Message-ID: <4F7439AE.6050006@gmail.com>
Date:	Thu, 29 Mar 2012 18:30:06 +0800
From:	Li Yu <raise.sail@...il.com>
To:	Pavel Emelyanov <xemul@...allels.com>
CC:	Linux Netdev List <netdev@...r.kernel.org>,
	David Miller <davem@...emloft.net>
Subject: Re: [PATCH 3/3] tcp: Repair socket queues

于 2012年03月28日 23:38, Pavel Emelyanov 写道:
> Reading queues under repair mode is done with recvmsg call.
> The queue-under-repair set by TCP_REPAIR_QUEUE option is used
> to determine which queue should be read. Thus both send and
> receive queue can be read with this.
>
> Caller must pass the MSG_PEEK flag.
>
> Writing to queues is done with sendmsg call and yet again --
> the repair-queue option can be used to push data into the
> receive queue.
>
> When putting an skb into receive queue a zero tcp header is
> appented to its head to address the tcp_hdr(skb)->syn and
> the ->fin checks by the (after repair) tcp_recvmsg. These
> flags flags are both set to zero and that's why.
>
> The fin cannot be met in the queue while reading the source
> socket, since the repair only works for closed/established
> sockets and queueing fin packet always changes its state.
>
> The syn in the queue denotes that the respective skb's seq
> is "off-by-one" as compared to the actual payload lenght. Thus,
> at the rcv queue refill we can just drop this flag and set the
> skb's sequences to precice values. IOW -- emulate the situation
> when the packet with data and syn is splitted into two -- a
> packet with syn and a packet with data and the former one is
> already "eaten".
>
> When the repair mode is turned off, the write queue seqs are
> updated so that the whole queue is considered to be 'already sent,
> waiting for ACKs' (write_seq = snd_nxt<= snd_una). From the
> protocol POV the send queue looks like it was sent, but the data
> between the write_seq and snd_nxt is lost in the network.
>
> This helps to avoid another sockoption for setting the snd_nxt
> sequence. Leaving the whole queue in a 'not yet sent' state (as
> it will be after sendmsg-s) will not allow to receive any acks
> from the peer since the ack_seq will be after the snd_nxt. Thus
> even the ack for the window probe will be dropped and the
> connection will be 'locked' with the zero peer window.
>

Do we need to restore various TCP options switch bits. e.g. window
scale factor, sack_ok and so on.

En, I think the recorded mss_cache may be need to restored too.

Thanks.

