/* Connection state tracking for netfilter.  This is separated from,
     but required by, the NAT layer; it can also be used by an iptables
     extension. */
  
  /* (C) 1999-2001 Paul `Rusty' Russell

   * (C) 2002-2006 Netfilter Core Team <coreteam@netfilter.org>

   * (C) 2003,2004 USAGI/WIDE Project <http://www.linux-ipv6.org>

   * (C) 2005-2012 Patrick McHardy <kaber@trash.net>

   *
   * This program is free software; you can redistribute it and/or modify
   * it under the terms of the GNU General Public License version 2 as
   * published by the Free Software Foundation.

   */

  #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

  #include <linux/types.h>
  #include <linux/netfilter.h>
  #include <linux/module.h>

  #include <linux/sched.h>

  #include <linux/skbuff.h>
  #include <linux/proc_fs.h>
  #include <linux/vmalloc.h>
  #include <linux/stddef.h>
  #include <linux/slab.h>
  #include <linux/random.h>
  #include <linux/jhash.h>
  #include <linux/err.h>
  #include <linux/percpu.h>
  #include <linux/moduleparam.h>
  #include <linux/notifier.h>
  #include <linux/kernel.h>
  #include <linux/netdevice.h>
  #include <linux/socket.h>

  #include <linux/mm.h>

  #include <linux/nsproxy.h>

  #include <linux/rculist_nulls.h>

  #include <net/netfilter/nf_conntrack.h>

  #include <net/netfilter/nf_conntrack_l4proto.h>

  #include <net/netfilter/nf_conntrack_expect.h>

  #include <net/netfilter/nf_conntrack_helper.h>

  #include <net/netfilter/nf_conntrack_seqadj.h>

  #include <net/netfilter/nf_conntrack_core.h>

  #include <net/netfilter/nf_conntrack_extend.h>

  #include <net/netfilter/nf_conntrack_acct.h>

  #include <net/netfilter/nf_conntrack_ecache.h>

  #include <net/netfilter/nf_conntrack_zones.h>

  #include <net/netfilter/nf_conntrack_timestamp.h>

  #include <net/netfilter/nf_conntrack_timeout.h>

  #include <net/netfilter/nf_conntrack_labels.h>

  #include <net/netfilter/nf_conntrack_synproxy.h>

  #include <net/netfilter/nf_nat.h>

  #include <net/netfilter/nf_nat_core.h>

  #include <net/netfilter/nf_nat_helper.h>

  #include <net/netns/hash.h>

  #include <net/ip.h>

  #include "nf_internals.h"

  __cacheline_aligned_in_smp spinlock_t nf_conntrack_locks[CONNTRACK_LOCKS];
  EXPORT_SYMBOL_GPL(nf_conntrack_locks);

  __cacheline_aligned_in_smp DEFINE_SPINLOCK(nf_conntrack_expect_lock);
  EXPORT_SYMBOL_GPL(nf_conntrack_expect_lock);

  struct hlist_nulls_head *nf_conntrack_hash __read_mostly;
  EXPORT_SYMBOL_GPL(nf_conntrack_hash);

  struct conntrack_gc_work {
  	struct delayed_work	dwork;
  	u32			last_bucket;
  	bool			exiting;

  	bool			early_drop;

  	long			next_gc_run;

  };

  static __read_mostly struct kmem_cache *nf_conntrack_cachep;

  static __read_mostly spinlock_t nf_conntrack_locks_all_lock;

  static __read_mostly DEFINE_SPINLOCK(nf_conntrack_locks_all_lock);

  static __read_mostly bool nf_conntrack_locks_all;

  /* every gc cycle scans at most 1/GC_MAX_BUCKETS_DIV part of table */

  #define GC_MAX_BUCKETS_DIV	128u
  /* upper bound of full table scan */
  #define GC_MAX_SCAN_JIFFIES	(16u * HZ)
  /* desired ratio of entries found to be expired */
  #define GC_EVICT_RATIO	50u

  
  static struct conntrack_gc_work conntrack_gc_work;

  void nf_conntrack_lock(spinlock_t *lock) __acquires(lock)
  {

  	/* 1) Acquire the lock */

  	spin_lock(lock);

  	/* 2) read nf_conntrack_locks_all, with ACQUIRE semantics
  	 * It pairs with the smp_store_release() in nf_conntrack_all_unlock()
  	 */
  	if (likely(smp_load_acquire(&nf_conntrack_locks_all) == false))
  		return;
  
  	/* fast path failed, unlock */
  	spin_unlock(lock);
  
  	/* Slow path 1) get global lock */
  	spin_lock(&nf_conntrack_locks_all_lock);
  
  	/* Slow path 2) get the lock we want */
  	spin_lock(lock);
  
  	/* Slow path 3) release the global lock */
  	spin_unlock(&nf_conntrack_locks_all_lock);

  }
  EXPORT_SYMBOL_GPL(nf_conntrack_lock);

  static void nf_conntrack_double_unlock(unsigned int h1, unsigned int h2)
  {
  	h1 %= CONNTRACK_LOCKS;
  	h2 %= CONNTRACK_LOCKS;
  	spin_unlock(&nf_conntrack_locks[h1]);
  	if (h1 != h2)
  		spin_unlock(&nf_conntrack_locks[h2]);
  }
  
  /* return true if we need to recompute hashes (in case hash table was resized) */
  static bool nf_conntrack_double_lock(struct net *net, unsigned int h1,
  				     unsigned int h2, unsigned int sequence)
  {
  	h1 %= CONNTRACK_LOCKS;
  	h2 %= CONNTRACK_LOCKS;
  	if (h1 <= h2) {

  		nf_conntrack_lock(&nf_conntrack_locks[h1]);

  		if (h1 != h2)
  			spin_lock_nested(&nf_conntrack_locks[h2],
  					 SINGLE_DEPTH_NESTING);
  	} else {

  		nf_conntrack_lock(&nf_conntrack_locks[h2]);

  		spin_lock_nested(&nf_conntrack_locks[h1],
  				 SINGLE_DEPTH_NESTING);
  	}

  	if (read_seqcount_retry(&nf_conntrack_generation, sequence)) {

  		nf_conntrack_double_unlock(h1, h2);
  		return true;
  	}
  	return false;
  }
  
  static void nf_conntrack_all_lock(void)
  {
  	int i;

  	spin_lock(&nf_conntrack_locks_all_lock);

  	nf_conntrack_locks_all = true;

  	for (i = 0; i < CONNTRACK_LOCKS; i++) {

  		spin_lock(&nf_conntrack_locks[i]);
  
