void udpv6_encap_enable(void)
{
	static_branch_inc(&udpv6_encap_needed_key);
}
EXPORT_SYMBOL(udpv6_encap_enable);

/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
 * through error handlers in encapsulations looking for a match.
 */
static int __udp6_lib_err_encap_no_sk(struct sk_buff *skb,
				      struct inet6_skb_parm *opt,
				      u8 type, u8 code, int offset, __be32 info)
{
	int i;

	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
		int (*handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
			       u8 type, u8 code, int offset, __be32 info);
		const struct ip6_tnl_encap_ops *encap;

		encap = rcu_dereference(ip6tun_encaps[i]);
		if (!encap)
			continue;
		handler = encap->err_handler;
		if (handler && !handler(skb, opt, type, code, offset, info))
			return 0;
	}

	return -ENOENT;
}

/* Try to match ICMP errors to UDP tunnels by looking up a socket without
 * reversing source and destination port: this will match tunnels that force the
 * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that
 * lwtunnels might actually break this assumption by being configured with
 * different destination ports on endpoints, in this case we won't be able to
 * trace ICMP messages back to them.
 *
 * If this doesn't match any socket, probe tunnels with arbitrary destination
 * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port
 * we've sent packets to won't necessarily match the local destination port.
 *
 * Then ask the tunnel implementation to match the error against a valid
 * association.
 *
 * Return an error if we can't find a match, the socket if we need further
 * processing, zero otherwise.
 */
static struct sock *__udp6_lib_err_encap(struct net *net,
					 const struct ipv6hdr *hdr, int offset,
					 struct udphdr *uh,
					 struct sock *sk,
					 struct sk_buff *skb,
					 struct inet6_skb_parm *opt,
					 u8 type, u8 code, __be32 info)
{
	int (*lookup)(struct sock *sk, struct sk_buff *skb);
	int network_offset, transport_offset;
	struct udp_sock *up;

	network_offset = skb_network_offset(skb);
	transport_offset = skb_transport_offset(skb);

	/* Network header needs to point to the outer IPv6 header inside ICMP */
	skb_reset_network_header(skb);

	/* Transport header needs to point to the UDP header */
	skb_set_transport_header(skb, offset);

	if (sk) {
		up = udp_sk(sk);

		lookup = READ_ONCE(up->encap_err_lookup);
		if (lookup && lookup(sk, skb))
			sk = NULL;

		goto out;
	}

	sk = __udp6_lib_lookup(net, &hdr->daddr, uh->source,
			       &hdr->saddr, uh->dest,
			       inet6_iif(skb), 0, skb);
	if (sk) {
		up = udp_sk(sk);

		lookup = READ_ONCE(up->encap_err_lookup);
		if (!lookup || lookup(sk, skb))
			sk = NULL;
	}

out:
	if (!sk) {
		sk = ERR_PTR(__udp6_lib_err_encap_no_sk(skb, opt, type, code,
							offset, info));
	}

	skb_set_transport_header(skb, transport_offset);
	skb_set_network_header(skb, network_offset);

	return sk;
}

static int udpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		     u8 type, u8 code, int offset, __be32 info)
{
	const struct ipv6hdr *hdr = (const struct ipv6hdr *)skb->data;
	struct udphdr *uh = (struct udphdr *)(skb->data + offset);
	const struct in6_addr *saddr, *daddr;
	struct net *net = dev_net(skb->dev);
	struct ipv6_pinfo *np;
	bool tunnel = false;
	struct sock *sk;
	int harderr;
	int err;

	daddr = seg6_get_daddr(skb, opt) ? : &hdr->daddr;
	saddr = &hdr->saddr;
	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
			       inet6_iif(skb), inet6_sdif(skb), NULL);

	if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) {
		/* No socket for error: try tunnels before discarding */
		if (static_branch_unlikely(&udpv6_encap_needed_key)) {
			sk = __udp6_lib_err_encap(net, hdr, offset, uh, sk, skb,
						  opt, type, code, info);
			if (!sk)
				return 0;
		} else
			sk = ERR_PTR(-ENOENT);

		if (IS_ERR(sk)) {
			__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
					  ICMP6_MIB_INERRORS);
			return PTR_ERR(sk);
		}

		tunnel = true;
	}

	harderr = icmpv6_err_convert(type, code, &err);
	np = inet6_sk(sk);

	if (type == ICMPV6_PKT_TOOBIG) {
		if (!ip6_sk_accept_pmtu(sk))
			goto out;
		ip6_sk_update_pmtu(skb, sk, info);
		if (READ_ONCE(np->pmtudisc) != IPV6_PMTUDISC_DONT)
			harderr = 1;
	}
	if (type == NDISC_REDIRECT) {
		if (tunnel) {
			ip6_redirect(skb, sock_net(sk), inet6_iif(skb),
				     READ_ONCE(sk->sk_mark),
				     sk_uid(sk));
		} else {
			ip6_sk_redirect(skb, sk);
		}
		goto out;
	}

