tcp.c

linux 内核源代码

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

	if (tcp_send_head(sk)) {
		struct sk_buff *skb = tcp_write_queue_tail(sk);
		if (!(flags & MSG_MORE) || forced_push(tp))
			tcp_mark_push(tp, skb);
		tcp_mark_urg(tp, flags, skb);
		__tcp_push_pending_frames(sk, 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_sock *tp = tcp_sk(sk);
	int mss_now, size_goal;
	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));
	size_goal = tp->xmit_size_goal;
	copied = 0;

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

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

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

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

			skb_entail(sk, skb);
			copy = size_goal;
		}

		if (copy > size)
			copy = size;

		i = skb_shinfo(skb)->nr_frags;
		can_coalesce = skb_can_coalesce(skb, i, page, offset);
		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
			tcp_mark_push(tp, skb);
			goto new_segment;
		}
		if (!sk_stream_wmem_schedule(sk, copy))
			goto wait_for_memory;

		if (can_coalesce) {
			skb_shinfo(skb)->frags[i - 1].size += copy;
		} else {
			get_page(page);
			skb_fill_page_desc(skb, i, page, offset, copy);
		}

		skb->len += copy;
		skb->data_len += copy;
		skb->truesize += copy;
		sk->sk_wmem_queued += copy;
		sk->sk_forward_alloc -= copy;
		skb->ip_summed = CHECKSUM_PARTIAL;
		tp->write_seq += copy;
		TCP_SKB_CB(skb)->end_seq += copy;
		skb_shinfo(skb)->gso_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, mss_now, TCP_NAGLE_PUSH);
		} else if (skb == tcp_send_head(sk))
			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, 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));
		size_goal = tp->xmit_size_goal;
	}

out:
	if (copied)
		tcp_push(sk, 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;

	if (!(sk->sk_route_caps & NETIF_F_SG) ||
	    !(sk->sk_route_caps & NETIF_F_ALL_CSUM))
		return sock_no_sendpage(sock, page, offset, size, 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_sock *tp = tcp_sk(sk);
	int tmp = tp->mss_cache;

	if (sk->sk_route_caps & NETIF_F_SG) {
		if (sk_can_gso(sk))
			tmp = 0;
		else {
			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 socket *sock, struct msghdr *msg,
		size_t size)
{
	struct sock *sk = sock->sk;
	struct iovec *iov;
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	int iovlen, flags;
	int mss_now, size_goal;
	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));
	size_goal = tp->xmit_size_goal;

	/* 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 = tcp_write_queue_tail(sk);

			if (!tcp_send_head(sk) ||
			    (copy = size_goal - 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),
							   0, sk->sk_allocation);
				if (!skb)
					goto wait_for_memory;

				/*
				 * Check whether we can use HW checksum.
				 */
				if (sk->sk_route_caps & NETIF_F_ALL_CSUM)
					skb->ip_summed = CHECKSUM_PARTIAL;

				skb_entail(sk, skb);
				copy = size_goal;
			}

			/* 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 (off == PAGE_SIZE) {
						put_page(page);
						TCP_PAGE(sk) = page = NULL;
						off = 0;
					}
				} else
					off = 0;

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

				if (!sk_stream_wmem_schedule(sk, copy))
					goto wait_for_memory;

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

				/* 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;
					}
				}

				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)->gso_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, mss_now, TCP_NAGLE_PUSH);
			} else if (skb == tcp_send_head(sk))
				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, 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));
			size_goal = tp->xmit_size_goal;
		}
	}

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

do_fault:
	if (!skb->len) {
		tcp_unlink_write_queue(skb, sk);
		/* It is the one place in all of TCP, except connection
		 * reset, where we can be unlinking the send_head.
		 */
		tcp_check_send_head(sk, skb);
		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_sock *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.
 */
void tcp_cleanup_rbuf(struct sock *sk, int copied)
{
	struct tcp_sock *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 (inet_csk_ack_scheduled(sk)) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		   /* Delayed ACKs frequently hit locked sockets during bulk
		    * receive. */
		if (icsk->icsk_ack.blocked ||
		    /* Once-per-two-segments ACK was not sent by tcp_input.c */
		    tp->rcv_nxt - tp->rcv_wup > icsk->icsk_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 &&
		     ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) ||
		      ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) &&
		       !icsk->icsk_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)) {