tcp.c

Linux Kernel 2.6.9 for OMAP1710

	sk->sk_max_ack_backlog = 0;
	sk->sk_ack_backlog = 0;
	tp->accept_queue = tp->accept_queue_tail = NULL;
	tp->syn_wait_lock = RW_LOCK_UNLOCKED;
	tcp_delack_init(tp);

	lopt = kmalloc(sizeof(struct tcp_listen_opt), GFP_KERNEL);
	if (!lopt)
		return -ENOMEM;

	memset(lopt, 0, sizeof(struct tcp_listen_opt));
	for (lopt->max_qlen_log = 6; ; lopt->max_qlen_log++)
		if ((1 << lopt->max_qlen_log) >= sysctl_max_syn_backlog)
			break;
	get_random_bytes(&lopt->hash_rnd, 4);

	write_lock_bh(&tp->syn_wait_lock);
	tp->listen_opt = lopt;
	write_unlock_bh(&tp->syn_wait_lock);

	/* There is race window here: we announce ourselves listening,
	 * but this transition is still not validated by get_port().
	 * It is OK, because this socket enters to hash table only
	 * after validation is complete.
	 */
	sk->sk_state = TCP_LISTEN;
	if (!sk->sk_prot->get_port(sk, inet->num)) {
		inet->sport = htons(inet->num);

		sk_dst_reset(sk);
		sk->sk_prot->hash(sk);

		return 0;
	}

	sk->sk_state = TCP_CLOSE;
	write_lock_bh(&tp->syn_wait_lock);
	tp->listen_opt = NULL;
	write_unlock_bh(&tp->syn_wait_lock);
	kfree(lopt);
	return -EADDRINUSE;
}

/*
 *	This routine closes sockets which have been at least partially
 *	opened, but not yet accepted.
 */

static void tcp_listen_stop (struct sock *sk)
{
	struct tcp_opt *tp = tcp_sk(sk);
	struct tcp_listen_opt *lopt = tp->listen_opt;
	struct open_request *acc_req = tp->accept_queue;
	struct open_request *req;
	int i;

	tcp_delete_keepalive_timer(sk);

	/* make all the listen_opt local to us */
	write_lock_bh(&tp->syn_wait_lock);
	tp->listen_opt = NULL;
	write_unlock_bh(&tp->syn_wait_lock);
	tp->accept_queue = tp->accept_queue_tail = NULL;

	if (lopt->qlen) {
		for (i = 0; i < TCP_SYNQ_HSIZE; i++) {
			while ((req = lopt->syn_table[i]) != NULL) {
				lopt->syn_table[i] = req->dl_next;
				lopt->qlen--;
				tcp_openreq_free(req);

		/* Following specs, it would be better either to send FIN
		 * (and enter FIN-WAIT-1, it is normal close)
		 * or to send active reset (abort).
		 * Certainly, it is pretty dangerous while synflood, but it is
		 * bad justification for our negligence 8)
		 * To be honest, we are not able to make either
		 * of the variants now.			--ANK
		 */
			}
		}
	}
	BUG_TRAP(!lopt->qlen);

	kfree(lopt);

	while ((req = acc_req) != NULL) {
		struct sock *child = req->sk;

		acc_req = req->dl_next;

		local_bh_disable();
		bh_lock_sock(child);
		BUG_TRAP(!sock_owned_by_user(child));
		sock_hold(child);

		tcp_disconnect(child, O_NONBLOCK);

		sock_orphan(child);

		atomic_inc(&tcp_orphan_count);

		tcp_destroy_sock(child);

		bh_unlock_sock(child);
		local_bh_enable();
		sock_put(child);

		sk_acceptq_removed(sk);
		tcp_openreq_fastfree(req);
	}
	BUG_TRAP(!sk->sk_ack_backlog);
}

static inline void tcp_mark_push(struct tcp_opt *tp, struct sk_buff *skb)
{
	TCP_SKB_CB(skb)->flags |= TCPCB_FLAG_PSH;
	tp->pushed_seq = tp->write_seq;
}

static inline int forced_push(struct tcp_opt *tp)
{
	return after(tp->write_seq, tp->pushed_seq + (tp->max_window >> 1));
}

static inline void skb_entail(struct sock *sk, struct tcp_opt *tp,
			      struct sk_buff *skb)
{
	skb->csum = 0;
	TCP_SKB_CB(skb)->seq = tp->write_seq;
	TCP_SKB_CB(skb)->end_seq = tp->write_seq;
	TCP_SKB_CB(skb)->flags = TCPCB_FLAG_ACK;
	TCP_SKB_CB(skb)->sacked = 0;
	__skb_queue_tail(&sk->sk_write_queue, skb);
	sk_charge_skb(sk, skb);
	if (!sk->sk_send_head)
		sk->sk_send_head = skb;
	else if (tp->nonagle&TCP_NAGLE_PUSH)
		tp->nonagle &= ~TCP_NAGLE_PUSH; 
}

