ccid3.c

linux 内核源代码

	/* prepare to send now (add options etc.) */
	dp->dccps_hc_tx_insert_options = 1;
	DCCP_SKB_CB(skb)->dccpd_ccval = hctx->ccid3hctx_last_win_count;
	hctx->ccid3hctx_idle = 0;

	/* set the nominal send time for the next following packet */
	hctx->ccid3hctx_t_nom = ktime_add_us(hctx->ccid3hctx_t_nom,
					     hctx->ccid3hctx_t_ipi);
	return 0;
}

static void ccid3_hc_tx_packet_sent(struct sock *sk, int more,
				    unsigned int len)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	struct dccp_tx_hist_entry *packet;

	ccid3_hc_tx_update_s(hctx, len);

	packet = dccp_tx_hist_entry_new(ccid3_tx_hist, GFP_ATOMIC);
	if (unlikely(packet == NULL)) {
		DCCP_CRIT("packet history - out of memory!");
		return;
	}
	dccp_tx_hist_add_entry(&hctx->ccid3hctx_hist, packet);

	packet->dccphtx_tstamp = ktime_get_real();
	packet->dccphtx_seqno  = dccp_sk(sk)->dccps_gss;
	packet->dccphtx_rtt    = hctx->ccid3hctx_rtt;
	packet->dccphtx_sent   = 1;
}

static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	struct ccid3_options_received *opt_recv;
	struct dccp_tx_hist_entry *packet;
	ktime_t now;
	unsigned long t_nfb;
	u32 pinv, r_sample;

	/* we are only interested in ACKs */
	if (!(DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_ACK ||
	      DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK))
		return;

	opt_recv = &hctx->ccid3hctx_options_received;

	switch (hctx->ccid3hctx_state) {
	case TFRC_SSTATE_NO_FBACK:
	case TFRC_SSTATE_FBACK:
		/* get packet from history to look up t_recvdata */
		packet = dccp_tx_hist_find_entry(&hctx->ccid3hctx_hist,
					      DCCP_SKB_CB(skb)->dccpd_ack_seq);
		if (unlikely(packet == NULL)) {
			DCCP_WARN("%s(%p), seqno %llu(%s) doesn't exist "
				  "in history!\n",  dccp_role(sk), sk,
			    (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq,
				dccp_packet_name(DCCP_SKB_CB(skb)->dccpd_type));
			return;
		}

		/* Update receive rate in units of 64 * bytes/second */
		hctx->ccid3hctx_x_recv = opt_recv->ccid3or_receive_rate;
		hctx->ccid3hctx_x_recv <<= 6;

		/* Update loss event rate */
		pinv = opt_recv->ccid3or_loss_event_rate;
		if (pinv == ~0U || pinv == 0)	       /* see RFC 4342, 8.5   */
			hctx->ccid3hctx_p = 0;
		else				       /* can not exceed 100% */
			hctx->ccid3hctx_p = 1000000 / pinv;

		now = ktime_get_real();
		/*
		 * Calculate new round trip sample as per [RFC 3448, 4.3] by
		 *	R_sample  =  (now - t_recvdata) - t_elapsed
		 */
		r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, packet->dccphtx_tstamp));

		/*
		 * Update RTT estimate by
		 * If (No feedback recv)
		 *    R = R_sample;
		 * Else
		 *    R = q * R + (1 - q) * R_sample;
		 *
		 * q is a constant, RFC 3448 recomments 0.9
		 */
		if (hctx->ccid3hctx_state == TFRC_SSTATE_NO_FBACK) {
			/*
			 * Larger Initial Windows [RFC 4342, sec. 5]
			 */
			hctx->ccid3hctx_rtt  = r_sample;
			hctx->ccid3hctx_x    = rfc3390_initial_rate(sk);
			hctx->ccid3hctx_t_ld = now;

			ccid3_update_send_interval(hctx);

			ccid3_pr_debug("%s(%p), s=%u, MSS=%u, "
				       "R_sample=%uus, X=%u\n", dccp_role(sk),
				       sk, hctx->ccid3hctx_s,
				       dccp_sk(sk)->dccps_mss_cache, r_sample,
				       (unsigned)(hctx->ccid3hctx_x >> 6));

			ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);
		} else {
			hctx->ccid3hctx_rtt = (9 * hctx->ccid3hctx_rtt +
						   r_sample) / 10;

			/* Update sending rate (step 4 of [RFC 3448, 4.3]) */
			if (hctx->ccid3hctx_p > 0)
				hctx->ccid3hctx_x_calc =
					tfrc_calc_x(hctx->ccid3hctx_s,
						    hctx->ccid3hctx_rtt,
						    hctx->ccid3hctx_p);
			ccid3_hc_tx_update_x(sk, &now);

			ccid3_pr_debug("%s(%p), RTT=%uus (sample=%uus), s=%u, "
				       "p=%u, X_calc=%u, X_recv=%u, X=%u\n",
				       dccp_role(sk),
				       sk, hctx->ccid3hctx_rtt, r_sample,
				       hctx->ccid3hctx_s, hctx->ccid3hctx_p,
				       hctx->ccid3hctx_x_calc,
				       (unsigned)(hctx->ccid3hctx_x_recv >> 6),
				       (unsigned)(hctx->ccid3hctx_x >> 6));
		}

		/* unschedule no feedback timer */
		sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer);

		/* remove all packets older than the one acked from history */
		dccp_tx_hist_purge_older(ccid3_tx_hist,
					 &hctx->ccid3hctx_hist, packet);
		/*
		 * As we have calculated new ipi, delta, t_nom it is possible
		 * that we now can send a packet, so wake up dccp_wait_for_ccid
		 */
		sk->sk_write_space(sk);

		/*
		 * Update timeout interval for the nofeedback timer.
		 * We use a configuration option to increase the lower bound.
		 * This can help avoid triggering the nofeedback timer too
		 * often ('spinning') on LANs with small RTTs.
		 */
		hctx->ccid3hctx_t_rto = max_t(u32, 4 * hctx->ccid3hctx_rtt,
						   CONFIG_IP_DCCP_CCID3_RTO *
						   (USEC_PER_SEC/1000));
		/*
		 * Schedule no feedback timer to expire in
		 * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)
		 */
		t_nfb = max(hctx->ccid3hctx_t_rto, 2 * hctx->ccid3hctx_t_ipi);

		ccid3_pr_debug("%s(%p), Scheduled no feedback timer to "
			       "expire in %lu jiffies (%luus)\n",
			       dccp_role(sk),
			       sk, usecs_to_jiffies(t_nfb), t_nfb);

		sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer,
				   jiffies + usecs_to_jiffies(t_nfb));

		/* set idle flag */
		hctx->ccid3hctx_idle = 1;
		break;
	case TFRC_SSTATE_NO_SENT:	/* fall through */
	case TFRC_SSTATE_TERM:		/* ignore feedback when closing */
		break;
	}
}

static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option,
				     unsigned char len, u16 idx,
				     unsigned char *value)
{
	int rc = 0;
	const struct dccp_sock *dp = dccp_sk(sk);
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);
	struct ccid3_options_received *opt_recv;
	__be32 opt_val;

	opt_recv = &hctx->ccid3hctx_options_received;

	if (opt_recv->ccid3or_seqno != dp->dccps_gsr) {
		opt_recv->ccid3or_seqno		     = dp->dccps_gsr;
		opt_recv->ccid3or_loss_event_rate    = ~0;
		opt_recv->ccid3or_loss_intervals_idx = 0;
		opt_recv->ccid3or_loss_intervals_len = 0;
		opt_recv->ccid3or_receive_rate	     = 0;
	}

