tcp_ipv4.c

	if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) {
		NET_INC_STATS_BH(net, LINUX_MIB_TCPMINTTLDROP);
		goto discard_and_relse;
	}

	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;
	nf_reset(skb);

	if (sk_filter(sk, skb))
		goto discard_and_relse;

	skb->dev = NULL;

	bh_lock_sock_nested(sk);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
#ifdef CONFIG_NET_DMA
		struct tcp_sock *tp = tcp_sk(sk);
		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
			tp->ucopy.dma_chan = net_dma_find_channel();
		if (tp->ucopy.dma_chan)
			ret = tcp_v4_do_rcv(sk, skb);
		else
#endif
		{
			if (!tcp_prequeue(sk, skb))
				ret = tcp_v4_do_rcv(sk, skb);
		}
	} else if (unlikely(sk_add_backlog(sk, skb,
					   sk->sk_rcvbuf + sk->sk_sndbuf))) {
		bh_unlock_sock(sk);
		NET_INC_STATS_BH(net, LINUX_MIB_TCPBACKLOGDROP);
		goto discard_and_relse;
	}
	bh_unlock_sock(sk);

	sock_put(sk);

	return ret;

no_tcp_socket:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
bad_packet:
		TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
	} else {
		tcp_v4_send_reset(NULL, skb);
	}

discard_it:
	/* Discard frame. */
	kfree_skb(skb);
	return 0;

discard_and_relse:
	sock_put(sk);
	goto discard_it;

do_time_wait:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		inet_twsk_put(inet_twsk(sk));
		goto discard_it;
	}

	if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
		TCP_INC_STATS_BH(net, TCP_MIB_INERRS);
		inet_twsk_put(inet_twsk(sk));
		goto discard_it;
	}
	switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
	case TCP_TW_SYN: {
		struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev),
							&tcp_hashinfo,
							iph->daddr, th->dest,
							inet_iif(skb));
		if (sk2) {
			inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
			inet_twsk_put(inet_twsk(sk));
			sk = sk2;
			goto process;
		}
		/* Fall through to ACK */
	}
	case TCP_TW_ACK:
		tcp_v4_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		goto no_tcp_socket;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

static struct timewait_sock_ops tcp_timewait_sock_ops = {
	.twsk_obj_size	= sizeof(struct tcp_timewait_sock),
	.twsk_unique	= tcp_twsk_unique,
	.twsk_destructor= tcp_twsk_destructor,
};

void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);

	dst_hold(dst);
	sk->sk_rx_dst = dst;
	inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
}
EXPORT_SYMBOL(inet_sk_rx_dst_set);

const struct inet_connection_sock_af_ops ipv4_specific = {
	.queue_xmit	   = ip_queue_xmit,
	.send_check	   = tcp_v4_send_check,
	.rebuild_header	   = inet_sk_rebuild_header,
	.sk_rx_dst_set	   = inet_sk_rx_dst_set,
	.conn_request	   = tcp_v4_conn_request,
	.syn_recv_sock	   = tcp_v4_syn_recv_sock,
	.net_header_len	   = sizeof(struct iphdr),
	.setsockopt	   = ip_setsockopt,
	.getsockopt	   = ip_getsockopt,
	.addr2sockaddr	   = inet_csk_addr2sockaddr,
	.sockaddr_len	   = sizeof(struct sockaddr_in),
	.bind_conflict	   = inet_csk_bind_conflict,
#ifdef CONFIG_COMPAT
	.compat_setsockopt = compat_ip_setsockopt,
	.compat_getsockopt = compat_ip_getsockopt,
#endif
};
EXPORT_SYMBOL(ipv4_specific);

#ifdef CONFIG_TCP_MD5SIG
static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = {
	.md5_lookup		= tcp_v4_md5_lookup,
	.calc_md5_hash		= tcp_v4_md5_hash_skb,
	.md5_parse		= tcp_v4_parse_md5_keys,
};
#endif

/* NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */
static int tcp_v4_init_sock(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);

	tcp_init_sock(sk);

	icsk->icsk_af_ops = &ipv4_specific;

#ifdef CONFIG_TCP_MD5SIG
	tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific;
#endif

	return 0;
}

void tcp_v4_destroy_sock(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	tcp_clear_xmit_timers(sk);

	tcp_cleanup_congestion_control(sk);