static inline void tcp_mark_urg(struct tcp_opt *tp, int flags,
				struct sk_buff *skb)
{
	if (flags & MSG_OOB) {
		tp->urg_mode = 1;
		tp->snd_up = tp->write_seq;
		TCP_SKB_CB(skb)->sacked |= TCPCB_URG;
	}
}

static inline void tcp_push(struct sock *sk, struct tcp_opt *tp, int flags,
			    int mss_now, int nonagle)
{
	if (sk->sk_send_head) {
		struct sk_buff *skb = sk->sk_write_queue.prev;
		if (!(flags & MSG_MORE) || forced_push(tp))
			tcp_mark_push(tp, skb);
		tcp_mark_urg(tp, flags, skb);
		__tcp_push_pending_frames(sk, tp, mss_now,
					  (flags & MSG_MORE) ? TCP_NAGLE_CORK : nonagle);
	}
}

static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
			 size_t psize, int flags)
{
	struct tcp_opt *tp = tcp_sk(sk);
	int mss_now;
	int err;
	ssize_t copied;
	long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_err;

	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
	copied = 0;

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
		goto do_error;

	while (psize > 0) {
		struct sk_buff *skb = sk->sk_write_queue.prev;
		struct page *page = pages[poffset / PAGE_SIZE];
		int copy, i;
		int offset = poffset % PAGE_SIZE;
		int size = min_t(size_t, psize, PAGE_SIZE - offset);

		if (!sk->sk_send_head || (copy = mss_now - skb->len) <= 0) {
new_segment:
			if (!sk_stream_memory_free(sk))
				goto wait_for_sndbuf;

			skb = sk_stream_alloc_pskb(sk, 0, tp->mss_cache,
						   sk->sk_allocation);
			if (!skb)
				goto wait_for_memory;

			skb_entail(sk, tp, skb);
			copy = mss_now;
		}

		if (copy > size)
			copy = size;

		i = skb_shinfo(skb)->nr_frags;
		if (skb_can_coalesce(skb, i, page, offset)) {
			skb_shinfo(skb)->frags[i - 1].size += copy;
		} else if (i < MAX_SKB_FRAGS) {
			get_page(page);
			skb_fill_page_desc(skb, i, page, offset, copy);
		} else {
			tcp_mark_push(tp, skb);
			goto new_segment;
		}

		skb->len += copy;
		skb->data_len += copy;
		skb->ip_summed = CHECKSUM_HW;
		tp->write_seq += copy;
		TCP_SKB_CB(skb)->end_seq += copy;
		skb_shinfo(skb)->tso_segs = 0;

		if (!copied)
			TCP_SKB_CB(skb)->flags &= ~TCPCB_FLAG_PSH;

		copied += copy;
		poffset += copy;
		if (!(psize -= copy))
			goto out;

		if (skb->len != mss_now || (flags & MSG_OOB))
			continue;

		if (forced_push(tp)) {
			tcp_mark_push(tp, skb);
			__tcp_push_pending_frames(sk, tp, mss_now, TCP_NAGLE_PUSH);
		} else if (skb == sk->sk_send_head)
			tcp_push_one(sk, mss_now);
		continue;

wait_for_sndbuf:
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
		if (copied)
			tcp_push(sk, tp, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);

		if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
			goto do_error;

		mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));
	}

out:
	if (copied)
		tcp_push(sk, tp, flags, mss_now, tp->nonagle);
	return copied;

do_error:
	if (copied)
		goto out;
out_err:
	return sk_stream_error(sk, flags, err);
}

ssize_t tcp_sendpage(struct socket *sock, struct page *page, int offset,
		     size_t size, int flags)
{
	ssize_t res;
	struct sock *sk = sock->sk;

#define TCP_ZC_CSUM_FLAGS (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM | NETIF_F_HW_CSUM)

	if (!(sk->sk_route_caps & NETIF_F_SG) ||
	    !(sk->sk_route_caps & TCP_ZC_CSUM_FLAGS))
		return sock_no_sendpage(sock, page, offset, size, flags);

#undef TCP_ZC_CSUM_FLAGS

	lock_sock(sk);
	TCP_CHECK_TIMER(sk);
	res = do_tcp_sendpages(sk, &page, offset, size, flags);
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return res;
}

