// 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.
   *
   *		The User Datagram Protocol (UDP).
   *

   * Authors:	Ross Biro

   *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
   *		Arnt Gulbrandsen, <agulbra@nvg.unit.no>

   *		Alan Cox, <alan@lxorguk.ukuu.org.uk>

   *		Hirokazu Takahashi, <taka@valinux.co.jp>
   *
   * Fixes:
   *		Alan Cox	:	verify_area() calls
   *		Alan Cox	: 	stopped close while in use off icmp
   *					messages. Not a fix but a botch that
   *					for udp at least is 'valid'.
   *		Alan Cox	:	Fixed icmp handling properly
   *		Alan Cox	: 	Correct error for oversized datagrams

   *		Alan Cox	:	Tidied select() semantics.
   *		Alan Cox	:	udp_err() fixed properly, also now

   *					select and read wake correctly on errors
   *		Alan Cox	:	udp_send verify_area moved to avoid mem leak
   *		Alan Cox	:	UDP can count its memory
   *		Alan Cox	:	send to an unknown connection causes
   *					an ECONNREFUSED off the icmp, but
   *					does NOT close.
   *		Alan Cox	:	Switched to new sk_buff handlers. No more backlog!
   *		Alan Cox	:	Using generic datagram code. Even smaller and the PEEK
   *					bug no longer crashes it.
   *		Fred Van Kempen	: 	Net2e support for sk->broadcast.
   *		Alan Cox	:	Uses skb_free_datagram
   *		Alan Cox	:	Added get/set sockopt support.
   *		Alan Cox	:	Broadcasting without option set returns EACCES.
   *		Alan Cox	:	No wakeup calls. Instead we now use the callbacks.
   *		Alan Cox	:	Use ip_tos and ip_ttl
   *		Alan Cox	:	SNMP Mibs
   *		Alan Cox	:	MSG_DONTROUTE, and 0.0.0.0 support.
   *		Matt Dillon	:	UDP length checks.
   *		Alan Cox	:	Smarter af_inet used properly.
   *		Alan Cox	:	Use new kernel side addressing.
   *		Alan Cox	:	Incorrect return on truncated datagram receive.
   *	Arnt Gulbrandsen 	:	New udp_send and stuff
   *		Alan Cox	:	Cache last socket
   *		Alan Cox	:	Route cache
   *		Jon Peatfield	:	Minor efficiency fix to sendto().
   *		Mike Shaver	:	RFC1122 checks.
   *		Alan Cox	:	Nonblocking error fix.
   *	Willy Konynenberg	:	Transparent proxying support.
   *		Mike McLagan	:	Routing by source
   *		David S. Miller	:	New socket lookup architecture.
   *					Last socket cache retained as it
   *					does have a high hit rate.
   *		Olaf Kirch	:	Don't linearise iovec on sendmsg.
   *		Andi Kleen	:	Some cleanups, cache destination entry

   *					for connect.

   *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
   *		Melvin Smith	:	Check msg_name not msg_namelen in sendto(),
   *					return ENOTCONN for unconnected sockets (POSIX)
   *		Janos Farkas	:	don't deliver multi/broadcasts to a different
   *					bound-to-device socket
   *	Hirokazu Takahashi	:	HW checksumming for outgoing UDP
   *					datagrams.
   *	Hirokazu Takahashi	:	sendfile() on UDP works now.
   *		Arnaldo C. Melo :	convert /proc/net/udp to seq_file
   *	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.
   *	Derek Atkins <derek@ihtfp.com>: Add Encapulation Support

   *	James Chapman		:	Add L2TP encapsulation type.

   */

  #define pr_fmt(fmt) "UDP: " fmt

  #include <linux/uaccess.h>

  #include <asm/ioctls.h>

  #include <linux/memblock.h>

  #include <linux/highmem.h>
  #include <linux/swap.h>

  #include <linux/types.h>
  #include <linux/fcntl.h>
  #include <linux/module.h>
  #include <linux/socket.h>
  #include <linux/sockios.h>

  #include <linux/igmp.h>

  #include <linux/inetdevice.h>

  #include <linux/in.h>
  #include <linux/errno.h>
  #include <linux/timer.h>
  #include <linux/mm.h>

  #include <linux/inet.h>

  #include <linux/netdevice.h>

  #include <linux/slab.h>

  #include <net/tcp_states.h>

  #include <linux/skbuff.h>
  #include <linux/proc_fs.h>
  #include <linux/seq_file.h>

  #include <net/net_namespace.h>

  #include <net/icmp.h>

  #include <net/inet_hashtables.h>

  #include <net/ip_tunnels.h>

  #include <net/route.h>

  #include <net/checksum.h>
  #include <net/xfrm.h>

  #include <trace/events/udp.h>

  #include <linux/static_key.h>

  #include <trace/events/skb.h>

  #include <net/busy_poll.h>

  #include "udp_impl.h"

  #include <net/sock_reuseport.h>

  #include <net/addrconf.h>

  #include <net/udp_tunnel.h>

  struct udp_table udp_table __read_mostly;

  EXPORT_SYMBOL(udp_table);

  long sysctl_udp_mem[3] __read_mostly;

  EXPORT_SYMBOL(sysctl_udp_mem);

  atomic_long_t udp_memory_allocated;

  EXPORT_SYMBOL(udp_memory_allocated);

  #define MAX_UDP_PORTS 65536
  #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN)

  static int udp_lib_lport_inuse(struct net *net, __u16 num,

  			       const struct udp_hslot *hslot,

  			       unsigned long *bitmap,

  			       struct sock *sk, unsigned int log)

  {

  	struct sock *sk2;

  	kuid_t uid = sock_i_uid(sk);

  	sk_for_each(sk2, &hslot->head) {

  		if (net_eq(sock_net(sk2), net) &&
  		    sk2 != sk &&

  		    (bitmap || udp_sk(sk2)->udp_port_hash == num) &&

  		    (!sk2->sk_reuse || !sk->sk_reuse) &&
  		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
  		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&

  		    inet_rcv_saddr_equal(sk, sk2, true)) {

  			if (sk2->sk_reuseport && sk->sk_reuseport &&
  			    !rcu_access_pointer(sk->sk_reuseport_cb) &&
  			    uid_eq(uid, sock_i_uid(sk2))) {
  				if (!bitmap)
  					return 0;
  			} else {
  				if (!bitmap)
  					return 1;
  				__set_bit(udp_sk(sk2)->udp_port_hash >> log,
  					  bitmap);
  			}