	/* Cleanup up the write buffer. */
	tcp_write_queue_purge(sk);

	/* Cleans up our, hopefully empty, out_of_order_queue. */
	__skb_queue_purge(&tp->out_of_order_queue);

#ifdef CONFIG_TCP_MD5SIG
	/* Clean up the MD5 key list, if any */
	if (tp->md5sig_info) {
		tcp_clear_md5_list(sk);
		kfree_rcu(tp->md5sig_info, rcu);
		tp->md5sig_info = NULL;
	}
#endif

#ifdef CONFIG_NET_DMA
	/* Cleans up our sk_async_wait_queue */
	__skb_queue_purge(&sk->sk_async_wait_queue);
#endif

	/* Clean prequeue, it must be empty really */
	__skb_queue_purge(&tp->ucopy.prequeue);

	/* Clean up a referenced TCP bind bucket. */
	if (inet_csk(sk)->icsk_bind_hash)
		inet_put_port(sk);

	/* TCP Cookie Transactions */
	if (tp->cookie_values != NULL) {
		kref_put(&tp->cookie_values->kref,
			 tcp_cookie_values_release);
		tp->cookie_values = NULL;
	}
	BUG_ON(tp->fastopen_rsk != NULL);

	/* If socket is aborted during connect operation */
	tcp_free_fastopen_req(tp);

	sk_sockets_allocated_dec(sk);
	sock_release_memcg(sk);
}
EXPORT_SYMBOL(tcp_v4_destroy_sock);

#ifdef CONFIG_PROC_FS
/* Proc filesystem TCP sock list dumping. */

static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head)
{
	return hlist_nulls_empty(head) ? NULL :
		list_entry(head->first, struct inet_timewait_sock, tw_node);
}

static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw)
{
	return !is_a_nulls(tw->tw_node.next) ?
		hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
}

/*
 * Get next listener socket follow cur.  If cur is NULL, get first socket
 * starting from bucket given in st->bucket; when st->bucket is zero the
 * very first socket in the hash table is returned.
 */
static void *listening_get_next(struct seq_file *seq, void *cur)
{
	struct inet_connection_sock *icsk;
	struct hlist_nulls_node *node;
	struct sock *sk = cur;
	struct inet_listen_hashbucket *ilb;
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);

	if (!sk) {
		ilb = &tcp_hashinfo.listening_hash[st->bucket];
		spin_lock_bh(&ilb->lock);
		sk = sk_nulls_head(&ilb->head);
		st->offset = 0;
		goto get_sk;
	}
	ilb = &tcp_hashinfo.listening_hash[st->bucket];
	++st->num;
	++st->offset;

	if (st->state == TCP_SEQ_STATE_OPENREQ) {
		struct request_sock *req = cur;

		icsk = inet_csk(st->syn_wait_sk);
		req = req->dl_next;
		while (1) {
			while (req) {
				if (req->rsk_ops->family == st->family) {
					cur = req;
					goto out;
				}
				req = req->dl_next;
			}
			if (++st->sbucket >= icsk->icsk_accept_queue.listen_opt->nr_table_entries)
				break;
get_req:
			req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket];
		}
		sk	  = sk_nulls_next(st->syn_wait_sk);
		st->state = TCP_SEQ_STATE_LISTENING;
		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
	} else {
		icsk = inet_csk(sk);
		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
		if (reqsk_queue_len(&icsk->icsk_accept_queue))
			goto start_req;
		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
		sk = sk_nulls_next(sk);
	}
get_sk:
	sk_nulls_for_each_from(sk, node) {
		if (!net_eq(sock_net(sk), net))
			continue;
		if (sk->sk_family == st->family) {
			cur = sk;
			goto out;
		}
		icsk = inet_csk(sk);
		read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
		if (reqsk_queue_len(&icsk->icsk_accept_queue)) {
start_req:
			st->uid		= sock_i_uid(sk);
			st->syn_wait_sk = sk;
			st->state	= TCP_SEQ_STATE_OPENREQ;
			st->sbucket	= 0;
			goto get_req;
		}
		read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
	}
	spin_unlock_bh(&ilb->lock);
	st->offset = 0;
	if (++st->bucket < INET_LHTABLE_SIZE) {
		ilb = &tcp_hashinfo.listening_hash[st->bucket];
		spin_lock_bh(&ilb->lock);
		sk = sk_nulls_head(&ilb->head);
		goto get_sk;
	}
	cur = NULL;
out:
	return cur;
}

static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc;

	st->bucket = 0;
	st->offset = 0;
	rc = listening_get_next(seq, NULL);

	while (rc && *pos) {
		rc = listening_get_next(seq, rc);
		--*pos;
	}
	return rc;
}

static inline bool empty_bucket(struct tcp_iter_state *st)
{
	return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) &&
		hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain);
}

