output.c

linux 内核源代码

/*
 *  net/dccp/output.c
 *
 *  An implementation of the DCCP protocol
 *  Arnaldo Carvalho de Melo <[e-mail]>
 *
 *	This program is free software; you can redistribute it and/or
 *	modify it under the terms of the GNU General Public License
 *	as published by the Free Software Foundation; either version
 *	2 of the License, or (at your option) any later version.
 */

#include <linux/dccp.h>
#include <linux/kernel.h>
#include <linux/skbuff.h>

#include <net/inet_sock.h>
#include <net/sock.h>

#include "ackvec.h"
#include "ccid.h"
#include "dccp.h"

static inline void dccp_event_ack_sent(struct sock *sk)
{
	inet_csk_clear_xmit_timer(sk, ICSK_TIME_DACK);
}

static void dccp_skb_entail(struct sock *sk, struct sk_buff *skb)
{
	skb_set_owner_w(skb, sk);
	WARN_ON(sk->sk_send_head);
	sk->sk_send_head = skb;
}

/*
 * All SKB's seen here are completely headerless. It is our
 * job to build the DCCP header, and pass the packet down to
 * IP so it can do the same plus pass the packet off to the
 * device.
 */
static int dccp_transmit_skb(struct sock *sk, struct sk_buff *skb)
{
	if (likely(skb != NULL)) {
		const struct inet_sock *inet = inet_sk(sk);
		const struct inet_connection_sock *icsk = inet_csk(sk);
		struct dccp_sock *dp = dccp_sk(sk);
		struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
		struct dccp_hdr *dh;
		/* XXX For now we're using only 48 bits sequence numbers */
		const u32 dccp_header_size = sizeof(*dh) +
					     sizeof(struct dccp_hdr_ext) +
					  dccp_packet_hdr_len(dcb->dccpd_type);
		int err, set_ack = 1;
		u64 ackno = dp->dccps_gsr;

		dccp_inc_seqno(&dp->dccps_gss);

		switch (dcb->dccpd_type) {
		case DCCP_PKT_DATA:
			set_ack = 0;
			/* fall through */
		case DCCP_PKT_DATAACK:
		case DCCP_PKT_RESET:
			break;

		case DCCP_PKT_REQUEST:
			set_ack = 0;
			/* fall through */

		case DCCP_PKT_SYNC:
		case DCCP_PKT_SYNCACK:
			ackno = dcb->dccpd_ack_seq;
			/* fall through */
		default:
			/*
			 * Set owner/destructor: some skbs are allocated via
			 * alloc_skb (e.g. when retransmission may happen).
			 * Only Data, DataAck, and Reset packets should come
			 * through here with skb->sk set.
			 */
			WARN_ON(skb->sk);
			skb_set_owner_w(skb, sk);
			break;
		}

		dcb->dccpd_seq = dp->dccps_gss;

		if (dccp_insert_options(sk, skb)) {
			kfree_skb(skb);
			return -EPROTO;
		}


		/* Build DCCP header and checksum it. */
		dh = dccp_zeroed_hdr(skb, dccp_header_size);
		dh->dccph_type	= dcb->dccpd_type;
		dh->dccph_sport	= inet->sport;
		dh->dccph_dport	= inet->dport;
		dh->dccph_doff	= (dccp_header_size + dcb->dccpd_opt_len) / 4;
		dh->dccph_ccval	= dcb->dccpd_ccval;
		dh->dccph_cscov = dp->dccps_pcslen;
		/* XXX For now we're using only 48 bits sequence numbers */
		dh->dccph_x	= 1;

		dp->dccps_awh = dp->dccps_gss;
		dccp_hdr_set_seq(dh, dp->dccps_gss);
		if (set_ack)
			dccp_hdr_set_ack(dccp_hdr_ack_bits(skb), ackno);

		switch (dcb->dccpd_type) {
		case DCCP_PKT_REQUEST:
			dccp_hdr_request(skb)->dccph_req_service =
							dp->dccps_service;
			break;
		case DCCP_PKT_RESET:
			dccp_hdr_reset(skb)->dccph_reset_code =
							dcb->dccpd_reset_code;
			break;
		}

		icsk->icsk_af_ops->send_check(sk, 0, skb);

		if (set_ack)
			dccp_event_ack_sent(sk);

		DCCP_INC_STATS(DCCP_MIB_OUTSEGS);

		memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
		err = icsk->icsk_af_ops->queue_xmit(skb, 0);
		return net_xmit_eval(err);
	}
	return -ENOBUFS;
}

unsigned int dccp_sync_mss(struct sock *sk, u32 pmtu)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct dccp_sock *dp = dccp_sk(sk);
	int mss_now = (pmtu - icsk->icsk_af_ops->net_header_len -
		       sizeof(struct dccp_hdr) - sizeof(struct dccp_hdr_ext));

	/* Now subtract optional transport overhead */
	mss_now -= icsk->icsk_ext_hdr_len;