  		}

  	}

  	return 0;
  }

  /*
   * Note: we still hold spinlock of primary hash chain, so no other writer
   * can insert/delete a socket with local_port == num
   */
  static int udp_lib_lport_inuse2(struct net *net, __u16 num,

  				struct udp_hslot *hslot2,

  				struct sock *sk)

  {
  	struct sock *sk2;

  	kuid_t uid = sock_i_uid(sk);

  	int res = 0;
  
  	spin_lock(&hslot2->lock);

  	udp_portaddr_for_each_entry(sk2, &hslot2->head) {

  		if (net_eq(sock_net(sk2), net) &&
  		    sk2 != sk &&
  		    (udp_sk(sk2)->udp_port_hash == num) &&
  		    (!sk2->sk_reuse || !sk->sk_reuse) &&
  		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
  		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&

  		    inet_rcv_saddr_equal(sk, sk2, true)) {

  			if (sk2->sk_reuseport && sk->sk_reuseport &&
  			    !rcu_access_pointer(sk->sk_reuseport_cb) &&
  			    uid_eq(uid, sock_i_uid(sk2))) {
  				res = 0;
  			} else {
  				res = 1;
  			}

  			break;
  		}

  	}

  	spin_unlock(&hslot2->lock);
  	return res;
  }

  static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)

  {
  	struct net *net = sock_net(sk);

  	kuid_t uid = sock_i_uid(sk);
  	struct sock *sk2;

  	sk_for_each(sk2, &hslot->head) {

  		if (net_eq(sock_net(sk2), net) &&
  		    sk2 != sk &&
  		    sk2->sk_family == sk->sk_family &&
  		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&
  		    (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) &&
  		    (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
  		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&

  		    inet_rcv_saddr_equal(sk, sk2, false)) {

  			return reuseport_add_sock(sk, sk2,
  						  inet_rcv_saddr_any(sk));

  		}
  	}

  	return reuseport_alloc(sk, inet_rcv_saddr_any(sk));

  }

  /**

   *  udp_lib_get_port  -  UDP/-Lite port lookup for IPv4 and IPv6

   *
   *  @sk:          socket struct in question
   *  @snum:        port number to look up

   *  @hash2_nulladdr: AF-dependent hash value in secondary hash chains,

   *                   with NULL address

   */

  int udp_lib_get_port(struct sock *sk, unsigned short snum,

  		     unsigned int hash2_nulladdr)

  {

  	struct udp_hslot *hslot, *hslot2;

  	struct udp_table *udptable = sk->sk_prot->h.udp_table;

  	int    error = 1;

  	struct net *net = sock_net(sk);

  	if (!snum) {

  		int low, high, remaining;

  		unsigned int rand;

  		unsigned short first, last;
  		DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN);

  		inet_get_local_port_range(net, &low, &high);

  		remaining = (high - low) + 1;

  		rand = prandom_u32();

  		first = reciprocal_scale(rand, remaining) + low;

  		/*
  		 * force rand to be an odd multiple of UDP_HTABLE_SIZE
  		 */

  		rand = (rand | 1) * (udptable->mask + 1);

  		last = first + udptable->mask + 1;
  		do {

  			hslot = udp_hashslot(udptable, net, first);

  			bitmap_zero(bitmap, PORTS_PER_CHAIN);

  			spin_lock_bh(&hslot->lock);

  			udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,

  					    udptable->log);

  
  			snum = first;
  			/*
  			 * Iterate on all possible values of snum for this hash.
  			 * Using steps of an odd multiple of UDP_HTABLE_SIZE
  			 * give us randomization and full range coverage.
  			 */

  			do {

  				if (low <= snum && snum <= high &&

  				    !test_bit(snum >> udptable->log, bitmap) &&

  				    !inet_is_local_reserved_port(net, snum))

  					goto found;
  				snum += rand;
  			} while (snum != first);
  			spin_unlock_bh(&hslot->lock);

  			cond_resched();

  		} while (++first != last);

  		goto fail;

  	} else {

  		hslot = udp_hashslot(udptable, net, snum);

  		spin_lock_bh(&hslot->lock);

  		if (hslot->count > 10) {
  			int exist;
  			unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum;
  
  			slot2          &= udptable->mask;
  			hash2_nulladdr &= udptable->mask;
  
  			hslot2 = udp_hashslot2(udptable, slot2);
  			if (hslot->count < hslot2->count)
  				goto scan_primary_hash;

  			exist = udp_lib_lport_inuse2(net, snum, hslot2, sk);

  			if (!exist && (hash2_nulladdr != slot2)) {
  				hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
  				exist = udp_lib_lport_inuse2(net, snum, hslot2,

  							     sk);

  			}
  			if (exist)
  				goto fail_unlock;
  			else
  				goto found;
  		}
  scan_primary_hash:

  		if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0))

  			goto fail_unlock;
  	}

  found:

  	inet_sk(sk)->inet_num = snum;

  	udp_sk(sk)->udp_port_hash = snum;
  	udp_sk(sk)->udp_portaddr_hash ^= snum;

  	if (sk_unhashed(sk)) {

  		if (sk->sk_reuseport &&

  		    udp_reuseport_add_sock(sk, hslot)) {

  			inet_sk(sk)->inet_num = 0;
  			udp_sk(sk)->udp_port_hash = 0;
  			udp_sk(sk)->udp_portaddr_hash ^= snum;
  			goto fail_unlock;
  		}

  		sk_add_node_rcu(sk, &hslot->head);

  		hslot->count++;

  		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);

  
  		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
  		spin_lock(&hslot2->lock);

  		if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&

  		    sk->sk_family == AF_INET6)
  			hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node,
  					   &hslot2->head);

  		else

  			hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node,
  					   &hslot2->head);

  		hslot2->count++;
  		spin_unlock(&hslot2->lock);