/*
 * Get first established socket starting from bucket given in st->bucket.
 * If st->bucket is zero, the very first socket in the hash is returned.
 */
static void *established_get_first(struct seq_file *seq)
{
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);
	void *rc = NULL;

	st->offset = 0;
	for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) {
		struct sock *sk;
		struct hlist_nulls_node *node;
		struct inet_timewait_sock *tw;
		spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket);

		/* Lockless fast path for the common case of empty buckets */
		if (empty_bucket(st))
			continue;

		spin_lock_bh(lock);
		sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) {
			if (sk->sk_family != st->family ||
			    !net_eq(sock_net(sk), net)) {
				continue;
			}
			rc = sk;
			goto out;
		}
		st->state = TCP_SEQ_STATE_TIME_WAIT;
		inet_twsk_for_each(tw, node,
				   &tcp_hashinfo.ehash[st->bucket].twchain) {
			if (tw->tw_family != st->family ||
			    !net_eq(twsk_net(tw), net)) {
				continue;
			}
			rc = tw;
			goto out;
		}
		spin_unlock_bh(lock);
		st->state = TCP_SEQ_STATE_ESTABLISHED;
	}
out:
	return rc;
}

static void *established_get_next(struct seq_file *seq, void *cur)
{
	struct sock *sk = cur;
	struct inet_timewait_sock *tw;
	struct hlist_nulls_node *node;
	struct tcp_iter_state *st = seq->private;
	struct net *net = seq_file_net(seq);

	++st->num;
	++st->offset;

	if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
		tw = cur;
		tw = tw_next(tw);
get_tw:
		while (tw && (tw->tw_family != st->family || !net_eq(twsk_net(tw), net))) {
			tw = tw_next(tw);
		}
		if (tw) {
			cur = tw;
			goto out;
		}
		spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
		st->state = TCP_SEQ_STATE_ESTABLISHED;

		/* Look for next non empty bucket */
		st->offset = 0;
		while (++st->bucket <= tcp_hashinfo.ehash_mask &&
				empty_bucket(st))
			;
		if (st->bucket > tcp_hashinfo.ehash_mask)
			return NULL;

		spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
		sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain);
	} else
		sk = sk_nulls_next(sk);

	sk_nulls_for_each_from(sk, node) {
		if (sk->sk_family == st->family && net_eq(sock_net(sk), net))
			goto found;
	}

	st->state = TCP_SEQ_STATE_TIME_WAIT;
	tw = tw_head(&tcp_hashinfo.ehash[st->bucket].twchain);
	goto get_tw;
found:
	cur = sk;
out:
	return cur;
}

static void *established_get_idx(struct seq_file *seq, loff_t pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc;

	st->bucket = 0;
	rc = established_get_first(seq);

	while (rc && pos) {
		rc = established_get_next(seq, rc);
		--pos;
	}
	return rc;
}

static void *tcp_get_idx(struct seq_file *seq, loff_t pos)
{
	void *rc;
	struct tcp_iter_state *st = seq->private;

	st->state = TCP_SEQ_STATE_LISTENING;
	rc	  = listening_get_idx(seq, &pos);

	if (!rc) {
		st->state = TCP_SEQ_STATE_ESTABLISHED;
		rc	  = established_get_idx(seq, pos);
	}

	return rc;
}

static void *tcp_seek_last_pos(struct seq_file *seq)
{
	struct tcp_iter_state *st = seq->private;
	int offset = st->offset;
	int orig_num = st->num;
	void *rc = NULL;