  		/* This spin_unlock provides the "release" to ensure that
  		 * nf_conntrack_locks_all==true is visible to everyone that
  		 * acquired spin_lock(&nf_conntrack_locks[]).
  		 */
  		spin_unlock(&nf_conntrack_locks[i]);

  	}

  }
  
  static void nf_conntrack_all_unlock(void)
  {

  	/* All prior stores must be complete before we clear

  	 * 'nf_conntrack_locks_all'. Otherwise nf_conntrack_lock()
  	 * might observe the false value but not the entire

  	 * critical section.
  	 * It pairs with the smp_load_acquire() in nf_conntrack_lock()

  	 */
  	smp_store_release(&nf_conntrack_locks_all, false);

  	spin_unlock(&nf_conntrack_locks_all_lock);

  }

  unsigned int nf_conntrack_htable_size __read_mostly;

  EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);

  unsigned int nf_conntrack_max __read_mostly;

  EXPORT_SYMBOL_GPL(nf_conntrack_max);

  seqcount_t nf_conntrack_generation __read_mostly;

  static unsigned int nf_conntrack_hash_rnd __read_mostly;

  static u32 hash_conntrack_raw(const struct nf_conntrack_tuple *tuple,
  			      const struct net *net)

  {

  	unsigned int n;

  	u32 seed;

  	get_random_once(&nf_conntrack_hash_rnd, sizeof(nf_conntrack_hash_rnd));

  	/* The direction must be ignored, so we hash everything up to the
  	 * destination ports (which is a multiple of 4) and treat the last
  	 * three bytes manually.
  	 */

  	seed = nf_conntrack_hash_rnd ^ net_hash_mix(net);

  	n = (sizeof(tuple->src) + sizeof(tuple->dst.u3)) / sizeof(u32);

  	return jhash2((u32 *)tuple, n, seed ^

  		      (((__force __u16)tuple->dst.u.all << 16) |
  		      tuple->dst.protonum));
  }

  static u32 scale_hash(u32 hash)

  {

  	return reciprocal_scale(hash, nf_conntrack_htable_size);

  }

  static u32 __hash_conntrack(const struct net *net,
  			    const struct nf_conntrack_tuple *tuple,
  			    unsigned int size)

  {

  	return reciprocal_scale(hash_conntrack_raw(tuple, net), size);

  }

  static u32 hash_conntrack(const struct net *net,
  			  const struct nf_conntrack_tuple *tuple)

  {

  	return scale_hash(hash_conntrack_raw(tuple, net));

  }

  static bool

  nf_ct_get_tuple(const struct sk_buff *skb,
  		unsigned int nhoff,
  		unsigned int dataoff,
  		u_int16_t l3num,
  		u_int8_t protonum,

  		struct net *net,

  		struct nf_conntrack_tuple *tuple,

  		const struct nf_conntrack_l4proto *l4proto)

  {

  	unsigned int size;
  	const __be32 *ap;
  	__be32 _addrs[8];

  	struct {
  		__be16 sport;
  		__be16 dport;
  	} _inet_hdr, *inet_hdr;

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

  
  	tuple->src.l3num = l3num;

  	switch (l3num) {
  	case NFPROTO_IPV4:
  		nhoff += offsetof(struct iphdr, saddr);
  		size = 2 * sizeof(__be32);
  		break;
  	case NFPROTO_IPV6:
  		nhoff += offsetof(struct ipv6hdr, saddr);
  		size = sizeof(_addrs);
  		break;
  	default:
  		return true;
  	}
  
  	ap = skb_header_pointer(skb, nhoff, size, _addrs);
  	if (!ap)

  		return false;

  	switch (l3num) {
  	case NFPROTO_IPV4:
  		tuple->src.u3.ip = ap[0];
  		tuple->dst.u3.ip = ap[1];
  		break;
  	case NFPROTO_IPV6:
  		memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
  		memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
  		break;
  	}

  	tuple->dst.protonum = protonum;
  	tuple->dst.dir = IP_CT_DIR_ORIGINAL;

  	if (unlikely(l4proto->pkt_to_tuple))
  		return l4proto->pkt_to_tuple(skb, dataoff, net, tuple);
  
  	/* Actually only need first 4 bytes to get ports. */
  	inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr);
  	if (!inet_hdr)
  		return false;
  
  	tuple->src.u.udp.port = inet_hdr->sport;
  	tuple->dst.u.udp.port = inet_hdr->dport;
  	return true;

  }

  static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
  			    u_int8_t *protonum)
  {
  	int dataoff = -1;

  	const struct iphdr *iph;
  	struct iphdr _iph;
  
  	iph = skb_header_pointer(skb, nhoff, sizeof(_iph), &_iph);
  	if (!iph)
  		return -1;
  
  	/* Conntrack defragments packets, we might still see fragments
  	 * inside ICMP packets though.
  	 */
  	if (iph->frag_off & htons(IP_OFFSET))
  		return -1;
  
  	dataoff = nhoff + (iph->ihl << 2);
  	*protonum = iph->protocol;
  
  	/* Check bogus IP headers */
  	if (dataoff > skb->len) {
  		pr_debug("bogus IPv4 packet: nhoff %u, ihl %u, skblen %u
  ",
  			 nhoff, iph->ihl << 2, skb->len);
  		return -1;
  	}

  	return dataoff;
  }

  #if IS_ENABLED(CONFIG_IPV6)

  static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
  			    u8 *protonum)
  {
  	int protoff = -1;

  	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
  	__be16 frag_off;
  	u8 nexthdr;
  
  	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
  			  &nexthdr, sizeof(nexthdr)) != 0) {
  		pr_debug("can't get nexthdr
  ");
  		return -1;
  	}
  	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
  	/*
  	 * (protoff == skb->len) means the packet has not data, just
  	 * IPv6 and possibly extensions headers, but it is tracked anyway
  	 */
  	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
  		pr_debug("can't find proto in pkt
  ");
  		return -1;
  	}
  