  	}

  	sock_set_flag(sk, SOCK_RCU_FREE);

  	error = 0;

  fail_unlock:
  	spin_unlock_bh(&hslot->lock);

  fail:

  	return error;
  }

  EXPORT_SYMBOL(udp_lib_get_port);

  int udp_v4_get_port(struct sock *sk, unsigned short snum)

  {

  	unsigned int hash2_nulladdr =

  		ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum);

  	unsigned int hash2_partial =

  		ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_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 int compute_score(struct sock *sk, struct net *net,
  			 __be32 saddr, __be16 sport,

  			 __be32 daddr, unsigned short hnum,

  			 int dif, int sdif)

  {

  	int score;
  	struct inet_sock *inet;

  	bool dev_match;

  	if (!net_eq(sock_net(sk), net) ||
  	    udp_sk(sk)->udp_port_hash != hnum ||
  	    ipv6_only_sock(sk))
  		return -1;

  	if (sk->sk_rcv_saddr != daddr)
  		return -1;

  	score = (sk->sk_family == PF_INET) ? 2 : 1;

  	inet = inet_sk(sk);

  	if (inet->inet_daddr) {
  		if (inet->inet_daddr != saddr)
  			return -1;
  		score += 4;
  	}
  
  	if (inet->inet_dport) {
  		if (inet->inet_dport != sport)
  			return -1;
  		score += 4;
  	}

  	dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if,
  					dif, sdif);
  	if (!dev_match)
  		return -1;
  	score += 4;

  	if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id())

  		score++;

  	return score;
  }

  static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
  		       const __u16 lport, const __be32 faddr,
  		       const __be16 fport)

  {

  	static u32 udp_ehash_secret __read_mostly;
  
  	net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret));

  	return __inet_ehashfn(laddr, lport, faddr, fport,

  			      udp_ehash_secret + net_hash_mix(net));

  }

  /* called with rcu_read_lock() */

  static struct sock *udp4_lib_lookup2(struct net *net,

  				     __be32 saddr, __be16 sport,
  				     __be32 daddr, unsigned int hnum,

  				     int dif, int sdif,

  				     struct udp_hslot *hslot2,
  				     struct sk_buff *skb)

  {
  	struct sock *sk, *result;

  	int score, badness;

  	u32 hash = 0;

  	result = NULL;

  	badness = 0;

  	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {

  		score = compute_score(sk, net, saddr, sport,

  				      daddr, hnum, dif, sdif);

  		if (score > badness) {

  			if (sk->sk_reuseport &&
  			    sk->sk_state != TCP_ESTABLISHED) {

  				hash = udp_ehashfn(net, daddr, hnum,
  						   saddr, sport);

  				result = reuseport_select_sock(sk, hash, skb,

  							sizeof(struct udphdr));

  				if (result && !reuseport_has_conns(sk, false))

  					return result;

  			}

  			badness = score;
  			result = sk;

  		}
  	}

  	return result;
  }

  /* UDP is nearly always wildcards out the wazoo, it makes no sense to try
   * harder than this. -DaveM
   */

  struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,

  		__be16 sport, __be32 daddr, __be16 dport, int dif,
  		int sdif, struct udp_table *udptable, struct sk_buff *skb)

  {

  	struct sock *result;

  	unsigned short hnum = ntohs(dport);

  	unsigned int hash2, slot2;
  	struct udp_hslot *hslot2;

  	hash2 = ipv4_portaddr_hash(net, daddr, hnum);
  	slot2 = hash2 & udptable->mask;
  	hslot2 = &udptable->hash2[slot2];
  
  	result = udp4_lib_lookup2(net, saddr, sport,
  				  daddr, hnum, dif, sdif,

  				  hslot2, skb);

  	if (!result) {
  		hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum);

  		slot2 = hash2 & udptable->mask;
  		hslot2 = &udptable->hash2[slot2];

  
  		result = udp4_lib_lookup2(net, saddr, sport,

  					  htonl(INADDR_ANY), hnum, dif, sdif,

  					  hslot2, skb);

  	}

  	if (IS_ERR(result))

  		return NULL;

  	return result;
  }

  EXPORT_SYMBOL_GPL(__udp4_lib_lookup);

  static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb,
  						 __be16 sport, __be16 dport,

  						 struct udp_table *udptable)

  {
  	const struct iphdr *iph = ip_hdr(skb);

  	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,

  				 iph->daddr, dport, inet_iif(skb),

  				 inet_sdif(skb), udptable, skb);

  }

  struct sock *udp4_lib_lookup_skb(struct sk_buff *skb,
  				 __be16 sport, __be16 dport)
  {

  	const struct iphdr *iph = ip_hdr(skb);
  
  	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
  				 iph->daddr, dport, inet_iif(skb),
  				 inet_sdif(skb), &udp_table, NULL);

  }
  EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);

  /* Must be called under rcu_read_lock().
   * Does increment socket refcount.
   */

  #if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4)

  struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
  			     __be32 daddr, __be16 dport, int dif)
  {

  	struct sock *sk;
  
  	sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,

  			       dif, 0, &udp_table, NULL);

  	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))

  		sk = NULL;
  	return sk;

  }
  EXPORT_SYMBOL_GPL(udp4_lib_lookup);

  #endif

  static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk,
  				       __be16 loc_port, __be32 loc_addr,
  				       __be16 rmt_port, __be32 rmt_addr,

  				       int dif, int sdif, unsigned short hnum)

  {
  	struct inet_sock *inet = inet_sk(sk);
  
  	if (!net_eq(sock_net(sk), net) ||
  	    udp_sk(sk)->udp_port_hash != hnum ||
  	    (inet->inet_daddr && inet->inet_daddr != rmt_addr) ||
  	    (inet->inet_dport != rmt_port && inet->inet_dport) ||
  	    (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) ||
  	    ipv6_only_sock(sk) ||

  	    !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif))

  		return false;

  	if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif))

  		return false;
  	return true;
  }

  DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key);
  void udp_encap_enable(void)
  {

  	static_branch_inc(&udp_encap_needed_key);

  }
  EXPORT_SYMBOL(udp_encap_enable);