	switch (st->state) {
	case TCP_SEQ_STATE_OPENREQ:
	case TCP_SEQ_STATE_LISTENING:
		if (st->bucket >= INET_LHTABLE_SIZE)
			break;
		st->state = TCP_SEQ_STATE_LISTENING;
		rc = listening_get_next(seq, NULL);
		while (offset-- && rc)
			rc = listening_get_next(seq, rc);
		if (rc)
			break;
		st->bucket = 0;
		/* Fallthrough */
	case TCP_SEQ_STATE_ESTABLISHED:
	case TCP_SEQ_STATE_TIME_WAIT:
		st->state = TCP_SEQ_STATE_ESTABLISHED;
		if (st->bucket > tcp_hashinfo.ehash_mask)
			break;
		rc = established_get_first(seq);
		while (offset-- && rc)
			rc = established_get_next(seq, rc);
	}

	st->num = orig_num;

	return rc;
}

static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc;

	if (*pos && *pos == st->last_pos) {
		rc = tcp_seek_last_pos(seq);
		if (rc)
			goto out;
	}

	st->state = TCP_SEQ_STATE_LISTENING;
	st->num = 0;
	st->bucket = 0;
	st->offset = 0;
	rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;

out:
	st->last_pos = *pos;
	return rc;
}

static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct tcp_iter_state *st = seq->private;
	void *rc = NULL;

	if (v == SEQ_START_TOKEN) {
		rc = tcp_get_idx(seq, 0);
		goto out;
	}

	switch (st->state) {
	case TCP_SEQ_STATE_OPENREQ:
	case TCP_SEQ_STATE_LISTENING:
		rc = listening_get_next(seq, v);
		if (!rc) {
			st->state = TCP_SEQ_STATE_ESTABLISHED;
			st->bucket = 0;
			st->offset = 0;
			rc	  = established_get_first(seq);
		}
		break;
	case TCP_SEQ_STATE_ESTABLISHED:
	case TCP_SEQ_STATE_TIME_WAIT:
		rc = established_get_next(seq, v);
		break;
	}
out:
	++*pos;
	st->last_pos = *pos;
	return rc;
}

static void tcp_seq_stop(struct seq_file *seq, void *v)
{
	struct tcp_iter_state *st = seq->private;

	switch (st->state) {
	case TCP_SEQ_STATE_OPENREQ:
		if (v) {
			struct inet_connection_sock *icsk = inet_csk(st->syn_wait_sk);
			read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);
		}
	case TCP_SEQ_STATE_LISTENING:
		if (v != SEQ_START_TOKEN)
			spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock);
		break;
	case TCP_SEQ_STATE_TIME_WAIT:
	case TCP_SEQ_STATE_ESTABLISHED:
		if (v)
			spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket));
		break;
	}
}

int tcp_seq_open(struct inode *inode, struct file *file)
{
	struct tcp_seq_afinfo *afinfo = PDE(inode)->data;
	struct tcp_iter_state *s;
	int err;

	err = seq_open_net(inode, file, &afinfo->seq_ops,
			  sizeof(struct tcp_iter_state));
	if (err < 0)
		return err;

	s = ((struct seq_file *)file->private_data)->private;
	s->family		= afinfo->family;
	s->last_pos 		= 0;
	return 0;
}
EXPORT_SYMBOL(tcp_seq_open);

int tcp_proc_register(struct net *net, struct tcp_seq_afinfo *afinfo)
{
	int rc = 0;
	struct proc_dir_entry *p;

	afinfo->seq_ops.start		= tcp_seq_start;
	afinfo->seq_ops.next		= tcp_seq_next;
	afinfo->seq_ops.stop		= tcp_seq_stop;

	p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
			     afinfo->seq_fops, afinfo);
	if (!p)
		rc = -ENOMEM;
	return rc;
}
EXPORT_SYMBOL(tcp_proc_register);

void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
	proc_net_remove(net, afinfo->name);
}
EXPORT_SYMBOL(tcp_proc_unregister);

static void get_openreq4(const struct sock *sk, const struct request_sock *req,
			 struct seq_file *f, int i, kuid_t uid, int *len)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	long delta = req->expires - jiffies;