	/* Tunnels don't have an application socket: don't pass errors back */
	if (tunnel) {
		if (udp_sk(sk)->encap_err_rcv)
			udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest,
						  ntohl(info), (u8 *)(uh+1));
		goto out;
	}

	if (!inet6_test_bit(RECVERR6, sk)) {
		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
			goto out;
	} else {
		ipv6_icmp_error(sk, skb, err, uh->dest, ntohl(info), (u8 *)(uh+1));
	}

	sk->sk_err = err;
	sk_error_report(sk);
out:
	return 0;
}

static int __udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int rc;

	if (!ipv6_addr_any(&sk->sk_v6_daddr)) {
		sock_rps_save_rxhash(sk, skb);
		sk_mark_napi_id(sk, skb);
		sk_incoming_cpu_update(sk);
	} else {
		sk_mark_napi_id_once(sk, skb);
	}

	rc = __udp_enqueue_schedule_skb(sk, skb);
	if (rc < 0) {
		enum skb_drop_reason drop_reason;
		struct net *net = sock_net(sk);

		/* Note that an ENOMEM error is charged twice */
		if (rc == -ENOMEM) {
			UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS);
			drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
		} else {
			UDP6_INC_STATS(net, UDP_MIB_MEMERRORS);
			drop_reason = SKB_DROP_REASON_PROTO_MEM;
		}
		UDP6_INC_STATS(net, UDP_MIB_INERRORS);
		trace_udp_fail_queue_rcv_skb(rc, sk, skb);
		sk_skb_reason_drop(sk, skb, drop_reason);
		return -1;
	}

	return 0;
}

static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
{
	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
	struct udp_sock *up = udp_sk(sk);
	struct net *net = sock_net(sk);

	if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) {
		drop_reason = SKB_DROP_REASON_XFRM_POLICY;
		goto drop;
	}
	nf_reset_ct(skb);

	if (static_branch_unlikely(&udpv6_encap_needed_key) &&
	    READ_ONCE(up->encap_type)) {
		int (*encap_rcv)(struct sock *sk, struct sk_buff *skb);

		/*
		 * This is an encapsulation socket so pass the skb to
		 * the socket's udp_encap_rcv() hook. Otherwise, just
		 * fall through and pass this up the UDP socket.
		 * up->encap_rcv() returns the following value:
		 * =0 if skb was successfully passed to the encap
		 *    handler or was discarded by it.
		 * >0 if skb should be passed on to UDP.
		 * <0 if skb should be resubmitted as proto -N
		 */

		/* if we're overly short, let UDP handle it */
		encap_rcv = READ_ONCE(up->encap_rcv);
		if (encap_rcv) {
			int ret;

			/* Verify checksum before giving to encap */
			if (udp_lib_checksum_complete(skb))
				goto csum_error;

			ret = encap_rcv(sk, skb);
			if (ret <= 0) {
				__UDP6_INC_STATS(net, UDP_MIB_INDATAGRAMS);
				return -ret;
			}
		}

		/* FALLTHROUGH -- it's a UDP Packet */
	}

	prefetch(&sk->sk_rmem_alloc);
	if (rcu_access_pointer(sk->sk_filter) &&
	    udp_lib_checksum_complete(skb))
		goto csum_error;

	drop_reason = sk_filter_trim_cap(sk, skb, sizeof(struct udphdr));
	if (drop_reason)
		goto drop;

	udp_csum_pull_header(skb);

	skb_dst_drop(skb);

	return __udpv6_queue_rcv_skb(sk, skb);

csum_error:
	drop_reason = SKB_DROP_REASON_UDP_CSUM;
	__UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS);
drop:
	__UDP6_INC_STATS(net, UDP_MIB_INERRORS);
	udp_drops_inc(sk);
	sk_skb_reason_drop(sk, skb, drop_reason);
	return -1;
}

static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	struct sk_buff *next, *segs;
	int ret;

	if (likely(!udp_unexpected_gso(sk, skb)))
		return udpv6_queue_rcv_one_skb(sk, skb);

	__skb_push(skb, -skb_mac_offset(skb));
	segs = udp_rcv_segment(sk, skb, false);
	skb_list_walk_safe(segs, skb, next) {
		__skb_pull(skb, skb_transport_offset(skb));

		udp_post_segment_fix_csum(skb);
		ret = udpv6_queue_rcv_one_skb(sk, skb);
		if (ret > 0)
			ip6_protocol_deliver_rcu(dev_net(skb->dev), skb, ret,
						 true);
	}
	return 0;
}

static bool __udp_v6_is_mcast_sock(struct net *net, const struct sock *sk,
				   __be16 loc_port, const struct in6_addr *loc_addr,
				   __be16 rmt_port, const struct in6_addr *rmt_addr,
				   int dif, int sdif, unsigned short hnum)
{
	const struct inet_sock *inet = inet_sk(sk);

	if (!net_eq(sock_net(sk), net))
		return false;

	if (udp_sk(sk)->udp_port_hash != hnum ||
	    sk->sk_family != PF_INET6 ||
	    (inet->inet_dport && inet->inet_dport != rmt_port) ||
	    (!ipv6_addr_any(&sk->sk_v6_daddr) &&
		    !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) ||
	    !udp_sk_bound_dev_eq(net, READ_ONCE(sk->sk_bound_dev_if), dif, sdif) ||
	    (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
		    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)))
		return false;
	if (!inet6_mc_check(sk, loc_addr, rmt_addr))
		return false;
	return true;
}

static void udp6_csum_zero_error(struct sk_buff *skb)
{
	/* RFC 2460 section 8.1 says that we SHOULD log
	 * this error. Well, it is reasonable.
	 */
	net_dbg_ratelimited("IPv6: udp checksum is 0 for [%pI6c]:%u->[%pI6c]:%u\n",
			    &ipv6_hdr(skb)->saddr, ntohs(udp_hdr(skb)->source),
			    &ipv6_hdr(skb)->daddr, ntohs(udp_hdr(skb)->dest));
}

