tcp_ipv4.c

struct tcp_func ipv4_specific = {
	.queue_xmit	=	ip_queue_xmit,
	.send_check	=	tcp_v4_send_check,
	.rebuild_header	=	tcp_v4_rebuild_header,
	.conn_request	=	tcp_v4_conn_request,
	.syn_recv_sock	=	tcp_v4_syn_recv_sock,
	.remember_stamp	=	tcp_v4_remember_stamp,
	.net_header_len	=	sizeof(struct iphdr),
	.setsockopt	=	ip_setsockopt,
	.getsockopt	=	ip_getsockopt,
	.addr2sockaddr	=	v4_addr2sockaddr,
	.sockaddr_len	=	sizeof(struct sockaddr_in),
};

/* 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 tcp_sock *tp = tcp_sk(sk);

	skb_queue_head_init(&tp->out_of_order_queue);
	tcp_init_xmit_timers(sk);
	tcp_prequeue_init(tp);

	tp->rto  = TCP_TIMEOUT_INIT;
	tp->mdev = TCP_TIMEOUT_INIT;

	/* So many TCP implementations out there (incorrectly) count the
	 * initial SYN frame in their delayed-ACK and congestion control
	 * algorithms that we must have the following bandaid to talk
	 * efficiently to them.  -DaveM
	 */
	tp->snd_cwnd = 2;

	/* See draft-stevens-tcpca-spec-01 for discussion of the
	 * initialization of these values.
	 */
	tp->snd_ssthresh = 0x7fffffff;	/* Infinity */
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache = 536;

	tp->reordering = sysctl_tcp_reordering;
	tp->ca_ops = &tcp_init_congestion_ops;

	sk->sk_state = TCP_CLOSE;

	sk->sk_write_space = sk_stream_write_space;
	sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);

	tp->af_specific = &ipv4_specific;

	sk->sk_sndbuf = sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sysctl_tcp_rmem[1];

	atomic_inc(&tcp_sockets_allocated);

	return 0;
}

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

	tcp_clear_xmit_timers(sk);

	tcp_cleanup_congestion_control(tp);

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

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

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

	/* Clean up a referenced TCP bind bucket. */
	if (tp->bind_hash)
		tcp_put_port(sk);

	/*
	 * If sendmsg cached page exists, toss it.
	 */
	if (sk->sk_sndmsg_page) {
		__free_page(sk->sk_sndmsg_page);
		sk->sk_sndmsg_page = NULL;
	}

	atomic_dec(&tcp_sockets_allocated);

	return 0;
}

EXPORT_SYMBOL(tcp_v4_destroy_sock);

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

static inline struct tcp_tw_bucket *tw_head(struct hlist_head *head)
{
	return hlist_empty(head) ? NULL :
		list_entry(head->first, struct tcp_tw_bucket, tw_node);
}

static inline struct tcp_tw_bucket *tw_next(struct tcp_tw_bucket *tw)
{
	return tw->tw_node.next ?
		hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL;
}

static void *listening_get_next(struct seq_file *seq, void *cur)
{
	struct tcp_sock *tp;
	struct hlist_node *node;
	struct sock *sk = cur;
	struct tcp_iter_state* st = seq->private;

	if (!sk) {
		st->bucket = 0;
		sk = sk_head(&tcp_listening_hash[0]);
		goto get_sk;
	}

	++st->num;

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

	       	tp = tcp_sk(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 >= TCP_SYNQ_HSIZE)
				break;
get_req:
			req = tp->accept_queue.listen_opt->syn_table[st->sbucket];
		}
		sk	  = sk_next(st->syn_wait_sk);
		st->state = TCP_SEQ_STATE_LISTENING;
		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
	} else {
	       	tp = tcp_sk(sk);
		read_lock_bh(&tp->accept_queue.syn_wait_lock);
		if (reqsk_queue_len(&tp->accept_queue))
			goto start_req;
		read_unlock_bh(&tp->accept_queue.syn_wait_lock);
		sk = sk_next(sk);
	}
get_sk:
	sk_for_each_from(sk, node) {
		if (sk->sk_family == st->family) {
			cur = sk;
			goto out;
		}
	       	tp = tcp_sk(sk);
		read_lock_bh(&tp->accept_queue.syn_wait_lock);
		if (reqsk_queue_len(&tp->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(&tp->accept_queue.syn_wait_lock);
	}
	if (++st->bucket < TCP_LHTABLE_SIZE) {
		sk = sk_head(&tcp_listening_hash[st->bucket]);
		goto get_sk;
	}
	cur = NULL;
out:
	return cur;
}