  	*protonum = nexthdr;

  	return protoff;
  }

  #endif

  
  static int get_l4proto(const struct sk_buff *skb,
  		       unsigned int nhoff, u8 pf, u8 *l4num)
  {
  	switch (pf) {
  	case NFPROTO_IPV4:
  		return ipv4_get_l4proto(skb, nhoff, l4num);

  #if IS_ENABLED(CONFIG_IPV6)

  	case NFPROTO_IPV6:
  		return ipv6_get_l4proto(skb, nhoff, l4num);

  #endif

  	default:
  		*l4num = 0;
  		break;
  	}
  	return -1;

  }

  bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff,

  		       u_int16_t l3num,
  		       struct net *net, struct nf_conntrack_tuple *tuple)

  {

  	const struct nf_conntrack_l4proto *l4proto;

  	u8 protonum;
  	int protoff;

  	int ret;
  
  	rcu_read_lock();

  	protoff = get_l4proto(skb, nhoff, l3num, &protonum);
  	if (protoff <= 0) {

  		rcu_read_unlock();

  		return false;

  	}
  
  	l4proto = __nf_ct_l4proto_find(l3num, protonum);

  	ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple,

  			      l4proto);

  
  	rcu_read_unlock();
  	return ret;
  }
  EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr);

  bool

  nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
  		   const struct nf_conntrack_tuple *orig,

  		   const struct nf_conntrack_l4proto *l4proto)

  {

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

  
  	inverse->src.l3num = orig->src.l3num;

  
  	switch (orig->src.l3num) {
  	case NFPROTO_IPV4:
  		inverse->src.u3.ip = orig->dst.u3.ip;
  		inverse->dst.u3.ip = orig->src.u3.ip;
  		break;
  	case NFPROTO_IPV6:
  		inverse->src.u3.in6 = orig->dst.u3.in6;
  		inverse->dst.u3.in6 = orig->src.u3.in6;
  		break;
  	default:
  		break;
  	}

  
  	inverse->dst.dir = !orig->dst.dir;
  
  	inverse->dst.protonum = orig->dst.protonum;

  
  	if (unlikely(l4proto->invert_tuple))
  		return l4proto->invert_tuple(inverse, orig);
  
  	inverse->src.u.all = orig->dst.u.all;
  	inverse->dst.u.all = orig->src.u.all;
  	return true;

  }

  EXPORT_SYMBOL_GPL(nf_ct_invert_tuple);

  static void
  clean_from_lists(struct nf_conn *ct)
  {

  	pr_debug("clean_from_lists(%p)
  ", ct);

  	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
  	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode);

  
  	/* Destroy all pending expectations */

  	nf_ct_remove_expectations(ct);

  }

  /* must be called with local_bh_disable */
  static void nf_ct_add_to_dying_list(struct nf_conn *ct)
  {
  	struct ct_pcpu *pcpu;
  
  	/* add this conntrack to the (per cpu) dying list */
  	ct->cpu = smp_processor_id();
  	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
  
  	spin_lock(&pcpu->lock);
  	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
  			     &pcpu->dying);
  	spin_unlock(&pcpu->lock);
  }
  
  /* must be called with local_bh_disable */
  static void nf_ct_add_to_unconfirmed_list(struct nf_conn *ct)
  {
  	struct ct_pcpu *pcpu;
  
  	/* add this conntrack to the (per cpu) unconfirmed list */
  	ct->cpu = smp_processor_id();
  	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
  
  	spin_lock(&pcpu->lock);
  	hlist_nulls_add_head(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
  			     &pcpu->unconfirmed);
  	spin_unlock(&pcpu->lock);
  }
  
  /* must be called with local_bh_disable */
  static void nf_ct_del_from_dying_or_unconfirmed_list(struct nf_conn *ct)
  {
  	struct ct_pcpu *pcpu;
  
  	/* We overload first tuple to link into unconfirmed or dying list.*/
  	pcpu = per_cpu_ptr(nf_ct_net(ct)->ct.pcpu_lists, ct->cpu);
  
  	spin_lock(&pcpu->lock);
  	BUG_ON(hlist_nulls_unhashed(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode));
  	hlist_nulls_del_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode);
  	spin_unlock(&pcpu->lock);
  }

  #define NFCT_ALIGN(len)	(((len) + NFCT_INFOMASK) & ~NFCT_INFOMASK)

  /* Released via destroy_conntrack() */

  struct nf_conn *nf_ct_tmpl_alloc(struct net *net,
  				 const struct nf_conntrack_zone *zone,
  				 gfp_t flags)

  {

  	struct nf_conn *tmpl, *p;

  	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK) {
  		tmpl = kzalloc(sizeof(*tmpl) + NFCT_INFOMASK, flags);
  		if (!tmpl)
  			return NULL;
  
  		p = tmpl;
  		tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
  		if (tmpl != p) {
  			tmpl = (struct nf_conn *)NFCT_ALIGN((unsigned long)p);
  			tmpl->proto.tmpl_padto = (char *)tmpl - (char *)p;
  		}
  	} else {
  		tmpl = kzalloc(sizeof(*tmpl), flags);
  		if (!tmpl)
  			return NULL;
  	}

  
  	tmpl->status = IPS_TEMPLATE;
  	write_pnet(&tmpl->ct_net, net);

  	nf_ct_zone_add(tmpl, zone);

  	atomic_set(&tmpl->ct_general.use, 0);
  
  	return tmpl;

  }
  EXPORT_SYMBOL_GPL(nf_ct_tmpl_alloc);

  void nf_ct_tmpl_free(struct nf_conn *tmpl)

  {
  	nf_ct_ext_destroy(tmpl);
  	nf_ct_ext_free(tmpl);

  
  	if (ARCH_KMALLOC_MINALIGN <= NFCT_INFOMASK)
  		kfree((char *)tmpl - tmpl->proto.tmpl_padto);
  	else
  		kfree(tmpl);

  }

  EXPORT_SYMBOL_GPL(nf_ct_tmpl_free);

  static void
  destroy_conntrack(struct nf_conntrack *nfct)
  {
  	struct nf_conn *ct = (struct nf_conn *)nfct;

  	const struct nf_conntrack_l4proto *l4proto;

  	pr_debug("destroy_conntrack(%p)
  ", ct);