/*
 * Note: called only from the BH handler context,
 * so we don't need to lock the hashes.
 */
static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb,
				    const struct in6_addr *saddr,
				    const struct in6_addr *daddr)
{
	struct udp_table *udptable = net->ipv4.udp_table;
	const struct udphdr *uh = udp_hdr(skb);
	unsigned int hash2, hash2_any, offset;
	unsigned short hnum = ntohs(uh->dest);
	struct sock *sk, *first = NULL;
	int sdif = inet6_sdif(skb);
	int dif = inet6_iif(skb);
	struct hlist_node *node;
	struct udp_hslot *hslot;
	struct sk_buff *nskb;
	bool use_hash2;

	hash2_any = 0;
	hash2 = 0;
	hslot = udp_hashslot(udptable, net, hnum);
	use_hash2 = hslot->count > 10;
	offset = offsetof(typeof(*sk), sk_node);

	if (use_hash2) {
		hash2_any = ipv6_portaddr_hash(net, &in6addr_any, hnum) &
			    udptable->mask;
		hash2 = ipv6_portaddr_hash(net, daddr, hnum) & udptable->mask;
start_lookup:
		hslot = &udptable->hash2[hash2].hslot;
		offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node);
	}

	sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) {
		if (!__udp_v6_is_mcast_sock(net, sk, uh->dest, daddr,
					    uh->source, saddr, dif, sdif,
					    hnum))
			continue;
		/* If zero checksum and no_check is not on for
		 * the socket then skip it.
		 */
		if (!uh->check && !udp_get_no_check6_rx(sk))
			continue;
		if (!first) {
			first = sk;
			continue;
		}
		nskb = skb_clone(skb, GFP_ATOMIC);
		if (unlikely(!nskb)) {
			udp_drops_inc(sk);
			__UDP6_INC_STATS(net, UDP_MIB_RCVBUFERRORS);
			__UDP6_INC_STATS(net, UDP_MIB_INERRORS);
			continue;
		}

		if (udpv6_queue_rcv_skb(sk, nskb) > 0)
			consume_skb(nskb);
	}

	/* Also lookup *:port if we are using hash2 and haven't done so yet. */
	if (use_hash2 && hash2 != hash2_any) {
		hash2 = hash2_any;
		goto start_lookup;
	}

	if (first) {
		if (udpv6_queue_rcv_skb(first, skb) > 0)
			consume_skb(skb);
	} else {
		kfree_skb(skb);
		__UDP6_INC_STATS(net, UDP_MIB_IGNOREDMULTI);
	}
	return 0;
}

static void udp6_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst)
{
	if (udp_sk_rx_dst_set(sk, dst))
		sk->sk_rx_dst_cookie = rt6_get_cookie(dst_rt6_info(dst));
}

/* wrapper for udp_queue_rcv_skb taking care of csum conversion and
 * return code conversion for ip layer consumption
 */
static int udp6_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb,
				struct udphdr *uh)
{
	int ret;

	if (inet_get_convert_csum(sk) && uh->check)
		skb_checksum_try_convert(skb, IPPROTO_UDP, ip6_compute_pseudo);

	ret = udpv6_queue_rcv_skb(sk, skb);

	/* a return value > 0 means to resubmit the input */
	if (ret > 0)
		return ret;
	return 0;
}

static int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh)
{
	int err;

	/* To support RFC 6936 (allow zero checksum in UDP/IPV6 for tunnels)
	 * we accept a checksum of zero here. When we find the socket
	 * for the UDP packet we'll check if that socket allows zero checksum
	 * for IPv6 (set by socket option).
	 *
	 * Note, we are only interested in != 0 or == 0, thus the
	 * force to int.
	 */
	err = (__force int)skb_checksum_init_zero_check(skb, IPPROTO_UDP, uh->check,
							ip6_compute_pseudo);
	if (err)
		return err;

	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
		/* If SW calculated the value, we know it's bad */
		if (skb->csum_complete_sw)
			return 1;

		/* HW says the value is bad. Let's validate that.
		 * skb->csum is no longer the full packet checksum,
		 * so don't treat is as such.
		 */
		skb_checksum_complete_unset(skb);
	}

	return 0;
}

INDIRECT_CALLABLE_SCOPE int udpv6_rcv(struct sk_buff *skb)
{
	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
	const struct in6_addr *saddr, *daddr;
	struct net *net = dev_net(skb->dev);
	struct sock *sk = NULL;
	struct udphdr *uh;
	bool refcounted;
	u32 ulen = 0;

	if (!pskb_may_pull(skb, sizeof(struct udphdr)))
		goto discard;

	saddr = &ipv6_hdr(skb)->saddr;
	daddr = &ipv6_hdr(skb)->daddr;
	uh = udp_hdr(skb);

	ulen = ntohs(uh->len);
	if (ulen > skb->len)
		goto short_packet;

	/* Check for jumbo payload */
	if (ulen == 0)
		ulen = skb->len;

	if (ulen < sizeof(*uh))
		goto short_packet;

	if (ulen < skb->len) {
		if (pskb_trim_rcsum(skb, ulen))
			goto short_packet;

		saddr = &ipv6_hdr(skb)->saddr;
		daddr = &ipv6_hdr(skb)->daddr;
		uh = udp_hdr(skb);
	}

	if (udp6_csum_init(skb, uh))
		goto csum_error;