  /* Handler for tunnels with arbitrary destination ports: no socket lookup, go
   * through error handlers in encapsulations looking for a match.
   */
  static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info)
  {
  	int i;
  
  	for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) {
  		int (*handler)(struct sk_buff *skb, u32 info);

  		const struct ip_tunnel_encap_ops *encap;

  		encap = rcu_dereference(iptun_encaps[i]);
  		if (!encap)

  			continue;

  		handler = encap->err_handler;

  		if (handler && !handler(skb, 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 *__udp4_lib_err_encap(struct net *net,
  					 const struct iphdr *iph,
  					 struct udphdr *uh,
  					 struct udp_table *udptable,

  					 struct sk_buff *skb, u32 info)

  {

  	int network_offset, transport_offset;

  	struct sock *sk;

  	network_offset = skb_network_offset(skb);
  	transport_offset = skb_transport_offset(skb);
  
  	/* Network header needs to point to the outer IPv4 header inside ICMP */
  	skb_reset_network_header(skb);
  
  	/* Transport header needs to point to the UDP header */
  	skb_set_transport_header(skb, iph->ihl << 2);

  	sk = __udp4_lib_lookup(net, iph->daddr, uh->source,
  			       iph->saddr, uh->dest, skb->dev->ifindex, 0,
  			       udptable, NULL);
  	if (sk) {
  		int (*lookup)(struct sock *sk, struct sk_buff *skb);
  		struct udp_sock *up = udp_sk(sk);
  
  		lookup = READ_ONCE(up->encap_err_lookup);
  		if (!lookup || lookup(sk, skb))
  			sk = NULL;
  	}
  
  	if (!sk)
  		sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info));

  
  	skb_set_transport_header(skb, transport_offset);
  	skb_set_network_header(skb, network_offset);
  
  	return sk;
  }

  /*
   * This routine is called by the ICMP module when it gets some
   * sort of error condition.  If err < 0 then the socket should
   * be closed and the error returned to the user.  If err > 0
   * it's just the icmp type << 8 | icmp code.
   * Header points to the ip header of the error packet. We move
   * on past this. Then (as it used to claim before adjustment)
   * header points to the first 8 bytes of the udp header.  We need
   * to find the appropriate port.
   */

  int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)

  {
  	struct inet_sock *inet;

  	const struct iphdr *iph = (const struct iphdr *)skb->data;

  	struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2));

  	const int type = icmp_hdr(skb)->type;
  	const int code = icmp_hdr(skb)->code;

  	bool tunnel = false;

  	struct sock *sk;
  	int harderr;
  	int err;

  	struct net *net = dev_net(skb->dev);

  	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,

  			       iph->saddr, uh->source, skb->dev->ifindex,
  			       inet_sdif(skb), udptable, NULL);

  	if (!sk) {

  		/* No socket for error: try tunnels before discarding */

  		sk = ERR_PTR(-ENOENT);
  		if (static_branch_unlikely(&udp_encap_needed_key)) {
  			sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb,
  						  info);
  			if (!sk)
  				return 0;
  		}

  		if (IS_ERR(sk)) {

  			__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);

  			return PTR_ERR(sk);

  		}

  		tunnel = true;

  	}
  
  	err = 0;
  	harderr = 0;
  	inet = inet_sk(sk);
  
  	switch (type) {
  	default:
  	case ICMP_TIME_EXCEEDED:
  		err = EHOSTUNREACH;
  		break;
  	case ICMP_SOURCE_QUENCH:
  		goto out;
  	case ICMP_PARAMETERPROB:
  		err = EPROTO;
  		harderr = 1;
  		break;
  	case ICMP_DEST_UNREACH:
  		if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */

  			ipv4_sk_update_pmtu(skb, sk, info);

  			if (inet->pmtudisc != IP_PMTUDISC_DONT) {
  				err = EMSGSIZE;
  				harderr = 1;
  				break;
  			}
  			goto out;
  		}
  		err = EHOSTUNREACH;
  		if (code <= NR_ICMP_UNREACH) {
  			harderr = icmp_err_convert[code].fatal;
  			err = icmp_err_convert[code].errno;
  		}
  		break;

  	case ICMP_REDIRECT:
  		ipv4_sk_redirect(skb, sk);

  		goto out;

  	}
  
  	/*
  	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
  	 *	4.1.3.3.
  	 */

  	if (tunnel) {
  		/* ...not for tunnels though: we don't have a sending socket */
  		goto out;
  	}

  	if (!inet->recverr) {
  		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
  			goto out;

  	} else

  		ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1));

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

  	return 0;

  }

  int udp_err(struct sk_buff *skb, u32 info)

  {

  	return __udp4_lib_err(skb, info, &udp_table);

  }
  
  /*
   * Throw away all pending data and cancel the corking. Socket is locked.
   */

  void udp_flush_pending_frames(struct sock *sk)

  {
  	struct udp_sock *up = udp_sk(sk);
  
  	if (up->pending) {
  		up->len = 0;
  		up->pending = 0;
  		ip_flush_pending_frames(sk);
  	}
  }

  EXPORT_SYMBOL(udp_flush_pending_frames);

  
  /**

   * 	udp4_hwcsum  -  handle outgoing HW checksumming

   * 	@skb: 	sk_buff containing the filled-in UDP header
   * 	        (checksum field must be zeroed out)

   *	@src:	source IP address
   *	@dst:	destination IP address

   */

  void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)

  {

  	struct udphdr *uh = udp_hdr(skb);

  	int offset = skb_transport_offset(skb);
  	int len = skb->len - offset;
  	int hlen = len;

  	__wsum csum = 0;

  	if (!skb_has_frag_list(skb)) {

  		/*
  		 * 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_tcpudp_magic(src, dst, len,
  					       IPPROTO_UDP, 0);

  	} else {

  		struct sk_buff *frags;

  		/*
  		 * 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
  		 */

  		skb_walk_frags(skb, frags) {

  			csum = csum_add(csum, frags->csum);
  			hlen -= frags->len;

  		}

  		csum = skb_checksum(skb, offset, hlen, csum);

  		skb->ip_summed = CHECKSUM_NONE;

  		uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum);
  		if (uh->check == 0)
  			uh->check = CSUM_MANGLED_0;
  	}
  }

  EXPORT_SYMBOL_GPL(udp4_hwcsum);

