tcp.c

Linux Kernel 2.6.9 for OMAP1710

				}

				TCP_OFF(sk) = off + copy;
			}

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

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

			from += copy;
			copied += copy;
			if ((seglen -= copy) == 0 && iovlen == 0)
				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);
	TCP_CHECK_TIMER(sk);
	release_sock(sk);
	return copied;

do_fault:
	if (!skb->len) {
		if (sk->sk_send_head == skb)
			sk->sk_send_head = NULL;
		__skb_unlink(skb, skb->list);
		sk_stream_free_skb(sk, skb);
	}

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

/*
 *	Handle reading urgent data. BSD has very simple semantics for
 *	this, no blocking and very strange errors 8)
 */

static int tcp_recv_urg(struct sock *sk, long timeo,
			struct msghdr *msg, int len, int flags,
			int *addr_len)
{
	struct tcp_opt *tp = tcp_sk(sk);

	/* No URG data to read. */
	if (sock_flag(sk, SOCK_URGINLINE) || !tp->urg_data ||
	    tp->urg_data == TCP_URG_READ)
		return -EINVAL;	/* Yes this is right ! */

	if (sk->sk_state == TCP_CLOSE && !sock_flag(sk, SOCK_DONE))
		return -ENOTCONN;

	if (tp->urg_data & TCP_URG_VALID) {
		int err = 0;
		char c = tp->urg_data;

		if (!(flags & MSG_PEEK))
			tp->urg_data = TCP_URG_READ;

		/* Read urgent data. */
		msg->msg_flags |= MSG_OOB;

		if (len > 0) {
			if (!(flags & MSG_TRUNC))
				err = memcpy_toiovec(msg->msg_iov, &c, 1);
			len = 1;
		} else
			msg->msg_flags |= MSG_TRUNC;

		return err ? -EFAULT : len;
	}

	if (sk->sk_state == TCP_CLOSE || (sk->sk_shutdown & RCV_SHUTDOWN))
		return 0;

	/* Fixed the recv(..., MSG_OOB) behaviour.  BSD docs and
	 * the available implementations agree in this case:
	 * this call should never block, independent of the
	 * blocking state of the socket.
	 * Mike <[e-mail]>
	 */
	return -EAGAIN;
}

/* Clean up the receive buffer for full frames taken by the user,
 * then send an ACK if necessary.  COPIED is the number of bytes
 * tcp_recvmsg has given to the user so far, it speeds up the
 * calculation of whether or not we must ACK for the sake of
 * a window update.
 */
static void cleanup_rbuf(struct sock *sk, int copied)
{
	struct tcp_opt *tp = tcp_sk(sk);
	int time_to_ack = 0;

#if TCP_DEBUG
	struct sk_buff *skb = skb_peek(&sk->sk_receive_queue);

	BUG_TRAP(!skb || before(tp->copied_seq, TCP_SKB_CB(skb)->end_seq));
#endif

	if (tcp_ack_scheduled(tp)) {
		   /* Delayed ACKs frequently hit locked sockets during bulk
		    * receive. */
		if (tp->ack.blocked ||
		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
		    tp->rcv_nxt - tp->rcv_wup > tp->ack.rcv_mss ||
		    /*
		     * If this read emptied read buffer, we send ACK, if
		     * connection is not bidirectional, user drained
		     * receive buffer and there was a small segment
		     * in queue.
		     */
		    (copied > 0 && (tp->ack.pending & TCP_ACK_PUSHED) &&
		     !tp->ack.pingpong && !atomic_read(&sk->sk_rmem_alloc)))
			time_to_ack = 1;
	}

	/* We send an ACK if we can now advertise a non-zero window
	 * which has been raised "significantly".
	 *
	 * Even if window raised up to infinity, do not send window open ACK
	 * in states, where we will not receive more. It is useless.
	 */
	if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) {
		__u32 rcv_window_now = tcp_receive_window(tp);

		/* Optimize, __tcp_select_window() is not cheap. */
		if (2*rcv_window_now <= tp->window_clamp) {
			__u32 new_window = __tcp_select_window(sk);