	/* Check if the socket is already available, e.g. due to early demux */
	sk = inet6_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest,
			      &refcounted, udp6_ehashfn);
	if (IS_ERR(sk))
		goto no_sk;

	if (sk) {
		struct dst_entry *dst = skb_dst(skb);
		int ret;

		if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
			udp6_sk_rx_dst_set(sk, dst);

		if (!uh->check && !udp_get_no_check6_rx(sk)) {
			if (refcounted)
				sock_put(sk);
			goto report_csum_error;
		}

		ret = udp6_unicast_rcv_skb(sk, skb, uh);
		if (refcounted)
			sock_put(sk);
		return ret;
	}

	/*
	 *	Multicast receive code
	 */
	if (ipv6_addr_is_multicast(daddr))
		return __udp6_lib_mcast_deliver(net, skb, saddr, daddr);

	/* Unicast */
	sk = __udp6_lib_lookup_skb(skb, uh->source, uh->dest);
	if (sk) {
		if (!uh->check && !udp_get_no_check6_rx(sk))
			goto report_csum_error;
		return udp6_unicast_rcv_skb(sk, skb, uh);
	}
no_sk:
	reason = SKB_DROP_REASON_NO_SOCKET;

	if (!uh->check)
		goto report_csum_error;

	if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard;
	nf_reset_ct(skb);

	if (udp_lib_checksum_complete(skb))
		goto csum_error;

	__UDP6_INC_STATS(net, UDP_MIB_NOPORTS);
	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_PORT_UNREACH, 0);

	sk_skb_reason_drop(sk, skb, reason);
	return 0;

short_packet:
	if (reason == SKB_DROP_REASON_NOT_SPECIFIED)
		reason = SKB_DROP_REASON_PKT_TOO_SMALL;
	net_dbg_ratelimited("UDPv6: short packet: From [%pI6c]:%u %d/%d to [%pI6c]:%u\n",
			    saddr, ntohs(uh->source),
			    ulen, skb->len,
			    daddr, ntohs(uh->dest));
	goto discard;

report_csum_error:
	udp6_csum_zero_error(skb);
csum_error:
	if (reason == SKB_DROP_REASON_NOT_SPECIFIED)
		reason = SKB_DROP_REASON_UDP_CSUM;
	__UDP6_INC_STATS(net, UDP_MIB_CSUMERRORS);
discard:
	__UDP6_INC_STATS(net, UDP_MIB_INERRORS);
	sk_skb_reason_drop(sk, skb, reason);
	return 0;
}


static struct sock *__udp6_lib_demux_lookup(struct net *net,
			__be16 loc_port, const struct in6_addr *loc_addr,
			__be16 rmt_port, const struct in6_addr *rmt_addr,
			int dif, int sdif)
{
	struct udp_table *udptable = net->ipv4.udp_table;
	unsigned short hnum = ntohs(loc_port);
	struct udp_hslot *hslot2;
	unsigned int hash2;
	__portpair ports;
	struct sock *sk;

	hash2 = ipv6_portaddr_hash(net, loc_addr, hnum);
	hslot2 = udp_hashslot2(udptable, hash2);
	ports = INET_COMBINED_PORTS(rmt_port, hnum);

	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
		if (sk->sk_state == TCP_ESTABLISHED &&
		    inet6_match(net, sk, rmt_addr, loc_addr, ports, dif, sdif))
			return sk;
		/* Only check first socket in chain */
		break;
	}
	return NULL;
}

void udp_v6_early_demux(struct sk_buff *skb)
{
	struct net *net = dev_net(skb->dev);
	const struct udphdr *uh;
	struct sock *sk;
	struct dst_entry *dst;
	int dif = skb->dev->ifindex;
	int sdif = inet6_sdif(skb);

	if (!pskb_may_pull(skb, skb_transport_offset(skb) +
	    sizeof(struct udphdr)))
		return;

	uh = udp_hdr(skb);

	if (skb->pkt_type == PACKET_HOST)
		sk = __udp6_lib_demux_lookup(net, uh->dest,
					     &ipv6_hdr(skb)->daddr,
					     uh->source, &ipv6_hdr(skb)->saddr,
					     dif, sdif);
	else
		return;

	if (!sk)
		return;

	skb->sk = sk;
	DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk));
	skb->destructor = sock_pfree;
	dst = rcu_dereference(sk->sk_rx_dst);

	if (dst)
		dst = dst_check(dst, sk->sk_rx_dst_cookie);
	if (dst) {
		/* set noref for now.
		 * any place which wants to hold dst has to call
		 * dst_hold_safe()
		 */
		skb_dst_set_noref(skb, dst);
	}
}