	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n",
		i,
		ireq->loc_addr,
		ntohs(inet_sk(sk)->inet_sport),
		ireq->rmt_addr,
		ntohs(ireq->rmt_port),
		TCP_SYN_RECV,
		0, 0, /* could print option size, but that is af dependent. */
		1,    /* timers active (only the expire timer) */
		jiffies_delta_to_clock_t(delta),
		req->num_timeout,
		from_kuid_munged(seq_user_ns(f), uid),
		0,  /* non standard timer */
		0, /* open_requests have no inode */
		atomic_read(&sk->sk_refcnt),
		req,
		len);
}

static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
{
	int timer_active;
	unsigned long timer_expires;
	const struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	const struct inet_sock *inet = inet_sk(sk);
	struct fastopen_queue *fastopenq = icsk->icsk_accept_queue.fastopenq;
	__be32 dest = inet->inet_daddr;
	__be32 src = inet->inet_rcv_saddr;
	__u16 destp = ntohs(inet->inet_dport);
	__u16 srcp = ntohs(inet->inet_sport);
	int rx_queue;

	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
		timer_active	= 1;
		timer_expires	= icsk->icsk_timeout;
	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
		timer_active	= 4;
		timer_expires	= icsk->icsk_timeout;
	} else if (timer_pending(&sk->sk_timer)) {
		timer_active	= 2;
		timer_expires	= sk->sk_timer.expires;
	} else {
		timer_active	= 0;
		timer_expires = jiffies;
	}

	if (sk->sk_state == TCP_LISTEN)
		rx_queue = sk->sk_ack_backlog;
	else
		/*
		 * because we dont lock socket, we might find a transient negative value
		 */
		rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);

	seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
			"%08X %5d %8d %lu %d %pK %lu %lu %u %u %d%n",
		i, src, srcp, dest, destp, sk->sk_state,
		tp->write_seq - tp->snd_una,
		rx_queue,
		timer_active,
		jiffies_delta_to_clock_t(timer_expires - jiffies),
		icsk->icsk_retransmits,
		from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)),
		icsk->icsk_probes_out,
		sock_i_ino(sk),
		atomic_read(&sk->sk_refcnt), sk,
		jiffies_to_clock_t(icsk->icsk_rto),
		jiffies_to_clock_t(icsk->icsk_ack.ato),
		(icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong,
		tp->snd_cwnd,
		sk->sk_state == TCP_LISTEN ?
		    (fastopenq ? fastopenq->max_qlen : 0) :
		    (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh),
		len);
}

static void get_timewait4_sock(const struct inet_timewait_sock *tw,
			       struct seq_file *f, int i, int *len)
{
	__be32 dest, src;
	__u16 destp, srcp;
	long delta = tw->tw_ttd - jiffies;

	dest  = tw->tw_daddr;
	src   = tw->tw_rcv_saddr;
	destp = ntohs(tw->tw_dport);
	srcp  = ntohs(tw->tw_sport);

	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK%n",
		i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
		3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0,
		atomic_read(&tw->tw_refcnt), tw, len);
}

#define TMPSZ 150

static int tcp4_seq_show(struct seq_file *seq, void *v)
{
	struct tcp_iter_state *st;
	int len;

	if (v == SEQ_START_TOKEN) {
		seq_printf(seq, "%-*s\n", TMPSZ - 1,
			   "  sl  local_address rem_address   st tx_queue "
			   "rx_queue tr tm->when retrnsmt   uid  timeout "
			   "inode");
		goto out;
	}
	st = seq->private;

	switch (st->state) {
	case TCP_SEQ_STATE_LISTENING:
	case TCP_SEQ_STATE_ESTABLISHED:
		get_tcp4_sock(v, seq, st->num, &len);
		break;
	case TCP_SEQ_STATE_OPENREQ:
		get_openreq4(st->syn_wait_sk, v, seq, st->num, st->uid, &len);
		break;
	case TCP_SEQ_STATE_TIME_WAIT:
		get_timewait4_sock(v, seq, st->num, &len);
		break;
	}
	seq_printf(seq, "%*s\n", TMPSZ - 1 - len, "");
out:
	return 0;
}

static const struct file_operations tcp_afinfo_seq_fops = {
	.owner   = THIS_MODULE,
	.open    = tcp_seq_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_net
};

static struct tcp_seq_afinfo tcp4_seq_afinfo = {
	.name		= "tcp",
	.family		= AF_INET,
	.seq_fops	= &tcp_afinfo_seq_fops,
	.seq_ops	= {
		.show		= tcp4_seq_show,
	},
};

static int __net_init tcp4_proc_init_net(struct net *net)
{
	return tcp_proc_register(net, &tcp4_seq_afinfo);
}