Yu

> Signed-off-by: Pavel Emelyanov<xemul@...allels.com>
> ---
>   net/ipv4/tcp.c        |   89 +++++++++++++++++++++++++++++++++++++++++++++++--
>   net/ipv4/tcp_output.c |    1 +
>   2 files changed, 87 insertions(+), 3 deletions(-)
>
> diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
> index 65ae921..2ab3a31 100644
> --- a/net/ipv4/tcp.c
> +++ b/net/ipv4/tcp.c
> @@ -911,6 +911,39 @@ static inline int select_size(const struct sock *sk, bool sg)
>   	return tmp;
>   }
>
> +static int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
> +{
> +	struct sk_buff *skb;
> +	struct tcp_skb_cb *cb;
> +	struct tcphdr *th;
> +
> +	skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
> +	if (!skb)
> +		goto err;
> +
> +	th = (struct tcphdr *)skb_put(skb, sizeof(*th));
> +	skb_reset_transport_header(skb);
> +	memset(th, 0, sizeof(*th));
> +
> +	if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
> +		goto err_free;
> +
> +	cb = TCP_SKB_CB(skb);
> +
> +	TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
> +	TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(skb)->seq + size;
> +	TCP_SKB_CB(skb)->ack_seq = tcp_sk(sk)->snd_una - 1;
> +
> +	tcp_queue_rcv(sk, skb, sizeof(*th));
> +
> +	return size;
> +
> +err_free:
> +	kfree_skb(skb);
> +err:
> +	return -ENOMEM;
> +}
> +
>   int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
>   		size_t size)
>   {
> @@ -932,6 +965,19 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
>   		if ((err = sk_stream_wait_connect(sk,&timeo)) != 0)
>   			goto out_err;
>
> +	if (unlikely(tp->repair)) {
> +		if (tp->repair_queue == TCP_RECV_QUEUE) {
> +			copied = tcp_send_rcvq(sk, msg, size);
> +			goto out;
> +		}
> +
> +		err = -EINVAL;
> +		if (tp->repair_queue == TCP_NO_QUEUE)
> +			goto out_err;
> +
> +		/* 'common' sending to sendq */
> +	}
> +
>   	/* This should be in poll */
>   	clear_bit(SOCK_ASYNC_NOSPACE,&sk->sk_socket->flags);
>
> @@ -1089,7 +1135,7 @@ new_segment:
>   			if ((seglen -= copy) == 0&&  iovlen == 0)
>   				goto out;
>
> -			if (skb->len<  max || (flags&  MSG_OOB))
> +			if (skb->len<  max || (flags&  MSG_OOB) || tp->repair)
>   				continue;
>
>   			if (forced_push(tp)) {
> @@ -1102,7 +1148,7 @@ new_segment:
>   wait_for_sndbuf:
>   			set_bit(SOCK_NOSPACE,&sk->sk_socket->flags);
>   wait_for_memory:
> -			if (copied)
> +			if (copied&&  !tp->repair)
>   				tcp_push(sk, flags&  ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
>
>   			if ((err = sk_stream_wait_memory(sk,&timeo)) != 0)
> @@ -1113,7 +1159,7 @@ wait_for_memory:
>   	}
>
>   out:
> -	if (copied)
> +	if (copied&&  !tp->repair)
>   		tcp_push(sk, flags, mss_now, tp->nonagle);
>   	release_sock(sk);
>   	return copied;
> @@ -1187,6 +1233,24 @@ static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
>   	return -EAGAIN;
>   }
>
> +static int tcp_peek_sndq(struct sock *sk, struct msghdr *msg, int len)
> +{
> +	struct sk_buff *skb;
> +	int copied = 0, err = 0;
> +
> +	/* XXX -- need to support SO_PEEK_OFF */
> +
> +	skb_queue_walk(&sk->sk_write_queue, skb) {
> +		err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, skb->len);
> +		if (err)
> +			break;
> +
> +		copied += skb->len;
> +	}
> +
> +	return err ?: copied;
> +}
> +
>   /* 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
> @@ -1432,6 +1496,21 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
>   	if (flags&  MSG_OOB)
>   		goto recv_urg;
>
> +	if (unlikely(tp->repair)) {
> +		err = -EPERM;
> +		if (!(flags&  MSG_PEEK))
> +			goto out;
> +
> +		if (tp->repair_queue == TCP_SEND_QUEUE)
> +			goto recv_sndq;
> +
> +		err = -EINVAL;
> +		if (tp->repair_queue == TCP_NO_QUEUE)
> +			goto out;
> +
> +		/* 'common' recv queue MSG_PEEK-ing */
> +	}
> +
>   	seq =&tp->copied_seq;
>   	if (flags&  MSG_PEEK) {
>   		peek_seq = tp->copied_seq;
> @@ -1783,6 +1862,10 @@ out:
>   recv_urg:
>   	err = tcp_recv_urg(sk, msg, len, flags);
>   	goto out;
> +
> +recv_sndq:
> +	err = tcp_peek_sndq(sk, msg, len);
> +	goto out;
>   }
>   EXPORT_SYMBOL(tcp_recvmsg);
>
> diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
> index 4e2ce39..b29d612 100644
> --- a/net/ipv4/tcp_output.c
> +++ b/net/ipv4/tcp_output.c
> @@ -2796,6 +2796,7 @@ void tcp_send_window_probe(struct sock *sk)
>   {
>   	if (sk->sk_state == TCP_ESTABLISHED) {
>   		tcp_sk(sk)->snd_wl1 = tcp_sk(sk)->rcv_nxt - 1;
> +		tcp_sk(sk)->snd_nxt = tcp_sk(sk)->write_seq;
>   		tcp_xmit_probe_skb(sk, 0);
>   	}
>   }

--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Powered by blists - more mailing lists