  /* Function to set UDP checksum for an IPv4 UDP packet. This is intended
   * for the simple case like when setting the checksum for a UDP tunnel.
   */
  void udp_set_csum(bool nocheck, struct sk_buff *skb,
  		  __be32 saddr, __be32 daddr, int len)
  {
  	struct udphdr *uh = udp_hdr(skb);

  	if (nocheck) {

  		uh->check = 0;

  	} else if (skb_is_gso(skb)) {

  		uh->check = ~udp_v4_check(len, saddr, daddr, 0);

  	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
  		uh->check = 0;
  		uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb));
  		if (uh->check == 0)
  			uh->check = CSUM_MANGLED_0;

  	} else {

  		skb->ip_summed = CHECKSUM_PARTIAL;
  		skb->csum_start = skb_transport_header(skb) - skb->head;
  		skb->csum_offset = offsetof(struct udphdr, check);
  		uh->check = ~udp_v4_check(len, saddr, daddr, 0);

  	}
  }
  EXPORT_SYMBOL(udp_set_csum);

  static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4,
  			struct inet_cork *cork)

  {

  	struct sock *sk = skb->sk;

  	struct inet_sock *inet = inet_sk(sk);

  	struct udphdr *uh;
  	int err = 0;
  	int is_udplite = IS_UDPLITE(sk);

  	int offset = skb_transport_offset(skb);
  	int len = skb->len - offset;

  	int datalen = len - sizeof(*uh);

  	__wsum csum = 0;

  	/*
  	 * Create a UDP header
  	 */
  	uh = udp_hdr(skb);

  	uh->source = inet->inet_sport;

  	uh->dest = fl4->fl4_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 + cork->gso_size > cork->fragsize) {
  			kfree_skb(skb);

  			return -EINVAL;

  		}
  		if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) {
  			kfree_skb(skb);

  			return -EINVAL;

  		}
  		if (sk->sk_no_check_tx) {
  			kfree_skb(skb);

  			return -EINVAL;

  		}

  		if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite ||

  		    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);
  		}

  		goto csum_partial;

  	}

  	if (is_udplite)  				 /*     UDP-Lite      */

  		csum = udplite_csum(skb);

  	else if (sk->sk_no_check_tx) {			 /* UDP csum off */

  
  		skb->ip_summed = CHECKSUM_NONE;
  		goto send;
  
  	} else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */

  csum_partial:

  		udp4_hwcsum(skb, fl4->saddr, fl4->daddr);

  		goto send;

  	} else
  		csum = udp_csum(skb);

  
  	/* add protocol-dependent pseudo-header */

  	uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len,

  				      sk->sk_protocol, csum);

  	if (uh->check == 0)
  		uh->check = CSUM_MANGLED_0;
  
  send:

  	err = ip_send_skb(sock_net(sk), skb);

  	if (err) {
  		if (err == -ENOBUFS && !inet->recverr) {

  			UDP_INC_STATS(sock_net(sk),
  				      UDP_MIB_SNDBUFERRORS, is_udplite);

  			err = 0;
  		}
  	} else

  		UDP_INC_STATS(sock_net(sk),
  			      UDP_MIB_OUTDATAGRAMS, is_udplite);

  	return err;
  }
  
  /*
   * Push out all pending data as one UDP datagram. Socket is locked.
   */

  int udp_push_pending_frames(struct sock *sk)

  {
  	struct udp_sock  *up = udp_sk(sk);
  	struct inet_sock *inet = inet_sk(sk);

  	struct flowi4 *fl4 = &inet->cork.fl.u.ip4;

  	struct sk_buff *skb;
  	int err = 0;

  	skb = ip_finish_skb(sk, fl4);

  	if (!skb)
  		goto out;

  	err = udp_send_skb(skb, fl4, &inet->cork.base);

  out:
  	up->len = 0;
  	up->pending = 0;

  	return err;
  }

  EXPORT_SYMBOL(udp_push_pending_frames);

  static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size)
  {
  	switch (cmsg->cmsg_type) {
  	case UDP_SEGMENT:
  		if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16)))
  			return -EINVAL;
  		*gso_size = *(__u16 *)CMSG_DATA(cmsg);
  		return 0;
  	default:
  		return -EINVAL;
  	}
  }
  
  int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size)
  {
  	struct cmsghdr *cmsg;
  	bool need_ip = false;
  	int err;
  
  	for_each_cmsghdr(cmsg, msg) {
  		if (!CMSG_OK(msg, cmsg))
  			return -EINVAL;
  
  		if (cmsg->cmsg_level != SOL_UDP) {
  			need_ip = true;
  			continue;
  		}
  
  		err = __udp_cmsg_send(cmsg, gso_size);
  		if (err)
  			return err;
  	}
  
  	return need_ip;
  }
  EXPORT_SYMBOL_GPL(udp_cmsg_send);

  int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)

  {
  	struct inet_sock *inet = inet_sk(sk);
  	struct udp_sock *up = udp_sk(sk);

  	DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);

  	struct flowi4 fl4_stack;

  	struct flowi4 *fl4;

  	int ulen = len;
  	struct ipcm_cookie ipc;
  	struct rtable *rt = NULL;
  	int free = 0;
  	int connected = 0;
  	__be32 daddr, faddr, saddr;
  	__be16 dport;
  	u8  tos;
  	int err, is_udplite = IS_UDPLITE(sk);
  	int corkreq = up->corkflag || msg->msg_flags&MSG_MORE;
  	int (*getfrag)(void *, char *, int, int, int, struct sk_buff *);

  	struct sk_buff *skb;

  	struct ip_options_data opt_copy;

  
  	if (len > 0xFFFF)
  		return -EMSGSIZE;
  
  	/*
  	 *	Check the flags.
  	 */

  	if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */

  		return -EOPNOTSUPP;

  	getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag;

  	fl4 = &inet->cork.fl.u.ip4;

  	if (up->pending) {
  		/*
  		 * 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_INET)) {
  				release_sock(sk);
  				return -EINVAL;
  			}
  			goto do_append_data;
  		}
  		release_sock(sk);
  	}
  	ulen += sizeof(struct udphdr);
  