static void *listening_get_idx(struct seq_file *seq, loff_t *pos)
{
	void *rc = listening_get_next(seq, NULL);

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

static void *established_get_first(struct seq_file *seq)
{
	struct tcp_iter_state* st = seq->private;
	void *rc = NULL;

	for (st->bucket = 0; st->bucket < tcp_ehash_size; ++st->bucket) {
		struct sock *sk;
		struct hlist_node *node;
		struct tcp_tw_bucket *tw;

		/* We can reschedule _before_ having picked the target: */
		cond_resched_softirq();

		read_lock(&tcp_ehash[st->bucket].lock);
		sk_for_each(sk, node, &tcp_ehash[st->bucket].chain) {
			if (sk->sk_family != st->family) {
				continue;
			}
			rc = sk;
			goto out;
		}
		st->state = TCP_SEQ_STATE_TIME_WAIT;
		tw_for_each(tw, node,
			    &tcp_ehash[st->bucket + tcp_ehash_size].chain) {
			if (tw->tw_family != st->family) {
				continue;
			}
			rc = tw;
			goto out;
		}
		read_unlock(&tcp_ehash[st->bucket].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 tcp_tw_bucket *tw;
	struct hlist_node *node;
	struct tcp_iter_state* st = seq->private;

	++st->num;

	if (st->state == TCP_SEQ_STATE_TIME_WAIT) {
		tw = cur;
		tw = tw_next(tw);
get_tw:
		while (tw && tw->tw_family != st->family) {
			tw = tw_next(tw);
		}
		if (tw) {
			cur = tw;
			goto out;
		}
		read_unlock(&tcp_ehash[st->bucket].lock);
		st->state = TCP_SEQ_STATE_ESTABLISHED;

		/* We can reschedule between buckets: */
		cond_resched_softirq();

		if (++st->bucket < tcp_ehash_size) {
			read_lock(&tcp_ehash[st->bucket].lock);
			sk = sk_head(&tcp_ehash[st->bucket].chain);
		} else {
			cur = NULL;
			goto out;
		}
	} else
		sk = sk_next(sk);

	sk_for_each_from(sk, node) {
		if (sk->sk_family == st->family)
			goto found;
	}

	st->state = TCP_SEQ_STATE_TIME_WAIT;
	tw = tw_head(&tcp_ehash[st->bucket + tcp_ehash_size].chain);
	goto get_tw;
found:
	cur = sk;
out:
	return cur;
}

static void *established_get_idx(struct seq_file *seq, loff_t pos)
{
	void *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;

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

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

	return rc;
}

static void *tcp_seq_start(struct seq_file *seq, loff_t *pos)
{
	struct tcp_iter_state* st = seq->private;
	st->state = TCP_SEQ_STATE_LISTENING;
	st->num = 0;
	return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN;
}

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

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

	switch (st->state) {
	case TCP_SEQ_STATE_OPENREQ:
	case TCP_SEQ_STATE_LISTENING:
		rc = listening_get_next(seq, v);
		if (!rc) {
			tcp_listen_unlock();
			local_bh_disable();
			st->state = TCP_SEQ_STATE_ESTABLISHED;
			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;
	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 tcp_sock *tp = tcp_sk(st->syn_wait_sk);
			read_unlock_bh(&tp->accept_queue.syn_wait_lock);
		}
	case TCP_SEQ_STATE_LISTENING:
		if (v != SEQ_START_TOKEN)
			tcp_listen_unlock();
		break;
	case TCP_SEQ_STATE_TIME_WAIT:
	case TCP_SEQ_STATE_ESTABLISHED:
		if (v)
			read_unlock(&tcp_ehash[st->bucket].lock);
		local_bh_enable();
		break;
	}
}