  	WARN_ON(atomic_read(&nfct->use) != 0);

  	if (unlikely(nf_ct_is_template(ct))) {
  		nf_ct_tmpl_free(ct);
  		return;
  	}

  	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));

  	if (l4proto->destroy)

  		l4proto->destroy(ct);

  	local_bh_disable();

  	/* Expectations will have been removed in clean_from_lists,
  	 * except TFTP can create an expectation on the first packet,
  	 * before connection is in the list, so we need to clean here,

  	 * too.
  	 */

  	nf_ct_remove_expectations(ct);

  	nf_ct_del_from_dying_or_unconfirmed_list(ct);

  	local_bh_enable();

  
  	if (ct->master)
  		nf_ct_put(ct->master);

  	pr_debug("destroy_conntrack: returning ct=%p to slab
  ", ct);

  	nf_conntrack_free(ct);
  }

  static void nf_ct_delete_from_lists(struct nf_conn *ct)

  {

  	struct net *net = nf_ct_net(ct);

  	unsigned int hash, reply_hash;

  	unsigned int sequence;

  	nf_ct_helper_destroy(ct);

  
  	local_bh_disable();
  	do {

  		sequence = read_seqcount_begin(&nf_conntrack_generation);

  		hash = hash_conntrack(net,

  				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);

  		reply_hash = hash_conntrack(net,

  					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
  	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));

  	clean_from_lists(ct);

  	nf_conntrack_double_unlock(hash, reply_hash);

  	nf_ct_add_to_dying_list(ct);

  	local_bh_enable();

  }

  bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)

  {

  	struct nf_conn_tstamp *tstamp;

  	if (test_and_set_bit(IPS_DYING_BIT, &ct->status))
  		return false;

  	tstamp = nf_conn_tstamp_find(ct);
  	if (tstamp && tstamp->stop == 0)

  		tstamp->stop = ktime_get_real_ns();

  	if (nf_conntrack_event_report(IPCT_DESTROY, ct,
  				    portid, report) < 0) {

  		/* destroy event was not delivered. nf_ct_put will
  		 * be done by event cache worker on redelivery.
  		 */

  		nf_ct_delete_from_lists(ct);

  		nf_conntrack_ecache_delayed_work(nf_ct_net(ct));

  		return false;

  	}

  
  	nf_conntrack_ecache_work(nf_ct_net(ct));

  	nf_ct_delete_from_lists(ct);

  	nf_ct_put(ct);

  	return true;
  }
  EXPORT_SYMBOL_GPL(nf_ct_delete);

  static inline bool
  nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,

  		const struct nf_conntrack_tuple *tuple,

  		const struct nf_conntrack_zone *zone,
  		const struct net *net)

  {
  	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
  
  	/* A conntrack can be recreated with the equal tuple,
  	 * so we need to check that the conntrack is confirmed
  	 */
  	return nf_ct_tuple_equal(tuple, &h->tuple) &&

  	       nf_ct_zone_equal(ct, zone, NF_CT_DIRECTION(h)) &&

  	       nf_ct_is_confirmed(ct) &&
  	       net_eq(net, nf_ct_net(ct));

  }

  static inline bool
  nf_ct_match(const struct nf_conn *ct1, const struct nf_conn *ct2)
  {
  	return nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
  				 &ct2->tuplehash[IP_CT_DIR_ORIGINAL].tuple) &&
  	       nf_ct_tuple_equal(&ct1->tuplehash[IP_CT_DIR_REPLY].tuple,
  				 &ct2->tuplehash[IP_CT_DIR_REPLY].tuple) &&
  	       nf_ct_zone_equal(ct1, nf_ct_zone(ct2), IP_CT_DIR_ORIGINAL) &&
  	       nf_ct_zone_equal(ct1, nf_ct_zone(ct2), IP_CT_DIR_REPLY) &&
  	       net_eq(nf_ct_net(ct1), nf_ct_net(ct2));
  }

  /* caller must hold rcu readlock and none of the nf_conntrack_locks */
  static void nf_ct_gc_expired(struct nf_conn *ct)
  {
  	if (!atomic_inc_not_zero(&ct->ct_general.use))
  		return;
  
  	if (nf_ct_should_gc(ct))
  		nf_ct_kill(ct);
  
  	nf_ct_put(ct);
  }

  /*
   * Warning :
   * - Caller must take a reference on returned object
   *   and recheck nf_ct_tuple_equal(tuple, &h->tuple)

   */

  static struct nf_conntrack_tuple_hash *

  ____nf_conntrack_find(struct net *net, const struct nf_conntrack_zone *zone,

  		      const struct nf_conntrack_tuple *tuple, u32 hash)

  {
  	struct nf_conntrack_tuple_hash *h;

  	struct hlist_nulls_head *ct_hash;

  	struct hlist_nulls_node *n;

  	unsigned int bucket, hsize;

  begin:

  	nf_conntrack_get_ht(&ct_hash, &hsize);
  	bucket = reciprocal_scale(hash, hsize);

  
  	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[bucket], hnnode) {

  		struct nf_conn *ct;
  
  		ct = nf_ct_tuplehash_to_ctrack(h);
  		if (nf_ct_is_expired(ct)) {
  			nf_ct_gc_expired(ct);
  			continue;
  		}
  
  		if (nf_ct_is_dying(ct))
  			continue;

  		if (nf_ct_key_equal(h, tuple, zone, net))

  			return h;

  	}

  	/*
  	 * 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.
  	 */

  	if (get_nulls_value(n) != bucket) {

  		NF_CT_STAT_INC_ATOMIC(net, search_restart);

  		goto begin;

  	}

  
  	return NULL;
  }

  /* Find a connection corresponding to a tuple. */

  static struct nf_conntrack_tuple_hash *

  __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,

  			const struct nf_conntrack_tuple *tuple, u32 hash)

  {
  	struct nf_conntrack_tuple_hash *h;

  	struct nf_conn *ct;

  	rcu_read_lock();

  begin:

  	h = ____nf_conntrack_find(net, zone, tuple, hash);

  	if (h) {
  		ct = nf_ct_tuplehash_to_ctrack(h);

  		if (unlikely(nf_ct_is_dying(ct) ||
  			     !atomic_inc_not_zero(&ct->ct_general.use)))

  			h = NULL;

  		else {

  			if (unlikely(!nf_ct_key_equal(h, tuple, zone, net))) {

  				nf_ct_put(ct);
  				goto begin;
  			}
  		}

  	}
  	rcu_read_unlock();

  
  	return h;
  }

  
  struct nf_conntrack_tuple_hash *

  nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone,

  		      const struct nf_conntrack_tuple *tuple)
  {
  	return __nf_conntrack_find_get(net, zone, tuple,

  				       hash_conntrack_raw(tuple, net));