  	/*
  	 *	Get and verify the address.
  	 */

  	if (usin) {

  		if (msg->msg_namelen < sizeof(*usin))
  			return -EINVAL;
  		if (usin->sin_family != AF_INET) {
  			if (usin->sin_family != AF_UNSPEC)
  				return -EAFNOSUPPORT;
  		}
  
  		daddr = usin->sin_addr.s_addr;
  		dport = usin->sin_port;
  		if (dport == 0)
  			return -EINVAL;
  	} else {
  		if (sk->sk_state != TCP_ESTABLISHED)
  			return -EDESTADDRREQ;

  		daddr = inet->inet_daddr;
  		dport = inet->inet_dport;

  		/* Open fast path for connected socket.
  		   Route will not be used, if at least one option is set.
  		 */
  		connected = 1;
  	}

  	ipcm_init_sk(&ipc, inet);

  	ipc.gso_size = up->gso_size;

  	if (msg->msg_controllen) {

  		err = udp_cmsg_send(sk, msg, &ipc.gso_size);
  		if (err > 0)
  			err = ip_cmsg_send(sk, msg, &ipc,
  					   sk->sk_family == AF_INET6);
  		if (unlikely(err < 0)) {

  			kfree(ipc.opt);

  			return err;

  		}

  		if (ipc.opt)
  			free = 1;
  		connected = 0;
  	}

  	if (!ipc.opt) {
  		struct ip_options_rcu *inet_opt;
  
  		rcu_read_lock();
  		inet_opt = rcu_dereference(inet->inet_opt);
  		if (inet_opt) {
  			memcpy(&opt_copy, inet_opt,
  			       sizeof(*inet_opt) + inet_opt->opt.optlen);
  			ipc.opt = &opt_copy.opt;
  		}
  		rcu_read_unlock();
  	}

  	if (cgroup_bpf_enabled && !connected) {
  		err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk,
  					    (struct sockaddr *)usin, &ipc.addr);
  		if (err)
  			goto out_free;
  		if (usin) {
  			if (usin->sin_port == 0) {
  				/* BPF program set invalid port. Reject it. */
  				err = -EINVAL;
  				goto out_free;
  			}
  			daddr = usin->sin_addr.s_addr;
  			dport = usin->sin_port;
  		}
  	}

  	saddr = ipc.addr;
  	ipc.addr = faddr = daddr;

  	if (ipc.opt && ipc.opt->opt.srr) {

  		if (!daddr) {
  			err = -EINVAL;
  			goto out_free;
  		}

  		faddr = ipc.opt->opt.faddr;

  		connected = 0;
  	}

  	tos = get_rttos(&ipc, inet);

  	if (sock_flag(sk, SOCK_LOCALROUTE) ||
  	    (msg->msg_flags & MSG_DONTROUTE) ||

  	    (ipc.opt && ipc.opt->opt.is_strictroute)) {

  		tos |= RTO_ONLINK;
  		connected = 0;
  	}
  
  	if (ipv4_is_multicast(daddr)) {

  		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))

  			ipc.oif = inet->mc_index;
  		if (!saddr)
  			saddr = inet->mc_addr;
  		connected = 0;

  	} else if (!ipc.oif) {

  		ipc.oif = inet->uc_index;

  	} else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
  		/* oif is set, packet is to local broadcast and
  		 * and uc_index is set. oif is most likely set
  		 * by sk_bound_dev_if. If uc_index != oif check if the
  		 * oif is an L3 master and uc_index is an L3 slave.
  		 * If so, we want to allow the send using the uc_index.
  		 */
  		if (ipc.oif != inet->uc_index &&
  		    ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),
  							      inet->uc_index)) {
  			ipc.oif = inet->uc_index;
  		}
  	}

  
  	if (connected)

  		rt = (struct rtable *)sk_dst_check(sk, 0);

  	if (!rt) {

  		struct net *net = sock_net(sk);

  		__u8 flow_flags = inet_sk_flowi_flags(sk);

  		fl4 = &fl4_stack;

  		flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, tos,

  				   RT_SCOPE_UNIVERSE, sk->sk_protocol,

  				   flow_flags,

  				   faddr, saddr, dport, inet->inet_sport,
  				   sk->sk_uid);

  		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
  		rt = ip_route_output_flow(net, fl4, sk);

  		if (IS_ERR(rt)) {
  			err = PTR_ERR(rt);

  			rt = NULL;

  			if (err == -ENETUNREACH)

  				IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);

  			goto out;
  		}
  
  		err = -EACCES;
  		if ((rt->rt_flags & RTCF_BROADCAST) &&
  		    !sock_flag(sk, SOCK_BROADCAST))
  			goto out;
  		if (connected)

  			sk_dst_set(sk, dst_clone(&rt->dst));

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

  	saddr = fl4->saddr;

  	if (!ipc.addr)

  		daddr = ipc.addr = fl4->daddr;

  	/* Lockless fast path for the non-corking case. */
  	if (!corkreq) {

  		struct inet_cork cork;

  		skb = ip_make_skb(sk, fl4, getfrag, msg, ulen,

  				  sizeof(struct udphdr), &ipc, &rt,

  				  &cork, msg->msg_flags);

  		err = PTR_ERR(skb);

  		if (!IS_ERR_OR_NULL(skb))

  			err = udp_send_skb(skb, fl4, &cork);

  		goto out;
  	}

  	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("socket already corked
  ");

  		err = -EINVAL;
  		goto out;
  	}
  	/*
  	 *	Now cork the socket to pend data.
  	 */

  	fl4 = &inet->cork.fl.u.ip4;
  	fl4->daddr = daddr;
  	fl4->saddr = saddr;

  	fl4->fl4_dport = dport;
  	fl4->fl4_sport = inet->inet_sport;

  	up->pending = AF_INET;
  
  do_append_data:
  	up->len += ulen;

  	err = ip_append_data(sk, fl4, getfrag, msg, ulen,

  			     sizeof(struct udphdr), &ipc, &rt,
  			     corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags);

  	if (err)
  		udp_flush_pending_frames(sk);
  	else if (!corkreq)
  		err = udp_push_pending_frames(sk);
  	else if (unlikely(skb_queue_empty(&sk->sk_write_queue)))
  		up->pending = 0;
  	release_sock(sk);
  
  out:
  	ip_rt_put(rt);

  out_free:

  	if (free)
  		kfree(ipc.opt);
  	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)) {