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

	if (unlikely(afinfo == NULL))
		return -EINVAL;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (!s)
		return -ENOMEM;
	memset(s, 0, sizeof(*s));
	s->family		= afinfo->family;
	s->seq_ops.start	= tcp_seq_start;
	s->seq_ops.next		= tcp_seq_next;
	s->seq_ops.show		= afinfo->seq_show;
	s->seq_ops.stop		= tcp_seq_stop;

	rc = seq_open(file, &s->seq_ops);
	if (rc)
		goto out_kfree;
	seq	     = file->private_data;
	seq->private = s;
out:
	return rc;
out_kfree:
	kfree(s);
	goto out;
}

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

	if (!afinfo)
		return -EINVAL;
	afinfo->seq_fops->owner		= afinfo->owner;
	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_private;
	
	p = proc_net_fops_create(afinfo->name, S_IRUGO, afinfo->seq_fops);
	if (p)
		p->data = afinfo;
	else
		rc = -ENOMEM;
	return rc;
}

void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo)
{
	if (!afinfo)
		return;
	proc_net_remove(afinfo->name);
	memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); 
}

static void get_openreq4(struct sock *sk, struct request_sock *req,
			 char *tmpbuf, int i, int uid)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	int ttd = req->expires - jiffies;

	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %p",
		i,
		ireq->loc_addr,
		ntohs(inet_sk(sk)->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);
}

static void get_tcp4_sock(struct sock *sp, char *tmpbuf, int i)
{
	int timer_active;
	unsigned long timer_expires;
	struct tcp_sock *tp = tcp_sk(sp);
	struct inet_sock *inet = inet_sk(sp);
	unsigned int dest = inet->daddr;
	unsigned int src = inet->rcv_saddr;
	__u16 destp = ntohs(inet->dport);
	__u16 srcp = ntohs(inet->sport);

	if (tp->pending == TCP_TIME_RETRANS) {
		timer_active	= 1;
		timer_expires	= tp->timeout;
	} else if (tp->pending == TCP_TIME_PROBE0) {
		timer_active	= 4;
		timer_expires	= tp->timeout;
	} else if (timer_pending(&sp->sk_timer)) {
		timer_active	= 2;
		timer_expires	= sp->sk_timer.expires;
	} else {
		timer_active	= 0;
		timer_expires = jiffies;
	}

	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
			"%08X %5d %8d %lu %d %p %u %u %u %u %d",
		i, src, srcp, dest, destp, sp->sk_state,
		tp->write_seq - tp->snd_una, tp->rcv_nxt - tp->copied_seq,
		timer_active,
		jiffies_to_clock_t(timer_expires - jiffies),
		tp->retransmits,
		sock_i_uid(sp),
		tp->probes_out,
		sock_i_ino(sp),
		atomic_read(&sp->sk_refcnt), sp,
		tp->rto, tp->ack.ato, (tp->ack.quick << 1) | tp->ack.pingpong,
		tp->snd_cwnd,
		tp->snd_ssthresh >= 0xFFFF ? -1 : tp->snd_ssthresh);
}

static void get_timewait4_sock(struct tcp_tw_bucket *tw, char *tmpbuf, int i)
{
	unsigned int 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);

	sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X"
		" %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %p",
		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);
}

#define TMPSZ 150

static int tcp4_seq_show(struct seq_file *seq, void *v)
{
	struct tcp_iter_state* st;
	char tmpbuf[TMPSZ + 1];