/*
 * Throw away all pending data and cancel the corking. Socket is locked.
 */
static void udp_v6_flush_pending_frames(struct sock *sk)
{
	struct udp_sock *up = udp_sk(sk);

	if (up->pending == AF_INET)
		udp_flush_pending_frames(sk);
	else if (up->pending) {
		up->len = 0;
		WRITE_ONCE(up->pending, 0);
		ip6_flush_pending_frames(sk);
	}
}

static int udpv6_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
			     int addr_len)
{
	if (addr_len < offsetofend(struct sockaddr, sa_family))
		return -EINVAL;
	/* The following checks are replicated from __ip6_datagram_connect()
	 * and intended to prevent BPF program called below from accessing
	 * bytes that are out of the bound specified by user in addr_len.
	 */
	if (uaddr->sa_family == AF_INET) {
		if (ipv6_only_sock(sk))
			return -EAFNOSUPPORT;
		return udp_pre_connect(sk, uaddr, addr_len);
	}

	if (addr_len < SIN6_LEN_RFC2133)
		return -EINVAL;

	return BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, &addr_len);
}

static int udpv6_connect(struct sock *sk, struct sockaddr_unsized *uaddr,
			 int addr_len)
{
	int res;

	lock_sock(sk);
	res = __ip6_datagram_connect(sk, uaddr, addr_len);
	if (!res)
		udp6_hash4(sk);
	release_sock(sk);
	return res;
}

/**
 *	udp6_hwcsum_outgoing  -  handle outgoing HW checksumming
 *	@sk:	socket we are sending on
 *	@skb:	sk_buff containing the filled-in UDP header
 *		(checksum field must be zeroed out)
 *	@saddr: source address
 *	@daddr: destination address
 *	@len:	length of packet
 */
static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
				 const struct in6_addr *saddr,
				 const struct in6_addr *daddr, int len)
{
	unsigned int offset;
	struct udphdr *uh = udp_hdr(skb);
	struct sk_buff *frags = skb_shinfo(skb)->frag_list;
	__wsum csum = 0;

	if (!frags) {
		/* Only one fragment on the socket.  */
		skb->csum_start = skb_transport_header(skb) - skb->head;
		skb->csum_offset = offsetof(struct udphdr, check);
		uh->check = ~csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP, 0);
	} else {
		/*
		 * HW-checksum won't work as there are two or more
		 * fragments on the socket so that all csums of sk_buffs
		 * should be together
		 */
		offset = skb_transport_offset(skb);
		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
		csum = skb->csum;

		skb->ip_summed = CHECKSUM_NONE;

		do {
			csum = csum_add(csum, frags->csum);
		} while ((frags = frags->next));

		uh->check = csum_ipv6_magic(saddr, daddr, len, IPPROTO_UDP,
					    csum);
		if (uh->check == 0)
			uh->check = CSUM_MANGLED_0;
	}
}

/*
 *	Sending
 */

static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6,
			   struct inet_cork *cork)
{
	struct sock *sk = skb->sk;
	int offset, len, datalen;
	struct udphdr *uh;
	int err = 0;

	offset = skb_transport_offset(skb);
	len = skb->len - offset;
	datalen = len - sizeof(*uh);

	/*
	 * Create a UDP header
	 */
	uh = udp_hdr(skb);
	uh->source = fl6->fl6_sport;
	uh->dest = fl6->fl6_dport;
	uh->len = htons(len);
	uh->check = 0;

	if (cork->gso_size) {
		const int hlen = skb_network_header_len(skb) +
				 sizeof(struct udphdr);

		if (hlen + min(datalen, cork->gso_size) > cork->fragsize) {
			kfree_skb(skb);
			return -EMSGSIZE;
		}
		if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) {
			kfree_skb(skb);
			return -EINVAL;
		}
		if (udp_get_no_check6_tx(sk)) {
			kfree_skb(skb);
			return -EINVAL;
		}
		if (dst_xfrm(skb_dst(skb))) {
			kfree_skb(skb);
			return -EIO;
		}

		if (datalen > cork->gso_size) {
			skb_shinfo(skb)->gso_size = cork->gso_size;
			skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4;
			skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen,
								 cork->gso_size);

			/* Don't checksum the payload, skb will get segmented */
			goto csum_partial;
		}
	}

	if (udp_get_no_check6_tx(sk)) {   /* UDP csum disabled */
		skb->ip_summed = CHECKSUM_NONE;
		goto send;
	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */
csum_partial:
		udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len);
		goto send;
	}

	/* add protocol-dependent pseudo-header */
	uh->check = csum_ipv6_magic(&fl6->saddr, &fl6->daddr,
				    len, IPPROTO_UDP, udp_csum(skb));
	if (uh->check == 0)
		uh->check = CSUM_MANGLED_0;

send:
	err = ip6_send_skb(skb);
	if (unlikely(err)) {
		if (err == -ENOBUFS && !inet6_test_bit(RECVERR6, sk)) {
			UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS);
			err = 0;
		}
	} else {
		UDP6_INC_STATS(sock_net(sk), UDP_MIB_OUTDATAGRAMS);
	}
	return err;
}

static int udp_v6_push_pending_frames(struct sock *sk)
{
	struct sk_buff *skb;
	struct udp_sock  *up = udp_sk(sk);
	int err = 0;

	if (up->pending == AF_INET)
		return udp_push_pending_frames(sk);

	skb = ip6_finish_skb(sk);
	if (!skb)
		goto out;

	err = udp_v6_send_skb(skb, &inet_sk(sk)->cork.fl.u.ip6,
			      &inet_sk(sk)->cork.base);
out:
	up->len = 0;
	WRITE_ONCE(up->pending, 0);
	return err;
}

int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
{
	int corkreq = udp_test_bit(CORK, sk) || msg->msg_flags & MSG_MORE;
	DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
	struct ipv6_txoptions *opt_to_free = NULL;
	struct in6_addr *daddr, *final_p, final;
	struct ip6_flowlabel *flowlabel = NULL;
	struct inet_sock *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct ipv6_txoptions *opt = NULL;
	struct udp_sock *up = udp_sk(sk);
	struct ipv6_txoptions opt_space;
	int addr_len = msg->msg_namelen;
	struct inet_cork_full cork;
	struct ipcm6_cookie ipc6;
	bool connected = false;
	struct dst_entry *dst;
	struct flowi6 *fl6;
	int ulen = len;
	int err;

	fl6 = &cork.fl.u.ip6;
	ipcm6_init_sk(&ipc6, sk);
	ipc6.gso_size = READ_ONCE(up->gso_size);