  }

  EXPORT_SYMBOL_GPL(nf_conntrack_find_get);

  static void __nf_conntrack_hash_insert(struct nf_conn *ct,
  				       unsigned int hash,

  				       unsigned int reply_hash)

  {

  	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,

  			   &nf_conntrack_hash[hash]);

  	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode,

  			   &nf_conntrack_hash[reply_hash]);

  }

  int
  nf_conntrack_hash_check_insert(struct nf_conn *ct)

  {

  	const struct nf_conntrack_zone *zone;

  	struct net *net = nf_ct_net(ct);

  	unsigned int hash, reply_hash;

  	struct nf_conntrack_tuple_hash *h;
  	struct hlist_nulls_node *n;

  	unsigned int sequence;

  	zone = nf_ct_zone(ct);

  	local_bh_disable();
  	do {

  		sequence = read_seqcount_begin(&nf_conntrack_generation);

  		hash = hash_conntrack(net,

  				      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);

  		reply_hash = hash_conntrack(net,

  					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
  	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));

  
  	/* See if there's one in the list already, including reverse */

  	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)

  		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,

  				    zone, net))

  			goto out;

  	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)

  		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,

  				    zone, net))

  			goto out;

  	smp_wmb();
  	/* The caller holds a reference to this object */
  	atomic_set(&ct->ct_general.use, 2);

  	__nf_conntrack_hash_insert(ct, hash, reply_hash);

  	nf_conntrack_double_unlock(hash, reply_hash);

  	NF_CT_STAT_INC(net, insert);

  	local_bh_enable();

  	return 0;
  
  out:

  	nf_conntrack_double_unlock(hash, reply_hash);

  	NF_CT_STAT_INC(net, insert_failed);

  	local_bh_enable();

  	return -EEXIST;

  }

  EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);

  static inline void nf_ct_acct_update(struct nf_conn *ct,
  				     enum ip_conntrack_info ctinfo,
  				     unsigned int len)
  {
  	struct nf_conn_acct *acct;
  
  	acct = nf_conn_acct_find(ct);
  	if (acct) {
  		struct nf_conn_counter *counter = acct->counter;
  
  		atomic64_inc(&counter[CTINFO2DIR(ctinfo)].packets);
  		atomic64_add(len, &counter[CTINFO2DIR(ctinfo)].bytes);
  	}
  }

  static void nf_ct_acct_merge(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
  			     const struct nf_conn *loser_ct)
  {
  	struct nf_conn_acct *acct;
  
  	acct = nf_conn_acct_find(loser_ct);
  	if (acct) {
  		struct nf_conn_counter *counter = acct->counter;

  		unsigned int bytes;
  
  		/* u32 should be fine since we must have seen one packet. */
  		bytes = atomic64_read(&counter[CTINFO2DIR(ctinfo)].bytes);
  		nf_ct_acct_update(ct, ctinfo, bytes);
  	}
  }
  
  /* Resolve race on insertion if this protocol allows this. */
  static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb,
  			       enum ip_conntrack_info ctinfo,
  			       struct nf_conntrack_tuple_hash *h)
  {
  	/* This is the conntrack entry already in hashes that won race. */
  	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);

  	const struct nf_conntrack_l4proto *l4proto;

  	enum ip_conntrack_info oldinfo;
  	struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo);

  
  	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
  	if (l4proto->allow_clash &&
  	    !nf_ct_is_dying(ct) &&
  	    atomic_inc_not_zero(&ct->ct_general.use)) {

  		if (((ct->status & IPS_NAT_DONE_MASK) == 0) ||
  		    nf_ct_match(ct, loser_ct)) {
  			nf_ct_acct_merge(ct, ctinfo, loser_ct);
  			nf_conntrack_put(&loser_ct->ct_general);
  			nf_ct_set(skb, ct, oldinfo);
  			return NF_ACCEPT;
  		}
  		nf_ct_put(ct);

  	}
  	NF_CT_STAT_INC(net, drop);
  	return NF_DROP;
  }

  /* Confirm a connection given skb; places it in hash table */
  int

  __nf_conntrack_confirm(struct sk_buff *skb)

  {

  	const struct nf_conntrack_zone *zone;

  	unsigned int hash, reply_hash;

  	struct nf_conntrack_tuple_hash *h;

  	struct nf_conn *ct;

  	struct nf_conn_help *help;

  	struct nf_conn_tstamp *tstamp;

  	struct hlist_nulls_node *n;

  	enum ip_conntrack_info ctinfo;

  	struct net *net;

  	unsigned int sequence;

  	int ret = NF_DROP;

  	ct = nf_ct_get(skb, &ctinfo);

  	net = nf_ct_net(ct);

  
  	/* ipt_REJECT uses nf_conntrack_attach to attach related
  	   ICMP/TCP RST packets in other direction.  Actual packet
  	   which created connection will be IP_CT_NEW or for an
  	   expected connection, IP_CT_RELATED. */
  	if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL)
  		return NF_ACCEPT;

  	zone = nf_ct_zone(ct);

  	local_bh_disable();
  
  	do {

  		sequence = read_seqcount_begin(&nf_conntrack_generation);

  		/* reuse the hash saved before */
  		hash = *(unsigned long *)&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev;

  		hash = scale_hash(hash);

  		reply_hash = hash_conntrack(net,

  					   &ct->tuplehash[IP_CT_DIR_REPLY].tuple);
  
  	} while (nf_conntrack_double_lock(net, hash, reply_hash, sequence));

  
  	/* We're not in hash table, and we refuse to set up related

  	 * connections for unconfirmed conns.  But packet copies and
  	 * REJECT will give spurious warnings here.
  	 */

  	/* Another skb with the same unconfirmed conntrack may
  	 * win the race. This may happen for bridge(br_flood)
  	 * or broadcast/multicast packets do skb_clone with
  	 * unconfirmed conntrack.