#define TCP_PAGE(sk)	(sk->sk_sndmsg_page)
#define TCP_OFF(sk)	(sk->sk_sndmsg_off)

static inline int select_size(struct sock *sk, struct tcp_opt *tp)
{
	int tmp = tp->mss_cache_std;

	if (sk->sk_route_caps & NETIF_F_SG) {
		int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER);

		if (tmp >= pgbreak &&
		    tmp <= pgbreak + (MAX_SKB_FRAGS - 1) * PAGE_SIZE)
			tmp = pgbreak;
	}
	return tmp;
}

int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t size)
{
	struct iovec *iov;
	struct tcp_opt *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int iovlen, flags;
	int mss_now;
	int err, copied;
	long timeo;

	lock_sock(sk);
	TCP_CHECK_TIMER(sk);

	flags = msg->msg_flags;
	timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);

	/* Wait for a connection to finish. */
	if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
			goto out_err;

	/* This should be in poll */
	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);

	mss_now = tcp_current_mss(sk, !(flags&MSG_OOB));

	/* Ok commence sending. */
	iovlen = msg->msg_iovlen;
	iov = msg->msg_iov;
	copied = 0;

	err = -EPIPE;
	if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
		goto do_error;

	while (--iovlen >= 0) {
		int seglen = iov->iov_len;
		unsigned char __user *from = iov->iov_base;

		iov++;

		while (seglen > 0) {
			int copy;

			skb = sk->sk_write_queue.prev;

			if (!sk->sk_send_head ||
			    (copy = mss_now - skb->len) <= 0) {

new_segment:
				/* Allocate new segment. If the interface is SG,
				 * allocate skb fitting to single page.
				 */
				if (!sk_stream_memory_free(sk))
					goto wait_for_sndbuf;

				skb = sk_stream_alloc_pskb(sk, select_size(sk, tp),
							   0, sk->sk_allocation);
				if (!skb)
					goto wait_for_memory;

				/*
				 * Check whether we can use HW checksum.
				 */
				if (sk->sk_route_caps &
				    (NETIF_F_IP_CSUM | NETIF_F_NO_CSUM |
				     NETIF_F_HW_CSUM))
					skb->ip_summed = CHECKSUM_HW;

				skb_entail(sk, tp, skb);
				copy = mss_now;
			}

			/* Try to append data to the end of skb. */
			if (copy > seglen)
				copy = seglen;

			/* Where to copy to? */
			if (skb_tailroom(skb) > 0) {
				/* We have some space in skb head. Superb! */
				if (copy > skb_tailroom(skb))
					copy = skb_tailroom(skb);
				if ((err = skb_add_data(skb, from, copy)) != 0)
					goto do_fault;
			} else {
				int merge = 0;
				int i = skb_shinfo(skb)->nr_frags;
				struct page *page = TCP_PAGE(sk);
				int off = TCP_OFF(sk);

				if (skb_can_coalesce(skb, i, page, off) &&
				    off != PAGE_SIZE) {
					/* We can extend the last page
					 * fragment. */
					merge = 1;
				} else if (i == MAX_SKB_FRAGS ||
					   (!i &&
					   !(sk->sk_route_caps & NETIF_F_SG))) {
					/* Need to add new fragment and cannot
					 * do this because interface is non-SG,
					 * or because all the page slots are
					 * busy. */
					tcp_mark_push(tp, skb);
					goto new_segment;
				} else if (page) {
					/* If page is cached, align
					 * offset to L1 cache boundary
					 */
					off = (off + L1_CACHE_BYTES - 1) &
					      ~(L1_CACHE_BYTES - 1);
					if (off == PAGE_SIZE) {
						put_page(page);
						TCP_PAGE(sk) = page = NULL;
					}
				}

				if (!page) {
					/* Allocate new cache page. */
					if (!(page = sk_stream_alloc_page(sk)))
						goto wait_for_memory;
					off = 0;
				}

				if (copy > PAGE_SIZE - off)
					copy = PAGE_SIZE - off;

				/* Time to copy data. We are close to
				 * the end! */
				err = skb_copy_to_page(sk, from, skb, page,
						       off, copy);
				if (err) {
					/* If this page was new, give it to the
					 * socket so it does not get leaked.
					 */
					if (!TCP_PAGE(sk)) {
						TCP_PAGE(sk) = page;
						TCP_OFF(sk) = 0;
					}
					goto do_error;
				}

				/* Update the skb. */
				if (merge) {
					skb_shinfo(skb)->frags[i - 1].size +=
									copy;
				} else {
					skb_fill_page_desc(skb, i, page, off, copy);
					if (TCP_PAGE(sk)) {
						get_page(page);
					} else if (off + copy < PAGE_SIZE) {
						get_page(page);
						TCP_PAGE(sk) = page;
					}