	/* destination address check */
	if (sin6) {
		if (addr_len < offsetof(struct sockaddr, sa_data))
			return -EINVAL;

		switch (sin6->sin6_family) {
		case AF_INET6:
			if (addr_len < SIN6_LEN_RFC2133)
				return -EINVAL;
			daddr = &sin6->sin6_addr;
			if (ipv6_addr_any(daddr) &&
			    ipv6_addr_v4mapped(&np->saddr))
				ipv6_addr_set_v4mapped(htonl(INADDR_LOOPBACK),
						       daddr);
			break;
		case AF_INET:
			goto do_udp_sendmsg;
		case AF_UNSPEC:
			msg->msg_name = sin6 = NULL;
			msg->msg_namelen = addr_len = 0;
			daddr = NULL;
			break;
		default:
			return -EINVAL;
		}
	} else if (!READ_ONCE(up->pending)) {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;
		daddr = &sk->sk_v6_daddr;
	} else
		daddr = NULL;

	if (daddr) {
		if (ipv6_addr_v4mapped(daddr)) {
			struct sockaddr_in sin;
			sin.sin_family = AF_INET;
			sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport;
			sin.sin_addr.s_addr = daddr->s6_addr32[3];
			msg->msg_name = &sin;
			msg->msg_namelen = sizeof(sin);
do_udp_sendmsg:
			err = ipv6_only_sock(sk) ?
				-ENETUNREACH : udp_sendmsg(sk, msg, len);
			msg->msg_name = sin6;
			msg->msg_namelen = addr_len;
			return err;
		}
	}

	/* Rough check on arithmetic overflow,
	   better check is made in ip6_append_data().
	   */
	if (len > INT_MAX - sizeof(struct udphdr))
		return -EMSGSIZE;

	if (READ_ONCE(up->pending)) {
		if (READ_ONCE(up->pending) == AF_INET)
			return udp_sendmsg(sk, msg, len);
		/*
		 * There are pending frames.
		 * The socket lock must be held while it's corked.
		 */
		lock_sock(sk);
		if (likely(up->pending)) {
			if (unlikely(up->pending != AF_INET6)) {
				release_sock(sk);
				return -EAFNOSUPPORT;
			}
			dst = NULL;
			goto do_append_data;
		}
		release_sock(sk);
	}
	ulen += sizeof(struct udphdr);

	memset(fl6, 0, sizeof(*fl6));

	if (sin6) {
		if (sin6->sin6_port == 0)
			return -EINVAL;

		fl6->fl6_dport = sin6->sin6_port;
		daddr = &sin6->sin6_addr;

		if (inet6_test_bit(SNDFLOW, sk)) {
			fl6->flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK;
			if (fl6->flowlabel & IPV6_FLOWLABEL_MASK) {
				flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
				if (IS_ERR(flowlabel))
					return -EINVAL;
			}
		}

		/*
		 * Otherwise it will be difficult to maintain
		 * sk->sk_dst_cache.
		 */
		if (sk->sk_state == TCP_ESTABLISHED &&
		    ipv6_addr_equal(daddr, &sk->sk_v6_daddr))
			daddr = &sk->sk_v6_daddr;

		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    sin6->sin6_scope_id &&
		    __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr)))
			fl6->flowi6_oif = sin6->sin6_scope_id;
	} else {
		if (sk->sk_state != TCP_ESTABLISHED)
			return -EDESTADDRREQ;

		fl6->fl6_dport = inet->inet_dport;
		daddr = &sk->sk_v6_daddr;
		fl6->flowlabel = np->flow_label;
		connected = true;
	}

	if (!fl6->flowi6_oif)
		fl6->flowi6_oif = READ_ONCE(sk->sk_bound_dev_if);

	if (!fl6->flowi6_oif)
		fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex;

	fl6->flowi6_uid = sk_uid(sk);

	if (msg->msg_controllen) {
		opt = &opt_space;
		memset(opt, 0, sizeof(struct ipv6_txoptions));
		opt->tot_len = sizeof(*opt);
		ipc6.opt = opt;

		err = udp_cmsg_send(sk, msg, &ipc6.gso_size);
		if (err > 0) {
			err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, fl6,
						    &ipc6);
			connected = false;
		}
		if (err < 0) {
			fl6_sock_release(flowlabel);
			return err;
		}
		if ((fl6->flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) {
			flowlabel = fl6_sock_lookup(sk, fl6->flowlabel);
			if (IS_ERR(flowlabel))
				return -EINVAL;
		}
		if (!(opt->opt_nflen|opt->opt_flen))
			opt = NULL;
	}
	if (!opt) {
		opt = txopt_get(np);
		opt_to_free = opt;
	}
	if (flowlabel)
		opt = fl6_merge_options(&opt_space, flowlabel, opt);
	opt = ipv6_fixup_options(&opt_space, opt);
	ipc6.opt = opt;