  		UDP_INC_STATS(sock_net(sk),
  			      UDP_MIB_SNDBUFERRORS, is_udplite);

  	}
  	return err;
  
  do_confirm:

  	if (msg->msg_flags & MSG_PROBE)
  		dst_confirm_neigh(&rt->dst, &fl4->daddr);

  	if (!(msg->msg_flags&MSG_PROBE) || len)
  		goto back_from_confirm;
  	err = 0;
  	goto out;
  }

  EXPORT_SYMBOL(udp_sendmsg);

  
  int udp_sendpage(struct sock *sk, struct page *page, int offset,
  		 size_t size, int flags)
  {

  	struct inet_sock *inet = inet_sk(sk);

  	struct udp_sock *up = udp_sk(sk);
  	int ret;

  	if (flags & MSG_SENDPAGE_NOTLAST)
  		flags |= MSG_MORE;

  	if (!up->pending) {
  		struct msghdr msg = {	.msg_flags = flags|MSG_MORE };
  
  		/* Call udp_sendmsg to specify destination address which
  		 * sendpage interface can't pass.
  		 * This will succeed only when the socket is connected.
  		 */

  		ret = udp_sendmsg(sk, &msg, 0);

  		if (ret < 0)
  			return ret;
  	}
  
  	lock_sock(sk);
  
  	if (unlikely(!up->pending)) {
  		release_sock(sk);

  		net_dbg_ratelimited("cork failed
  ");

  		return -EINVAL;
  	}

  	ret = ip_append_page(sk, &inet->cork.fl.u.ip4,
  			     page, offset, size, flags);

  	if (ret == -EOPNOTSUPP) {
  		release_sock(sk);
  		return sock_no_sendpage(sk->sk_socket, page, offset,
  					size, flags);
  	}
  	if (ret < 0) {
  		udp_flush_pending_frames(sk);
  		goto out;
  	}
  
  	up->len += size;
  	if (!(up->corkflag || (flags&MSG_MORE)))
  		ret = udp_push_pending_frames(sk);
  	if (!ret)
  		ret = size;
  out:
  	release_sock(sk);
  	return ret;
  }

  #define UDP_SKB_IS_STATELESS 0x80000000

  /* all head states (dst, sk, nf conntrack) except skb extensions are
   * cleared by udp_rcv().
   *
   * We need to preserve secpath, if present, to eventually process
   * IP_CMSG_PASSSEC at recvmsg() time.
   *
   * Other extensions can be cleared.
   */
  static bool udp_try_make_stateless(struct sk_buff *skb)
  {
  	if (!skb_has_extensions(skb))
  		return true;
  
  	if (!secpath_exists(skb)) {
  		skb_ext_reset(skb);
  		return true;
  	}
  
  	return false;
  }

  static void udp_set_dev_scratch(struct sk_buff *skb)
  {

  	struct udp_dev_scratch *scratch = udp_skb_scratch(skb);

  
  	BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long));

  	scratch->_tsize_state = skb->truesize;
  #if BITS_PER_LONG == 64

  	scratch->len = skb->len;
  	scratch->csum_unnecessary = !!skb_csum_unnecessary(skb);
  	scratch->is_linear = !skb_is_nonlinear(skb);

  #endif

  	if (udp_try_make_stateless(skb))

  		scratch->_tsize_state |= UDP_SKB_IS_STATELESS;

  }

  static void udp_skb_csum_unnecessary_set(struct sk_buff *skb)
  {
  	/* We come here after udp_lib_checksum_complete() returned 0.
  	 * This means that __skb_checksum_complete() might have
  	 * set skb->csum_valid to 1.
  	 * On 64bit platforms, we can set csum_unnecessary
  	 * to true, but only if the skb is not shared.
  	 */
  #if BITS_PER_LONG == 64
  	if (!skb_shared(skb))
  		udp_skb_scratch(skb)->csum_unnecessary = true;
  #endif
  }

  static int udp_skb_truesize(struct sk_buff *skb)
  {

  	return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS;

  }

  static bool udp_skb_has_head_state(struct sk_buff *skb)

  {

  	return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS);

  }

  /* fully reclaim rmem/fwd memory allocated for skb */

  static void udp_rmem_release(struct sock *sk, int size, int partial,
  			     bool rx_queue_lock_held)

  {

  	struct udp_sock *up = udp_sk(sk);

  	struct sk_buff_head *sk_queue;

  	int amt;

  	if (likely(partial)) {
  		up->forward_deficit += size;
  		size = up->forward_deficit;

  		if (size < (sk->sk_rcvbuf >> 2) &&
  		    !skb_queue_empty(&up->reader_queue))

  			return;
  	} else {
  		size += up->forward_deficit;
  	}
  	up->forward_deficit = 0;

  	/* acquire the sk_receive_queue for fwd allocated memory scheduling,
  	 * if the called don't held it already
  	 */

  	sk_queue = &sk->sk_receive_queue;

  	if (!rx_queue_lock_held)
  		spin_lock(&sk_queue->lock);

  	sk->sk_forward_alloc += size;
  	amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1);
  	sk->sk_forward_alloc -= amt;

  
  	if (amt)
  		__sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);

  
  	atomic_sub(size, &sk->sk_rmem_alloc);

  
  	/* this can save us from acquiring the rx queue lock on next receive */
  	skb_queue_splice_tail_init(sk_queue, &up->reader_queue);

  	if (!rx_queue_lock_held)
  		spin_unlock(&sk_queue->lock);

  }

  /* Note: called with reader_queue.lock held.

   * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch
   * This avoids a cache line miss while receive_queue lock is held.
   * Look at __udp_enqueue_schedule_skb() to find where this copy is done.
   */

  void udp_skb_destructor(struct sock *sk, struct sk_buff *skb)

  {

  	prefetch(&skb->data);
  	udp_rmem_release(sk, udp_skb_truesize(skb), 1, false);

  }

  EXPORT_SYMBOL(udp_skb_destructor);

  /* as above, but the caller held the rx queue lock, too */

  static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb)

  {

  	prefetch(&skb->data);
  	udp_rmem_release(sk, udp_skb_truesize(skb), 1, true);

  }

  /* Idea of busylocks is to let producers grab an extra spinlock
   * to relieve pressure on the receive_queue spinlock shared by consumer.
   * Under flood, this means that only one producer can be in line
   * trying to acquire the receive_queue spinlock.
   * These busylock can be allocated on a per cpu manner, instead of a
   * per socket one (that would consume a cache line per socket)
   */
  static int udp_busylocks_log __read_mostly;
  static spinlock_t *udp_busylocks __read_mostly;
  
  static spinlock_t *busylock_acquire(void *ptr)
  {
  	spinlock_t *busy;
  
  	busy = udp_busylocks + hash_ptr(ptr, udp_busylocks_log);
  	spin_lock(busy);
  	return busy;
  }
  
  static void busylock_release(spinlock_t *busy)
  {
  	if (busy)
  		spin_unlock(busy);
  }

  int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
  {
  	struct sk_buff_head *list = &sk->sk_receive_queue;
  	int rmem, delta, amt, err = -ENOMEM;

  	spinlock_t *busy = NULL;

  	int size;

  
  	/* try to avoid the costly atomic add/sub pair when the receive
  	 * queue is full; always allow at least a packet
  	 */
  	rmem = atomic_read(&sk->sk_rmem_alloc);

  	if (rmem > sk->sk_rcvbuf)

  		goto drop;

  	/* Under mem pressure, it might be helpful to help udp_recvmsg()
  	 * having linear skbs :
  	 * - Reduce memory overhead and thus increase receive queue capacity
  	 * - Less cache line misses at copyout() time
  	 * - Less work at consume_skb() (less alien page frag freeing)
  	 */

  	if (rmem > (sk->sk_rcvbuf >> 1)) {

  		skb_condense(skb);

  
  		busy = busylock_acquire(sk);
  	}

  	size = skb->truesize;

  	udp_set_dev_scratch(skb);

  	/* we drop only if the receive buf is full and the receive
  	 * queue contains some other skb
  	 */
  	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);

  	if (rmem > (size + (unsigned int)sk->sk_rcvbuf))

  		goto uncharge_drop;
  
  	spin_lock(&list->lock);
  	if (size >= sk->sk_forward_alloc) {
  		amt = sk_mem_pages(size);
  		delta = amt << SK_MEM_QUANTUM_SHIFT;
  		if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
  			err = -ENOBUFS;
  			spin_unlock(&list->lock);
  			goto uncharge_drop;
  		}
  
  		sk->sk_forward_alloc += delta;
  	}
  
  	sk->sk_forward_alloc -= size;

  	/* no need to setup a destructor, we will explicitly release the
  	 * forward allocated memory on dequeue
  	 */

  	sock_skb_set_dropcount(sk, skb);
  
  	__skb_queue_tail(list, skb);
  	spin_unlock(&list->lock);
  
  	if (!sock_flag(sk, SOCK_DEAD))
  		sk->sk_data_ready(sk);

  	busylock_release(busy);

  	return 0;
  
  uncharge_drop:
  	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
  
  drop:
  	atomic_inc(&sk->sk_drops);

  	busylock_release(busy);

  	return err;
  }
  EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);

  void udp_destruct_sock(struct sock *sk)

  {
  	/* reclaim completely the forward allocated memory */

  	struct udp_sock *up = udp_sk(sk);

  	unsigned int total = 0;
  	struct sk_buff *skb;

  	skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue);
  	while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) {

  		total += skb->truesize;
  		kfree_skb(skb);
  	}

  	udp_rmem_release(sk, total, 0, true);

  	inet_sock_destruct(sk);
  }

  EXPORT_SYMBOL_GPL(udp_destruct_sock);

  
  int udp_init_sock(struct sock *sk)
  {

  	skb_queue_head_init(&udp_sk(sk)->reader_queue);

  	sk->sk_destruct = udp_destruct_sock;
  	return 0;
  }
  EXPORT_SYMBOL_GPL(udp_init_sock);
  
  void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
  {
  	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
  		bool slow = lock_sock_fast(sk);
  
  		sk_peek_offset_bwd(sk, len);
  		unlock_sock_fast(sk, slow);
  	}

  	if (!skb_unref(skb))
  		return;

  	/* In the more common cases we cleared the head states previously,
  	 * see __udp_queue_rcv_skb().

  	 */

  	if (unlikely(udp_skb_has_head_state(skb)))

  		skb_release_head_state(skb);

  	__consume_stateless_skb(skb);

  }
  EXPORT_SYMBOL_GPL(skb_consume_udp);

  static struct sk_buff *__first_packet_length(struct sock *sk,
  					     struct sk_buff_head *rcvq,
  					     int *total)
  {
  	struct sk_buff *skb;

  	while ((skb = skb_peek(rcvq)) != NULL) {
  		if (udp_lib_checksum_complete(skb)) {
  			__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS,
  					IS_UDPLITE(sk));
  			__UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS,
  					IS_UDPLITE(sk));
  			atomic_inc(&sk->sk_drops);
  			__skb_unlink(skb, rcvq);
  			*total += skb->truesize;
  			kfree_skb(skb);
  		} else {

  			udp_skb_csum_unnecessary_set(skb);

  			break;
  		}

  	}
  	return skb;
  }

  /**
   *	first_packet_length	- return length of first packet in receive queue
   *	@sk: socket
   *
   *	Drops all bad checksum frames, until a valid one is found.

   *	Returns the length of found skb, or -1 if none is found.

   */

  static int first_packet_length(struct sock *sk)

  {

  	struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue;
  	struct sk_buff_head *sk_queue = &sk->sk_receive_queue;

  	struct sk_buff *skb;

  	int total = 0;

  	int res;

  	spin_lock_bh(&rcvq->lock);

  	skb = __first_packet_length(sk, rcvq, &total);

  	if (!skb && !skb_queue_empty_lockless(sk_queue)) {

  		spin_lock(&sk_queue->lock);
  		skb_queue_splice_tail_init(sk_queue, rcvq);
  		spin_unlock(&sk_queue->lock);
  
  		skb = __first_packet_length(sk, rcvq, &total);

  	}

  	res = skb ? skb->len : -1;

  	if (total)