  	 */

  	if (unlikely(nf_ct_is_confirmed(ct))) {
  		WARN_ON_ONCE(1);
  		nf_conntrack_double_unlock(hash, reply_hash);
  		local_bh_enable();
  		return NF_DROP;
  	}

  	pr_debug("Confirming conntrack %p
  ", ct);

  	/* We have to check the DYING flag after unlink to prevent
  	 * a race against nf_ct_get_next_corpse() possibly called from
  	 * user context, else we insert an already 'dead' hash, blocking
  	 * further use of that particular connection -JM.
  	 */
  	nf_ct_del_from_dying_or_unconfirmed_list(ct);

  	if (unlikely(nf_ct_is_dying(ct))) {
  		nf_ct_add_to_dying_list(ct);
  		goto dying;
  	}

  	/* See if there's one in the list already, including reverse:
  	   NAT could have grabbed it without realizing, since we're
  	   not in the hash.  If there is, we lost race. */

  	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[hash], hnnode)

  		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple,

  				    zone, net))

  			goto out;

  	hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[reply_hash], hnnode)

  		if (nf_ct_key_equal(h, &ct->tuplehash[IP_CT_DIR_REPLY].tuple,

  				    zone, net))

  			goto out;

  	/* Timer relative to confirmation time, not original
  	   setting time, otherwise we'd get timer wrap in
  	   weird delay cases. */

  	ct->timeout += nfct_time_stamp;

  	atomic_inc(&ct->ct_general.use);

  	ct->status |= IPS_CONFIRMED;

  	/* set conntrack timestamp, if enabled. */
  	tstamp = nf_conn_tstamp_find(ct);
  	if (tstamp) {

  		if (skb->tstamp == 0)

  			__net_timestamp(skb);

  
  		tstamp->start = ktime_to_ns(skb->tstamp);
  	}

  	/* Since the lookup is lockless, hash insertion must be done after
  	 * starting the timer and setting the CONFIRMED bit. The RCU barriers
  	 * guarantee that no other CPU can find the conntrack before the above
  	 * stores are visible.
  	 */

  	__nf_conntrack_hash_insert(ct, hash, reply_hash);

  	nf_conntrack_double_unlock(hash, reply_hash);

  	local_bh_enable();

  	help = nfct_help(ct);
  	if (help && help->helper)

  		nf_conntrack_event_cache(IPCT_HELPER, ct);

  	nf_conntrack_event_cache(master_ct(ct) ?

  				 IPCT_RELATED : IPCT_NEW, ct);

  	return NF_ACCEPT;

  out:

  	nf_ct_add_to_dying_list(ct);

  	ret = nf_ct_resolve_clash(net, skb, ctinfo, h);
  dying:

  	nf_conntrack_double_unlock(hash, reply_hash);

  	NF_CT_STAT_INC(net, insert_failed);

  	local_bh_enable();

  	return ret;

  }

  EXPORT_SYMBOL_GPL(__nf_conntrack_confirm);

  
  /* Returns true if a connection correspondings to the tuple (required
     for NAT). */
  int
  nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
  			 const struct nf_conn *ignored_conntrack)
  {

  	struct net *net = nf_ct_net(ignored_conntrack);

  	const struct nf_conntrack_zone *zone;

  	struct nf_conntrack_tuple_hash *h;

  	struct hlist_nulls_head *ct_hash;

  	unsigned int hash, hsize;

  	struct hlist_nulls_node *n;

  	struct nf_conn *ct;

  
  	zone = nf_ct_zone(ignored_conntrack);

  	rcu_read_lock();

   begin:

  	nf_conntrack_get_ht(&ct_hash, &hsize);
  	hash = __hash_conntrack(net, tuple, hsize);

  
  	hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[hash], hnnode) {

  		ct = nf_ct_tuplehash_to_ctrack(h);

  
  		if (ct == ignored_conntrack)
  			continue;
  
  		if (nf_ct_is_expired(ct)) {
  			nf_ct_gc_expired(ct);
  			continue;
  		}
  
  		if (nf_ct_key_equal(h, tuple, zone, net)) {

  			/* Tuple is taken already, so caller will need to find
  			 * a new source port to use.
  			 *
  			 * Only exception:
  			 * If the *original tuples* are identical, then both
  			 * conntracks refer to the same flow.
  			 * This is a rare situation, it can occur e.g. when
  			 * more than one UDP packet is sent from same socket
  			 * in different threads.
  			 *
  			 * Let nf_ct_resolve_clash() deal with this later.
  			 */
  			if (nf_ct_tuple_equal(&ignored_conntrack->tuplehash[IP_CT_DIR_ORIGINAL].tuple,
  					      &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple))
  				continue;

  			NF_CT_STAT_INC_ATOMIC(net, found);
  			rcu_read_unlock();

  			return 1;
  		}

  	}

  
  	if (get_nulls_value(n) != hash) {
  		NF_CT_STAT_INC_ATOMIC(net, search_restart);
  		goto begin;
  	}

  	rcu_read_unlock();

  	return 0;

  }

  EXPORT_SYMBOL_GPL(nf_conntrack_tuple_taken);

  #define NF_CT_EVICTION_RANGE	8

  /* There's a small race here where we may free a just-assured
     connection.  Too bad: we're in trouble anyway. */

  static unsigned int early_drop_list(struct net *net,
  				    struct hlist_nulls_head *head)

  {

  	struct nf_conntrack_tuple_hash *h;

  	struct hlist_nulls_node *n;

  	unsigned int drops = 0;
  	struct nf_conn *tmp;

  	hlist_nulls_for_each_entry_rcu(h, n, head, hnnode) {
  		tmp = nf_ct_tuplehash_to_ctrack(h);

  		if (test_bit(IPS_OFFLOAD_BIT, &tmp->status))
  			continue;

  		if (nf_ct_is_expired(tmp)) {
  			nf_ct_gc_expired(tmp);
  			continue;
  		}

  		if (test_bit(IPS_ASSURED_BIT, &tmp->status) ||
  		    !net_eq(nf_ct_net(tmp), net) ||
  		    nf_ct_is_dying(tmp))
  			continue;

  		if (!atomic_inc_not_zero(&tmp->ct_general.use))
  			continue;

  		/* kill only if still in same netns -- might have moved due to

  		 * SLAB_TYPESAFE_BY_RCU rules.