	fl6->flowi6_proto = IPPROTO_UDP;
	fl6->flowi6_mark = ipc6.sockc.mark;
	fl6->daddr = *daddr;
	if (ipv6_addr_any(&fl6->saddr) && !ipv6_addr_any(&np->saddr))
		fl6->saddr = np->saddr;
	fl6->fl6_sport = inet->inet_sport;

	if (cgroup_bpf_enabled(CGROUP_UDP6_SENDMSG) && !connected) {
		err = BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk,
					   (struct sockaddr *)sin6,
					   &addr_len,
					   &fl6->saddr);
		if (err)
			goto out_no_dst;
		if (sin6) {
			if (ipv6_addr_v4mapped(&sin6->sin6_addr)) {
				/* BPF program rewrote IPv6-only by IPv4-mapped
				 * IPv6. It's currently unsupported.
				 */
				err = -ENOTSUPP;
				goto out_no_dst;
			}
			if (sin6->sin6_port == 0) {
				/* BPF program set invalid port. Reject it. */
				err = -EINVAL;
				goto out_no_dst;
			}
			fl6->fl6_dport = sin6->sin6_port;
			fl6->daddr = sin6->sin6_addr;
		}
	}

	if (ipv6_addr_any(&fl6->daddr))
		fl6->daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */

	final_p = fl6_update_dst(fl6, opt, &final);
	if (final_p)
		connected = false;

	if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) {
		fl6->flowi6_oif = READ_ONCE(np->mcast_oif);
		connected = false;
	} else if (!fl6->flowi6_oif)
		fl6->flowi6_oif = READ_ONCE(np->ucast_oif);

	security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));

	fl6->flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6->flowlabel);

	dst = ip6_sk_dst_lookup_flow(sk, fl6, final_p, connected);
	if (IS_ERR(dst)) {
		err = PTR_ERR(dst);
		dst = NULL;
		goto out;
	}

	if (ipc6.hlimit < 0)
		ipc6.hlimit = ip6_sk_dst_hoplimit(np, fl6, dst);

	if (msg->msg_flags&MSG_CONFIRM)
		goto do_confirm;
back_from_confirm:

	/* Lockless fast path for the non-corking case */
	if (!corkreq) {
		struct sk_buff *skb;

		skb = ip6_make_skb(sk, ip_generic_getfrag, msg, ulen,
				   sizeof(struct udphdr), &ipc6,
				   dst_rt6_info(dst),
				   msg->msg_flags, &cork);
		err = PTR_ERR(skb);
		if (!IS_ERR_OR_NULL(skb))
			err = udp_v6_send_skb(skb, fl6, &cork.base);
		/* ip6_make_skb steals dst reference */
		goto out_no_dst;
	}

	lock_sock(sk);
	if (unlikely(up->pending)) {
		/* The socket is already corked while preparing it. */
		/* ... which is an evident application bug. --ANK */
		release_sock(sk);

		net_dbg_ratelimited("udp cork app bug 2\n");
		err = -EINVAL;
		goto out;
	}

	WRITE_ONCE(up->pending, AF_INET6);

do_append_data:
	up->len += ulen;
	err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen,
			      sizeof(struct udphdr), &ipc6, fl6,
			      dst_rt6_info(dst),
			      corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);
	if (err)
		udp_v6_flush_pending_frames(sk);
	else if (!corkreq)
		err = udp_v6_push_pending_frames(sk);
	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
		WRITE_ONCE(up->pending, 0);

	if (err > 0)
		err = inet6_test_bit(RECVERR6, sk) ? net_xmit_errno(err) : 0;
	release_sock(sk);

out:
	dst_release(dst);
out_no_dst:
	fl6_sock_release(flowlabel);
	txopt_put(opt_to_free);
	if (!err)
		return len;
	/*
	 * ENOBUFS = no kernel mem, SOCK_NOSPACE = no sndbuf space.  Reporting
	 * ENOBUFS might not be good (it's not tunable per se), but otherwise
	 * we don't have a good statistic (IpOutDiscards but it can be too many
	 * things).  We could add another new stat but at least for now that
	 * seems like overkill.
	 */
	if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags))
		UDP6_INC_STATS(sock_net(sk), UDP_MIB_SNDBUFERRORS);

	return err;

do_confirm:
	if (msg->msg_flags & MSG_PROBE)
		dst_confirm_neigh(dst, &fl6->daddr);
	if (!(msg->msg_flags&MSG_PROBE) || len)
		goto back_from_confirm;
	err = 0;
	goto out;
}
EXPORT_SYMBOL(udpv6_sendmsg);

static void udpv6_splice_eof(struct socket *sock)
{
	struct sock *sk = sock->sk;
	struct udp_sock *up = udp_sk(sk);

	if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk))
		return;

	lock_sock(sk);
	if (up->pending && !udp_test_bit(CORK, sk))
		udp_v6_push_pending_frames(sk);
	release_sock(sk);
}

static void udpv6_destroy_sock(struct sock *sk)
{
	struct udp_sock *up = udp_sk(sk);
	lock_sock(sk);