static void __net_exit tcp4_proc_exit_net(struct net *net)
{
	tcp_proc_unregister(net, &tcp4_seq_afinfo);
}

static struct pernet_operations tcp4_net_ops = {
	.init = tcp4_proc_init_net,
	.exit = tcp4_proc_exit_net,
};

int __init tcp4_proc_init(void)
{
	return register_pernet_subsys(&tcp4_net_ops);
}

void tcp4_proc_exit(void)
{
	unregister_pernet_subsys(&tcp4_net_ops);
}
#endif /* CONFIG_PROC_FS */

struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
{
	const struct iphdr *iph = skb_gro_network_header(skb);
	__wsum wsum;
	__sum16 sum;

	switch (skb->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (!tcp_v4_check(skb_gro_len(skb), iph->saddr, iph->daddr,
				  skb->csum)) {
			skb->ip_summed = CHECKSUM_UNNECESSARY;
			break;
		}
flush:
		NAPI_GRO_CB(skb)->flush = 1;
		return NULL;

	case CHECKSUM_NONE:
		wsum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
					  skb_gro_len(skb), IPPROTO_TCP, 0);
		sum = csum_fold(skb_checksum(skb,
					     skb_gro_offset(skb),
					     skb_gro_len(skb),
					     wsum));
		if (sum)
			goto flush;

		skb->ip_summed = CHECKSUM_UNNECESSARY;
		break;
	}

	return tcp_gro_receive(head, skb);
}

int tcp4_gro_complete(struct sk_buff *skb)
{
	const struct iphdr *iph = ip_hdr(skb);
	struct tcphdr *th = tcp_hdr(skb);

	th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb),
				  iph->saddr, iph->daddr, 0);
	skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;

	return tcp_gro_complete(skb);
}

struct proto tcp_prot = {
	.name			= "TCP",
	.owner			= THIS_MODULE,
	.close			= tcp_close,
	.connect		= tcp_v4_connect,
	.disconnect		= tcp_disconnect,
	.accept			= inet_csk_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v4_init_sock,
	.destroy		= tcp_v4_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.recvmsg		= tcp_recvmsg,
	.sendmsg		= tcp_sendmsg,
	.sendpage		= tcp_sendpage,
	.backlog_rcv		= tcp_v4_do_rcv,
	.release_cb		= tcp_release_cb,
	.mtu_reduced		= tcp_v4_mtu_reduced,
	.hash			= inet_hash,
	.unhash			= inet_unhash,
	.get_port		= inet_csk_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.sockets_allocated	= &tcp_sockets_allocated,
	.orphan_count		= &tcp_orphan_count,
	.memory_allocated	= &tcp_memory_allocated,
	.memory_pressure	= &tcp_memory_pressure,
	.sysctl_wmem		= sysctl_tcp_wmem,
	.sysctl_rmem		= sysctl_tcp_rmem,
	.max_header		= MAX_TCP_HEADER,
	.obj_size		= sizeof(struct tcp_sock),
	.slab_flags		= SLAB_DESTROY_BY_RCU,
	.twsk_prot		= &tcp_timewait_sock_ops,
	.rsk_prot		= &tcp_request_sock_ops,
	.h.hashinfo		= &tcp_hashinfo,
	.no_autobind		= true,
#ifdef CONFIG_COMPAT
	.compat_setsockopt	= compat_tcp_setsockopt,
	.compat_getsockopt	= compat_tcp_getsockopt,
#endif
#ifdef CONFIG_MEMCG_KMEM
	.init_cgroup		= tcp_init_cgroup,
	.destroy_cgroup		= tcp_destroy_cgroup,
	.proto_cgroup		= tcp_proto_cgroup,
#endif
};
EXPORT_SYMBOL(tcp_prot);

static int __net_init tcp_sk_init(struct net *net)
{
	return 0;
}

static void __net_exit tcp_sk_exit(struct net *net)
{
}

static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
{
	inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET);
}

static struct pernet_operations __net_initdata tcp_sk_ops = {
       .init	   = tcp_sk_init,
       .exit	   = tcp_sk_exit,
       .exit_batch = tcp_sk_exit_batch,
};

void __init tcp_v4_init(void)
{
	inet_hashinfo_init(&tcp_hashinfo);
	if (register_pernet_subsys(&tcp_sk_ops))
		panic("Failed to create the TCP control socket.\n");
}