tcp_ipv4.c

		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 int 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;
	}
}

static 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;
}

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

	afinfo->seq_fops.open		= tcp_seq_open;
	afinfo->seq_fops.read		= seq_read;
	afinfo->seq_fops.llseek		= seq_lseek;
	afinfo->seq_fops.release	= seq_release_net;

	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(struct sock *sk, struct request_sock *req,
			 struct seq_file *f, int i, int uid, int *len)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	int ttd = req->expires - jiffies;

	seq_printf(f, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p%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_to_clock_t(ttd),
		req->retrans,
		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;
	struct tcp_sock *tp = tcp_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_sock *inet = inet_sk(sk);
	__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 %p %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_to_clock_t(timer_expires - jiffies),
		icsk->icsk_retransmits,
		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,
		tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh,
		len);
}

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

	if (ttd < 0)
		ttd = 0;

	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 %p%n",
		i, src, srcp, dest, destp, tw->tw_substate, 0, 0,
		3, jiffies_to_clock_t(ttd), 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 struct tcp_seq_afinfo tcp4_seq_afinfo = {
	.name		= "tcp",
	.family		= AF_INET,
	.seq_fops	= {
		.owner		= THIS_MODULE,
	},
	.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)
{
	struct iphdr *iph = skb_gro_network_header(skb);

	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;
		}

		/* fall through */
	case CHECKSUM_NONE:
		NAPI_GRO_CB(skb)->flush = 1;
		return NULL;
	}

	return tcp_gro_receive(head, skb);
}

int tcp4_gro_complete(struct sk_buff *skb)
{
	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,
	.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_mem		= sysctl_tcp_mem,
	.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
};
EXPORT_SYMBOL(tcp_prot);


static int __net_init tcp_sk_init(struct net *net)
{
	return inet_ctl_sock_create(&net->ipv4.tcp_sock,
				    PF_INET, SOCK_RAW, IPPROTO_TCP, net);
}

static void __net_exit tcp_sk_exit(struct net *net)
{
	inet_ctl_sock_destroy(net->ipv4.tcp_sock);
}

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");
}