	/* protects from races with udp_abort() */
	sock_set_flag(sk, SOCK_DEAD);
	udp_v6_flush_pending_frames(sk);
	release_sock(sk);

	if (static_branch_unlikely(&udpv6_encap_needed_key)) {
		if (up->encap_type) {
			void (*encap_destroy)(struct sock *sk);
			encap_destroy = READ_ONCE(up->encap_destroy);
			if (encap_destroy)
				encap_destroy(sk);
		}
		if (udp_test_bit(ENCAP_ENABLED, sk)) {
			static_branch_dec(&udpv6_encap_needed_key);
			udp_encap_disable();
			udp_tunnel_cleanup_gro(sk);
		}
	}
}

/*
 *	Socket option code for UDP
 */
static int udpv6_setsockopt(struct sock *sk, int level, int optname,
			    sockptr_t optval, unsigned int optlen)
{
	if (level == SOL_UDP || level == SOL_SOCKET)
		return udp_lib_setsockopt(sk, level, optname,
					  optval, optlen,
					  udp_v6_push_pending_frames);
	return ipv6_setsockopt(sk, level, optname, optval, optlen);
}

static int udpv6_getsockopt(struct sock *sk, int level, int optname,
			    char __user *optval, int __user *optlen)
{
	if (level == SOL_UDP)
		return udp_lib_getsockopt(sk, level, optname, optval, optlen);
	return ipv6_getsockopt(sk, level, optname, optval, optlen);
}


/* ------------------------------------------------------------------------ */
#ifdef CONFIG_PROC_FS
static int udp6_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_puts(seq, IPV6_SEQ_DGRAM_HEADER);
	} else {
		int bucket = ((struct udp_iter_state *)seq->private)->bucket;
		const struct inet_sock *inet = inet_sk((const struct sock *)v);
		__u16 srcp = ntohs(inet->inet_sport);
		__u16 destp = ntohs(inet->inet_dport);
		__ip6_dgram_sock_seq_show(seq, v, srcp, destp,
					  udp_rqueue_get(v), bucket);
	}
	return 0;
}

static const struct seq_operations udp6_seq_ops = {
	.start		= udp_seq_start,
	.next		= udp_seq_next,
	.stop		= udp_seq_stop,
	.show		= udp6_seq_show,
};

static struct udp_seq_afinfo udp6_seq_afinfo = {
	.family		= AF_INET6,
};

int __net_init udp6_proc_init(struct net *net)
{
	if (!proc_create_net_data("udp6", 0444, net->proc_net, &udp6_seq_ops,
			sizeof(struct udp_iter_state), &udp6_seq_afinfo))
		return -ENOMEM;
	return 0;
}

void udp6_proc_exit(struct net *net)
{
	remove_proc_entry("udp6", net->proc_net);
}
#endif /* CONFIG_PROC_FS */

/* ------------------------------------------------------------------------ */

struct proto udpv6_prot = {
	.name			= "UDPv6",
	.owner			= THIS_MODULE,
	.close			= udp_lib_close,
	.pre_connect		= udpv6_pre_connect,
	.connect		= udpv6_connect,
	.disconnect		= udp_disconnect,
	.ioctl			= udp_ioctl,
	.init			= udpv6_init_sock,
	.destroy		= udpv6_destroy_sock,
	.setsockopt		= udpv6_setsockopt,
	.getsockopt		= udpv6_getsockopt,
	.sendmsg		= udpv6_sendmsg,
	.recvmsg		= udpv6_recvmsg,
	.splice_eof		= udpv6_splice_eof,
	.release_cb		= ip6_datagram_release_cb,
	.hash			= udp_lib_hash,
	.unhash			= udp_lib_unhash,
	.rehash			= udp_v6_rehash,
	.get_port		= udp_v6_get_port,
	.put_port		= udp_lib_unhash,
#ifdef CONFIG_BPF_SYSCALL
	.psock_update_sk_prot	= udp_bpf_update_proto,
#endif

	.memory_allocated	= &net_aligned_data.udp_memory_allocated,
	.per_cpu_fw_alloc	= &udp_memory_per_cpu_fw_alloc,

	.sysctl_mem		= sysctl_udp_mem,
	.sysctl_wmem_offset     = offsetof(struct net, ipv4.sysctl_udp_wmem_min),
	.sysctl_rmem_offset     = offsetof(struct net, ipv4.sysctl_udp_rmem_min),
	.obj_size		= sizeof(struct udp6_sock),
	.ipv6_pinfo_offset = offsetof(struct udp6_sock, inet6),
	.diag_destroy		= udp_abort,
};

static struct inet_protosw udpv6_protosw = {
	.type =      SOCK_DGRAM,
	.protocol =  IPPROTO_UDP,
	.prot =      &udpv6_prot,
	.ops =       &inet6_dgram_ops,
	.flags =     INET_PROTOSW_PERMANENT,
};

int __init udpv6_init(void)
{
	int ret;

	net_hotdata.udpv6_protocol = (struct inet6_protocol) {
		.handler     = udpv6_rcv,
		.err_handler = udpv6_err,
		.flags	     = INET6_PROTO_NOPOLICY | INET6_PROTO_FINAL,
	};
	ret = inet6_add_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP);
	if (ret)
		goto out;

	ret = inet6_register_protosw(&udpv6_protosw);
	if (ret)
		goto out_udpv6_protocol;
out:
	return ret;

out_udpv6_protocol:
	inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP);
	goto out;
}

void udpv6_exit(void)
{
	inet6_unregister_protosw(&udpv6_protosw);
	inet6_del_protocol(&net_hotdata.udpv6_protocol, IPPROTO_UDP);
}