tcp.c

《嵌入式系统设计与实例开发实验教材二源码》Linux内核移植与编译实验

}

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

	if (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 sock *sk, struct msghdr *msg, int size)
{
	struct iovec *iov;
	struct tcp_opt *tp;
	struct sk_buff *skb;
	int iovlen, flags;
	int mss_now;
	int err, copied;
	long timeo;

	tp = &(sk->tp_pinfo.af_tcp);

	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->state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
		if((err = wait_for_tcp_connect(sk, flags, &timeo)) != 0)
			goto out_err;

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

	mss_now = tcp_current_mss(sk);

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

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

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

		iov++;

		while (seglen > 0) {
			int copy;
			
			skb = sk->write_queue.prev;

			if (tp->send_head == NULL ||
			    (copy = mss_now - skb->len) <= 0) {

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

				skb = tcp_alloc_pskb(sk, select_size(sk, tp), 0, sk->allocation);
				if (skb == NULL)
					goto wait_for_memory;

				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 (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 == 0 && !(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=tcp_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 = tcp_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) == NULL) {
						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 {
					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;
					}
				}

				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;

			from += copy;
			copied += copy;
			seglen -= copy;

			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, 1);
			} else if (skb == tp->send_head)
				tcp_push_one(sk, mss_now);
			continue;

wait_for_sndbuf:
			set_bit(SOCK_NOSPACE, &sk->socket->flags);
wait_for_memory:
			if (copied)
				tcp_push(sk, tp, flags&~MSG_MORE, mss_now, 1);

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

			mss_now = tcp_current_mss(sk);
		}
	}

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 == 0) {
		if (tp->send_head == skb)
			tp->send_head = NULL;
		__skb_unlink(skb, skb->list);
		tcp_free_skb(sk, skb);
	}

do_error:
	if (copied)
		goto out;
out_err:
	err = tcp_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 = &(sk->tp_pinfo.af_tcp);

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

	if (sk->state==TCP_CLOSE && !sk->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->state == TCP_CLOSE || (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;
}

/*
 *	Release a skb if it is no longer needed. This routine
 *	must be called with interrupts disabled or with the
 *	socket locked so that the sk_buff queue operation is ok.
 */

static inline void tcp_eat_skb(struct sock *sk, struct sk_buff * skb)
{
	__skb_unlink(skb, &sk->receive_queue);
	__kfree_skb(skb);
}

/* 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 = &(sk->tp_pinfo.af_tcp);
	int time_to_ack = 0;

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

	BUG_TRAP(skb==NULL || 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->rmem_alloc) == 0)) {
			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->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);
}

/* Now socket state including sk->err is changed only under lock,
 * hence we may omit checks after joining wait queue.
 * We check receive queue before schedule() only as optimization;
 * it is very likely that release_sock() added new data.
 */

static long tcp_data_wait(struct sock *sk, long timeo)
{
	DECLARE_WAITQUEUE(wait, current);

	add_wait_queue(sk->sleep, &wait);

	__set_current_state(TASK_INTERRUPTIBLE);

	set_bit(SOCK_ASYNC_WAITDATA, &sk->socket->flags);
	release_sock(sk);

	if (skb_queue_empty(&sk->receive_queue))
		timeo = schedule_timeout(timeo);

	lock_sock(sk);
	clear_bit(SOCK_ASYNC_WAITDATA, &sk->socket->flags);

	remove_wait_queue(sk->sleep, &wait);
	__set_current_state(TASK_RUNNING);
	return timeo;
}

static void tcp_prequeue_process(struct sock *sk)
{
	struct sk_buff *skb;
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);

	net_statistics[smp_processor_id()*2+1].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->backlog_rcv(sk, skb);
	local_bh_enable();

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

/*
 *	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 sock *sk, struct msghdr *msg,
		int len, int nonblock, int flags, int *addr_len)
{
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);
	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->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. */
		if (copied && tp->urg_data && tp->urg_seq == *seq)
			break;

		/* We need to check signals first, to get correct SIGURG
		 * handling. FIXME: Need to check this doesnt impact 1003.1g
		 * and move it down to the bottom of the loop
		 */
		if (signal_pending(current)) {
			if (copied)
				break;
			copied = timeo ? sock_intr_errno(timeo) : -EAGAIN;
			break;
		}

		/* Next get a buffer. */

		skb = skb_peek(&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->receive_queue);

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

		if (copied >= target && sk->backlog.tail == NULL)
			break;

		if (copied) {
			if (sk->err ||
			    sk->state == TCP_CLOSE ||
			    (sk->shutdown & RCV_SHUTDOWN) ||
			    !timeo ||
			    (flags & MSG_PEEK))
				break;
		} else {
			if (sk->done)
				break;

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

			if (sk->shutdown & RCV_SHUTDOWN)