  		 *
  		 * We steal the timer reference.  If that fails timer has
  		 * already fired or someone else deleted it. Just drop ref
  		 * and move to next entry.
  		 */
  		if (net_eq(nf_ct_net(tmp), net) &&
  		    nf_ct_is_confirmed(tmp) &&

  		    nf_ct_delete(tmp, 0, 0))
  			drops++;
  
  		nf_ct_put(tmp);

  	}

  	return drops;
  }

  static noinline int early_drop(struct net *net, unsigned int hash)

  {

  	unsigned int i, bucket;

  	for (i = 0; i < NF_CT_EVICTION_RANGE; i++) {
  		struct hlist_nulls_head *ct_hash;

  		unsigned int hsize, drops;

  		rcu_read_lock();

  		nf_conntrack_get_ht(&ct_hash, &hsize);

  		if (!i)
  			bucket = reciprocal_scale(hash, hsize);
  		else
  			bucket = (bucket + 1) % hsize;

  		drops = early_drop_list(net, &ct_hash[bucket]);

  		rcu_read_unlock();

  		if (drops) {
  			NF_CT_STAT_ADD_ATOMIC(net, early_drop, drops);
  			return true;

  		}

  	}

  	return false;

  }

  static bool gc_worker_skip_ct(const struct nf_conn *ct)
  {
  	return !nf_ct_is_confirmed(ct) || nf_ct_is_dying(ct);
  }
  
  static bool gc_worker_can_early_drop(const struct nf_conn *ct)
  {
  	const struct nf_conntrack_l4proto *l4proto;
  
  	if (!test_bit(IPS_ASSURED_BIT, &ct->status))
  		return true;
  
  	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
  	if (l4proto->can_early_drop && l4proto->can_early_drop(ct))
  		return true;
  
  	return false;
  }

  #define	DAY	(86400 * HZ)
  
  /* Set an arbitrary timeout large enough not to ever expire, this save
   * us a check for the IPS_OFFLOAD_BIT from the packet path via
   * nf_ct_is_expired().
   */
  static void nf_ct_offload_timeout(struct nf_conn *ct)
  {
  	if (nf_ct_expires(ct) < DAY / 2)
  		ct->timeout = nfct_time_stamp + DAY;
  }

  static void gc_worker(struct work_struct *work)
  {

  	unsigned int min_interval = max(HZ / GC_MAX_BUCKETS_DIV, 1u);

  	unsigned int i, goal, buckets = 0, expired_count = 0;

  	unsigned int nf_conntrack_max95 = 0;

  	struct conntrack_gc_work *gc_work;

  	unsigned int ratio, scanned = 0;
  	unsigned long next_run;

  
  	gc_work = container_of(work, struct conntrack_gc_work, dwork.work);

  	goal = nf_conntrack_htable_size / GC_MAX_BUCKETS_DIV;

  	i = gc_work->last_bucket;

  	if (gc_work->early_drop)
  		nf_conntrack_max95 = nf_conntrack_max / 100u * 95u;

  
  	do {
  		struct nf_conntrack_tuple_hash *h;
  		struct hlist_nulls_head *ct_hash;
  		struct hlist_nulls_node *n;
  		unsigned int hashsz;
  		struct nf_conn *tmp;
  
  		i++;
  		rcu_read_lock();
  
  		nf_conntrack_get_ht(&ct_hash, &hashsz);
  		if (i >= hashsz)
  			i = 0;
  
  		hlist_nulls_for_each_entry_rcu(h, n, &ct_hash[i], hnnode) {

  			struct net *net;

  			tmp = nf_ct_tuplehash_to_ctrack(h);

  			scanned++;

  			if (test_bit(IPS_OFFLOAD_BIT, &tmp->status)) {
  				nf_ct_offload_timeout(tmp);
  				continue;
  			}

  			if (nf_ct_is_expired(tmp)) {
  				nf_ct_gc_expired(tmp);
  				expired_count++;
  				continue;
  			}

  
  			if (nf_conntrack_max95 == 0 || gc_worker_skip_ct(tmp))
  				continue;
  
  			net = nf_ct_net(tmp);
  			if (atomic_read(&net->ct.count) < nf_conntrack_max95)
  				continue;
  
  			/* need to take reference to avoid possible races */
  			if (!atomic_inc_not_zero(&tmp->ct_general.use))
  				continue;
  
  			if (gc_worker_skip_ct(tmp)) {
  				nf_ct_put(tmp);
  				continue;
  			}
  
  			if (gc_worker_can_early_drop(tmp))
  				nf_ct_kill(tmp);
  
  			nf_ct_put(tmp);

  		}
  
  		/* could check get_nulls_value() here and restart if ct
  		 * was moved to another chain.  But given gc is best-effort
  		 * we will just continue with next hash slot.
  		 */
  		rcu_read_unlock();

  		cond_resched();

  	} while (++buckets < goal);

  
  	if (gc_work->exiting)
  		return;

  	/*
  	 * Eviction will normally happen from the packet path, and not
  	 * from this gc worker.
  	 *
  	 * This worker is only here to reap expired entries when system went
  	 * idle after a busy period.
  	 *
  	 * The heuristics below are supposed to balance conflicting goals:
  	 *
  	 * 1. Minimize time until we notice a stale entry
  	 * 2. Maximize scan intervals to not waste cycles
  	 *

  	 * Normally, expire ratio will be close to 0.

  	 *

  	 * As soon as a sizeable fraction of the entries have expired
  	 * increase scan frequency.