	/*
	 * FIXME: this should come from the CCID infrastructure, where, say,
	 * TFRC will say it wants TIMESTAMPS, ELAPSED time, etc, for now lets
	 * put a rough estimate for NDP + TIMESTAMP + TIMESTAMP_ECHO + ELAPSED
	 * TIME + TFRC_OPT_LOSS_EVENT_RATE + TFRC_OPT_RECEIVE_RATE + padding to
	 * make it a multiple of 4
	 */

	mss_now -= ((5 + 6 + 10 + 6 + 6 + 6 + 3) / 4) * 4;

	/* And store cached results */
	icsk->icsk_pmtu_cookie = pmtu;
	dp->dccps_mss_cache = mss_now;

	return mss_now;
}

EXPORT_SYMBOL_GPL(dccp_sync_mss);

void dccp_write_space(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);

	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
	/* Should agree with poll, otherwise some programs break */
	if (sock_writeable(sk))
		sk_wake_async(sk, 2, POLL_OUT);

	read_unlock(&sk->sk_callback_lock);
}

/**
 * dccp_wait_for_ccid - Wait for ccid to tell us we can send a packet
 * @sk:    socket to wait for
 * @skb:   current skb to pass on for waiting
 * @delay: sleep timeout in milliseconds (> 0)
 * This function is called by default when the socket is closed, and
 * when a non-zero linger time is set on the socket. For consistency
 */
static int dccp_wait_for_ccid(struct sock *sk, struct sk_buff *skb, int delay)
{
	struct dccp_sock *dp = dccp_sk(sk);
	DEFINE_WAIT(wait);
	unsigned long jiffdelay;
	int rc;

	do {
		dccp_pr_debug("delayed send by %d msec\n", delay);
		jiffdelay = msecs_to_jiffies(delay);

		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);

		sk->sk_write_pending++;
		release_sock(sk);
		schedule_timeout(jiffdelay);
		lock_sock(sk);
		sk->sk_write_pending--;

		if (sk->sk_err)
			goto do_error;
		if (signal_pending(current))
			goto do_interrupted;

		rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);
	} while ((delay = rc) > 0);
out:
	finish_wait(sk->sk_sleep, &wait);
	return rc;

do_error:
	rc = -EPIPE;
	goto out;
do_interrupted:
	rc = -EINTR;
	goto out;
}

void dccp_write_xmit(struct sock *sk, int block)
{
	struct dccp_sock *dp = dccp_sk(sk);
	struct sk_buff *skb;

	while ((skb = skb_peek(&sk->sk_write_queue))) {
		int err = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);

		if (err > 0) {
			if (!block) {
				sk_reset_timer(sk, &dp->dccps_xmit_timer,
						msecs_to_jiffies(err)+jiffies);
				break;
			} else
				err = dccp_wait_for_ccid(sk, skb, err);
			if (err && err != -EINTR)
				DCCP_BUG("err=%d after dccp_wait_for_ccid", err);
		}

		skb_dequeue(&sk->sk_write_queue);
		if (err == 0) {
			struct dccp_skb_cb *dcb = DCCP_SKB_CB(skb);
			const int len = skb->len;

			if (sk->sk_state == DCCP_PARTOPEN) {
				/* See 8.1.5.  Handshake Completion */
				inet_csk_schedule_ack(sk);
				inet_csk_reset_xmit_timer(sk, ICSK_TIME_DACK,
						  inet_csk(sk)->icsk_rto,
						  DCCP_RTO_MAX);
				dcb->dccpd_type = DCCP_PKT_DATAACK;
			} else if (dccp_ack_pending(sk))
				dcb->dccpd_type = DCCP_PKT_DATAACK;
			else
				dcb->dccpd_type = DCCP_PKT_DATA;

			err = dccp_transmit_skb(sk, skb);
			ccid_hc_tx_packet_sent(dp->dccps_hc_tx_ccid, sk, 0, len);
			if (err)
				DCCP_BUG("err=%d after ccid_hc_tx_packet_sent",
					 err);
		} else {
			dccp_pr_debug("packet discarded due to err=%d\n", err);
			kfree_skb(skb);
		}
	}
}

int dccp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
{
	if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk) != 0)
		return -EHOSTUNREACH; /* Routing failure or similar. */

	return dccp_transmit_skb(sk, (skb_cloned(skb) ?
				      pskb_copy(skb, GFP_ATOMIC):
				      skb_clone(skb, GFP_ATOMIC)));
}

struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
				   struct request_sock *req)
{
	struct dccp_hdr *dh;
	struct dccp_request_sock *dreq;
	const u32 dccp_header_size = sizeof(struct dccp_hdr) +
				     sizeof(struct dccp_hdr_ext) +
				     sizeof(struct dccp_hdr_response);
	struct sk_buff *skb = sock_wmalloc(sk, sk->sk_prot->max_header, 1,
					   GFP_ATOMIC);