	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, tmpbuf, st->num);
		break;
	case TCP_SEQ_STATE_OPENREQ:
		get_openreq4(st->syn_wait_sk, v, tmpbuf, st->num, st->uid);
		break;
	case TCP_SEQ_STATE_TIME_WAIT:
		get_timewait4_sock(v, tmpbuf, st->num);
		break;
	}
	seq_printf(seq, "%-*s\n", TMPSZ - 1, tmpbuf);
out:
	return 0;
}

static struct file_operations tcp4_seq_fops;
static struct tcp_seq_afinfo tcp4_seq_afinfo = {
	.owner		= THIS_MODULE,
	.name		= "tcp",
	.family		= AF_INET,
	.seq_show	= tcp4_seq_show,
	.seq_fops	= &tcp4_seq_fops,
};

int __init tcp4_proc_init(void)
{
	return tcp_proc_register(&tcp4_seq_afinfo);
}

void tcp4_proc_exit(void)
{
	tcp_proc_unregister(&tcp4_seq_afinfo);
}
#endif /* CONFIG_PROC_FS */

struct proto tcp_prot = {
	.name			= "TCP",
	.owner			= THIS_MODULE,
	.close			= tcp_close,
	.connect		= tcp_v4_connect,
	.disconnect		= tcp_disconnect,
	.accept			= tcp_accept,
	.ioctl			= tcp_ioctl,
	.init			= tcp_v4_init_sock,
	.destroy		= tcp_v4_destroy_sock,
	.shutdown		= tcp_shutdown,
	.setsockopt		= tcp_setsockopt,
	.getsockopt		= tcp_getsockopt,
	.sendmsg		= tcp_sendmsg,
	.recvmsg		= tcp_recvmsg,
	.backlog_rcv		= tcp_v4_do_rcv,
	.hash			= tcp_v4_hash,
	.unhash			= tcp_unhash,
	.get_port		= tcp_v4_get_port,
	.enter_memory_pressure	= tcp_enter_memory_pressure,
	.sockets_allocated	= &tcp_sockets_allocated,
	.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),
	.rsk_prot		= &tcp_request_sock_ops,
};



void __init tcp_v4_init(struct net_proto_family *ops)
{
	int err = sock_create_kern(PF_INET, SOCK_RAW, IPPROTO_TCP, &tcp_socket);
	if (err < 0)
		panic("Failed to create the TCP control socket.\n");
	tcp_socket->sk->sk_allocation   = GFP_ATOMIC;
	inet_sk(tcp_socket->sk)->uc_ttl = -1;

	/* Unhash it so that IP input processing does not even
	 * see it, we do not wish this socket to see incoming
	 * packets.
	 */
	tcp_socket->sk->sk_prot->unhash(tcp_socket->sk);
}

EXPORT_SYMBOL(ipv4_specific);
EXPORT_SYMBOL(tcp_bind_hash);
EXPORT_SYMBOL(tcp_bucket_create);
EXPORT_SYMBOL(tcp_hashinfo);
EXPORT_SYMBOL(tcp_inherit_port);
EXPORT_SYMBOL(tcp_listen_wlock);
EXPORT_SYMBOL(tcp_port_rover);
EXPORT_SYMBOL(tcp_prot);
EXPORT_SYMBOL(tcp_put_port);
EXPORT_SYMBOL(tcp_unhash);
EXPORT_SYMBOL(tcp_v4_conn_request);
EXPORT_SYMBOL(tcp_v4_connect);
EXPORT_SYMBOL(tcp_v4_do_rcv);
EXPORT_SYMBOL(tcp_v4_rebuild_header);
EXPORT_SYMBOL(tcp_v4_remember_stamp);
EXPORT_SYMBOL(tcp_v4_send_check);
EXPORT_SYMBOL(tcp_v4_syn_recv_sock);

#ifdef CONFIG_PROC_FS
EXPORT_SYMBOL(tcp_proc_register);
EXPORT_SYMBOL(tcp_proc_unregister);
#endif
EXPORT_SYMBOL(sysctl_local_port_range);
EXPORT_SYMBOL(sysctl_tcp_low_latency);
EXPORT_SYMBOL(sysctl_tcp_tw_reuse);