			/* Send ACK now, if this read freed lots of space
			 * in our buffer. Certainly, new_window is new window.
			 * We can advertise it now, if it is not less than current one.
			 * "Lots" means "at least twice" here.
			 */
			if (new_window && new_window >= 2 * rcv_window_now)
				time_to_ack = 1;
		}
	}
	if (time_to_ack)
		tcp_send_ack(sk);
}

static void tcp_prequeue_process(struct sock *sk)
{
	struct sk_buff *skb;
	struct tcp_opt *tp = tcp_sk(sk);

	NET_ADD_STATS_USER(LINUX_MIB_TCPPREQUEUED, skb_queue_len(&tp->ucopy.prequeue));

	/* RX process wants to run with disabled BHs, though it is not
	 * necessary */
	local_bh_disable();
	while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
		sk->sk_backlog_rcv(sk, skb);
	local_bh_enable();

	/* Clear memory counter. */
	tp->ucopy.memory = 0;
}

static inline struct sk_buff *tcp_recv_skb(struct sock *sk, u32 seq, u32 *off)
{
	struct sk_buff *skb;
	u32 offset;

	skb_queue_walk(&sk->sk_receive_queue, skb) {
		offset = seq - TCP_SKB_CB(skb)->seq;
		if (skb->h.th->syn)
			offset--;
		if (offset < skb->len || skb->h.th->fin) {
			*off = offset;
			return skb;
		}
	}
	return NULL;
}

/*
 * This routine provides an alternative to tcp_recvmsg() for routines
 * that would like to handle copying from skbuffs directly in 'sendfile'
 * fashion.
 * Note:
 *	- It is assumed that the socket was locked by the caller.
 *	- The routine does not block.
 *	- At present, there is no support for reading OOB data
 *	  or for 'peeking' the socket using this routine
 *	  (although both would be easy to implement).
 */
int tcp_read_sock(struct sock *sk, read_descriptor_t *desc,
		  sk_read_actor_t recv_actor)
{
	struct sk_buff *skb;
	struct tcp_opt *tp = tcp_sk(sk);
	u32 seq = tp->copied_seq;
	u32 offset;
	int copied = 0;

	if (sk->sk_state == TCP_LISTEN)
		return -ENOTCONN;
	while ((skb = tcp_recv_skb(sk, seq, &offset)) != NULL) {
		if (offset < skb->len) {
			size_t used, len;

			len = skb->len - offset;
			/* Stop reading if we hit a patch of urgent data */
			if (tp->urg_data) {
				u32 urg_offset = tp->urg_seq - seq;
				if (urg_offset < len)
					len = urg_offset;
				if (!len)
					break;
			}
			used = recv_actor(desc, skb, offset, len);
			if (used <= len) {
				seq += used;
				copied += used;
				offset += used;
			}
			if (offset != skb->len)
				break;
		}
		if (skb->h.th->fin) {
			sk_eat_skb(sk, skb);
			++seq;
			break;
		}
		sk_eat_skb(sk, skb);
		if (!desc->count)
			break;
	}
	tp->copied_seq = seq;

	tcp_rcv_space_adjust(sk);

	/* Clean up data we have read: This will do ACK frames. */
	if (copied)
		cleanup_rbuf(sk, copied);
	return copied;
}

/*
 *	This routine copies from a sock struct into the user buffer.
 *
 *	Technical note: in 2.3 we work on _locked_ socket, so that
 *	tricks with *seq access order and skb->users are not required.
 *	Probably, code can be easily improved even more.
 */

int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
		size_t len, int nonblock, int flags, int *addr_len)
{
	struct tcp_opt *tp = tcp_sk(sk);
	int copied = 0;
	u32 peek_seq;
	u32 *seq;
	unsigned long used;
	int err;
	int target;		/* Read at least this many bytes */
	long timeo;
	struct task_struct *user_recv = NULL;

	lock_sock(sk);

	TCP_CHECK_TIMER(sk);

	err = -ENOTCONN;
	if (sk->sk_state == TCP_LISTEN)
		goto out;

	timeo = sock_rcvtimeo(sk, nonblock);

	/* Urgent data needs to be handled specially. */
	if (flags & MSG_OOB)
		goto recv_urg;

	seq = &tp->copied_seq;
	if (flags & MSG_PEEK) {
		peek_seq = tp->copied_seq;
		seq = &peek_seq;
	}

	target = sock_rcvlowat(sk, flags & MSG_WAITALL, len);

	do {
		struct sk_buff *skb;
		u32 offset;