  	 */

  	ratio = scanned ? expired_count * 100 / scanned : 0;

  	if (ratio > GC_EVICT_RATIO) {
  		gc_work->next_gc_run = min_interval;

  	} else {

  		unsigned int max = GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV;

  		BUILD_BUG_ON((GC_MAX_SCAN_JIFFIES / GC_MAX_BUCKETS_DIV) == 0);
  
  		gc_work->next_gc_run += min_interval;
  		if (gc_work->next_gc_run > max)
  			gc_work->next_gc_run = max;

  	}

  	next_run = gc_work->next_gc_run;

  	gc_work->last_bucket = i;

  	gc_work->early_drop = false;

  	queue_delayed_work(system_power_efficient_wq, &gc_work->dwork, next_run);

  }
  
  static void conntrack_gc_work_init(struct conntrack_gc_work *gc_work)
  {

  	INIT_DEFERRABLE_WORK(&gc_work->dwork, gc_worker);

  	gc_work->next_gc_run = HZ;

  	gc_work->exiting = false;
  }

  static struct nf_conn *

  __nf_conntrack_alloc(struct net *net,
  		     const struct nf_conntrack_zone *zone,

  		     const struct nf_conntrack_tuple *orig,
  		     const struct nf_conntrack_tuple *repl,
  		     gfp_t gfp, u32 hash)

  {

  	struct nf_conn *ct;

  	/* We don't want any race condition at early drop stage */

  	atomic_inc(&net->ct.count);

  	if (nf_conntrack_max &&

  	    unlikely(atomic_read(&net->ct.count) > nf_conntrack_max)) {

  		if (!early_drop(net, hash)) {

  			if (!conntrack_gc_work.early_drop)
  				conntrack_gc_work.early_drop = true;

  			atomic_dec(&net->ct.count);

  			net_warn_ratelimited("nf_conntrack: table full, dropping packet
  ");

  			return ERR_PTR(-ENOMEM);
  		}
  	}

  	/*
  	 * Do not use kmem_cache_zalloc(), as this cache uses

  	 * SLAB_TYPESAFE_BY_RCU.

  	 */

  	ct = kmem_cache_alloc(nf_conntrack_cachep, gfp);

  	if (ct == NULL)
  		goto out;

  	spin_lock_init(&ct->lock);

  	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;

  	ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL;

  	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;

  	/* save hash for reusing when confirming */
  	*(unsigned long *)(&ct->tuplehash[IP_CT_DIR_REPLY].hnnode.pprev) = hash;

  	ct->status = 0;

  	write_pnet(&ct->ct_net, net);

  	memset(&ct->__nfct_init_offset[0], 0,
  	       offsetof(struct nf_conn, proto) -
  	       offsetof(struct nf_conn, __nfct_init_offset[0]));

  	nf_ct_zone_add(ct, zone);

  	/* Because we use RCU lookups, we set ct_general.use to zero before
  	 * this is inserted in any list.

  	 */

  	atomic_set(&ct->ct_general.use, 0);

  	return ct;

  out:
  	atomic_dec(&net->ct.count);

  	return ERR_PTR(-ENOMEM);

  }

  struct nf_conn *nf_conntrack_alloc(struct net *net,
  				   const struct nf_conntrack_zone *zone,

  				   const struct nf_conntrack_tuple *orig,
  				   const struct nf_conntrack_tuple *repl,
  				   gfp_t gfp)
  {
  	return __nf_conntrack_alloc(net, zone, orig, repl, gfp, 0);
  }

  EXPORT_SYMBOL_GPL(nf_conntrack_alloc);

  void nf_conntrack_free(struct nf_conn *ct)

  {

  	struct net *net = nf_ct_net(ct);

  	/* A freed object has refcnt == 0, that's

  	 * the golden rule for SLAB_TYPESAFE_BY_RCU

  	 */

  	WARN_ON(atomic_read(&ct->ct_general.use) != 0);

  	nf_ct_ext_destroy(ct);

  	nf_ct_ext_free(ct);

  	kmem_cache_free(nf_conntrack_cachep, ct);

  	smp_mb__before_atomic();

  	atomic_dec(&net->ct.count);

  }

  EXPORT_SYMBOL_GPL(nf_conntrack_free);

  /* Allocate a new conntrack: we return -ENOMEM if classification
     failed due to stress.  Otherwise it really is unclassifiable. */

  static noinline struct nf_conntrack_tuple_hash *

  init_conntrack(struct net *net, struct nf_conn *tmpl,

  	       const struct nf_conntrack_tuple *tuple,

  	       const struct nf_conntrack_l4proto *l4proto,

  	       struct sk_buff *skb,

  	       unsigned int dataoff, u32 hash)

  {

  	struct nf_conn *ct;

  	struct nf_conn_help *help;

  	struct nf_conntrack_tuple repl_tuple;

  	struct nf_conntrack_ecache *ecache;

  	struct nf_conntrack_expect *exp = NULL;

  	const struct nf_conntrack_zone *zone;

  	struct nf_conn_timeout *timeout_ext;

  	struct nf_conntrack_zone tmp;

  	if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) {

  		pr_debug("Can't invert tuple.
  ");

  		return NULL;
  	}

  	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);

  	ct = __nf_conntrack_alloc(net, zone, tuple, &repl_tuple, GFP_ATOMIC,
  				  hash);

  	if (IS_ERR(ct))

  		return (struct nf_conntrack_tuple_hash *)ct;

  	if (!nf_ct_add_synproxy(ct, tmpl)) {
  		nf_conntrack_free(ct);
  		return ERR_PTR(-ENOMEM);

  	}

  	timeout_ext = tmpl ? nf_ct_timeout_find(tmpl) : NULL;

  	if (!l4proto->new(ct, skb, dataoff)) {

  		nf_conntrack_free(ct);

  		pr_debug("can't track with proto module
  ");

  		return NULL;
  	}

  	if (timeout_ext)

  		nf_ct_timeout_ext_add(ct, rcu_dereference(timeout_ext->timeout),
  				      GFP_ATOMIC);

  	nf_ct_acct_ext_add(ct, GFP_ATOMIC);

  	nf_ct_tstamp_ext_add(ct, GFP_ATOMIC);

  	nf_ct_labels_ext_add(ct);

  
  	ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL;
  	nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0,
  				 ecache ? ecache->expmask : 0,
  			     GFP_ATOMIC);

  	local_bh_disable();
  	if (net->ct.expect_count) {
  		spin_lock(&nf_conntrack_expect_lock);
  		exp = nf_ct_find_expectation(net, zone, tuple);
  		if (exp) {

  			pr_debug("expectation arrives ct=%p exp=%p
  ",

  				 ct, exp);
  			/* Welcome, Mr. Bond.  We've been expecting you... */
  			__set_bit(IPS_EXPECTED_BIT, &ct->status);
  			/* exp->master safe, refcnt bumped in nf_ct_find_expectation */
  			ct->master = exp->master;
  			if (exp->helper) {

  				help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);

  				if (help)
  					rcu_assign_pointer(help->helper, exp->helper);
  			}

  #ifdef CONFIG_NF_CONNTRACK_MARK

  			ct->mark = exp->master->mark;

  #endif