		/* Are we at urgent data? Stop if we have read anything or have SIGURG pending. */
		if (tp->urg_data && tp->urg_seq == *seq) {
			if (copied)
				break;
			if (signal_pending(current)) {
				copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
				break;
			}
		}

		/* Next get a buffer. */

		skb = skb_peek(&sk->sk_receive_queue);
		do {
			if (!skb)
				break;

			/* Now that we have two receive queues this
			 * shouldn't happen.
			 */
			if (before(*seq, TCP_SKB_CB(skb)->seq)) {
				printk(KERN_INFO "recvmsg bug: copied %X "
				       "seq %X\n", *seq, TCP_SKB_CB(skb)->seq);
				break;
			}
			offset = *seq - TCP_SKB_CB(skb)->seq;
			if (skb->h.th->syn)
				offset--;
			if (offset < skb->len)
				goto found_ok_skb;
			if (skb->h.th->fin)
				goto found_fin_ok;
			BUG_TRAP(flags & MSG_PEEK);
			skb = skb->next;
		} while (skb != (struct sk_buff *)&sk->sk_receive_queue);

		/* Well, if we have backlog, try to process it now yet. */

		if (copied >= target && !sk->sk_backlog.tail)
			break;

		if (copied) {
			if (sk->sk_err ||
			    sk->sk_state == TCP_CLOSE ||
			    (sk->sk_shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    signal_pending(current) ||
			    (flags & MSG_PEEK))
				break;
		} else {
			if (sock_flag(sk, SOCK_DONE))
				break;

			if (sk->sk_err) {
				copied = sock_error(sk);
				break;
			}

			if (sk->sk_shutdown & RCV_SHUTDOWN)
				break;

			if (sk->sk_state == TCP_CLOSE) {
				if (!sock_flag(sk, SOCK_DONE)) {
					/* This occurs when user tries to read
					 * from never connected socket.
					 */
					copied = -ENOTCONN;
					break;
				}
				break;
			}

			if (!timeo) {
				copied = -EAGAIN;
				break;
			}

			if (signal_pending(current)) {
				copied = sock_intr_errno(timeo);
				break;
			}
		}

		cleanup_rbuf(sk, copied);

		if (tp->ucopy.task == user_recv) {
			/* Install new reader */
			if (!user_recv && !(flags & (MSG_TRUNC | MSG_PEEK))) {
				user_recv = current;
				tp->ucopy.task = user_recv;
				tp->ucopy.iov = msg->msg_iov;
			}

			tp->ucopy.len = len;

			BUG_TRAP(tp->copied_seq == tp->rcv_nxt ||
				 (flags & (MSG_PEEK | MSG_TRUNC)));

			/* Ugly... If prequeue is not empty, we have to
			 * process it before releasing socket, otherwise
			 * order will be broken at second iteration.
			 * More elegant solution is required!!!
			 *
			 * Look: we have the following (pseudo)queues:
			 *
			 * 1. packets in flight
			 * 2. backlog
			 * 3. prequeue
			 * 4. receive_queue
			 *
			 * Each queue can be processed only if the next ones
			 * are empty. At this point we have empty receive_queue.
			 * But prequeue _can_ be not empty after 2nd iteration,
			 * when we jumped to start of loop because backlog
			 * processing added something to receive_queue.
			 * We cannot release_sock(), because backlog contains
			 * packets arrived _after_ prequeued ones.
			 *
			 * Shortly, algorithm is clear --- to process all
			 * the queues in order. We could make it more directly,
			 * requeueing packets from backlog to prequeue, if
			 * is not empty. It is more elegant, but eats cycles,
			 * unfortunately.
			 */
			if (skb_queue_len(&tp->ucopy.prequeue))
				goto do_prequeue;

			/* __ Set realtime policy in scheduler __ */
		}

		if (copied >= target) {
			/* Do not sleep, just process backlog. */
			release_sock(sk);
			lock_sock(sk);
		} else
			sk_wait_data(sk, &timeo);

		if (user_recv) {
			int chunk;

			/* __ Restore normal policy in scheduler __ */

			if ((chunk = len - tp->ucopy.len) != 0) {
				NET_ADD_STATS_USER(LINUX_MIB_TCPDIRECTCOPYFROMBACKLOG, chunk);