	switch (option) {
	case TFRC_OPT_LOSS_EVENT_RATE:
		if (unlikely(len != 4)) {
			DCCP_WARN("%s(%p), invalid len %d "
				  "for TFRC_OPT_LOSS_EVENT_RATE\n",
				  dccp_role(sk), sk, len);
			rc = -EINVAL;
		} else {
			opt_val = get_unaligned((__be32 *)value);
			opt_recv->ccid3or_loss_event_rate = ntohl(opt_val);
			ccid3_pr_debug("%s(%p), LOSS_EVENT_RATE=%u\n",
				       dccp_role(sk), sk,
				       opt_recv->ccid3or_loss_event_rate);
		}
		break;
	case TFRC_OPT_LOSS_INTERVALS:
		opt_recv->ccid3or_loss_intervals_idx = idx;
		opt_recv->ccid3or_loss_intervals_len = len;
		ccid3_pr_debug("%s(%p), LOSS_INTERVALS=(%u, %u)\n",
			       dccp_role(sk), sk,
			       opt_recv->ccid3or_loss_intervals_idx,
			       opt_recv->ccid3or_loss_intervals_len);
		break;
	case TFRC_OPT_RECEIVE_RATE:
		if (unlikely(len != 4)) {
			DCCP_WARN("%s(%p), invalid len %d "
				  "for TFRC_OPT_RECEIVE_RATE\n",
				  dccp_role(sk), sk, len);
			rc = -EINVAL;
		} else {
			opt_val = get_unaligned((__be32 *)value);
			opt_recv->ccid3or_receive_rate = ntohl(opt_val);
			ccid3_pr_debug("%s(%p), RECEIVE_RATE=%u\n",
				       dccp_role(sk), sk,
				       opt_recv->ccid3or_receive_rate);
		}
		break;
	}

	return rc;
}

static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk)
{
	struct ccid3_hc_tx_sock *hctx = ccid_priv(ccid);

	hctx->ccid3hctx_state = TFRC_SSTATE_NO_SENT;
	INIT_LIST_HEAD(&hctx->ccid3hctx_hist);

	hctx->ccid3hctx_no_feedback_timer.function =
				ccid3_hc_tx_no_feedback_timer;
	hctx->ccid3hctx_no_feedback_timer.data     = (unsigned long)sk;
	init_timer(&hctx->ccid3hctx_no_feedback_timer);

	return 0;
}

static void ccid3_hc_tx_exit(struct sock *sk)
{
	struct ccid3_hc_tx_sock *hctx = ccid3_hc_tx_sk(sk);

	ccid3_hc_tx_set_state(sk, TFRC_SSTATE_TERM);
	sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer);

	/* Empty packet history */
	dccp_tx_hist_purge(ccid3_tx_hist, &hctx->ccid3hctx_hist);
}

static void ccid3_hc_tx_get_info(struct sock *sk, struct tcp_info *info)
{
	struct ccid3_hc_tx_sock *hctx;

	/* Listen socks doesn't have a private CCID block */
	if (sk->sk_state == DCCP_LISTEN)
		return;

	hctx = ccid3_hc_tx_sk(sk);
	info->tcpi_rto = hctx->ccid3hctx_t_rto;
	info->tcpi_rtt = hctx->ccid3hctx_rtt;
}

static int ccid3_hc_tx_getsockopt(struct sock *sk, const int optname, int len,
				  u32 __user *optval, int __user *optlen)
{
	const struct ccid3_hc_tx_sock *hctx;
	const void *val;

	/* Listen socks doesn't have a private CCID block */
	if (sk->sk_state == DCCP_LISTEN)
		return -EINVAL;

	hctx = ccid3_hc_tx_sk(sk);
	switch (optname) {
	case DCCP_SOCKOPT_CCID_TX_INFO:
		if (len < sizeof(hctx->ccid3hctx_tfrc))
			return -EINVAL;
		len = sizeof(hctx->ccid3hctx_tfrc);
		val = &hctx->ccid3hctx_tfrc;
		break;
	default:
		return -ENOPROTOOPT;
	}

	if (put_user(len, optlen) || copy_to_user(optval, val, len))
		return -EFAULT;

	return 0;
}

/*
 *	Receiver Half-Connection Routines
 */
#ifdef CONFIG_IP_DCCP_CCID3_DEBUG
static const char *ccid3_rx_state_name(enum ccid3_hc_rx_states state)
{
	static char *ccid3_rx_state_names[] = {
	[TFRC_RSTATE_NO_DATA] = "NO_DATA",
	[TFRC_RSTATE_DATA]    = "DATA",
	[TFRC_RSTATE_TERM]    = "TERM",
	};

	return ccid3_rx_state_names[state];
}
#endif

static void ccid3_hc_rx_set_state(struct sock *sk,
				  enum ccid3_hc_rx_states state)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	enum ccid3_hc_rx_states oldstate = hcrx->ccid3hcrx_state;

	ccid3_pr_debug("%s(%p) %-8.8s -> %s\n",
		       dccp_role(sk), sk, ccid3_rx_state_name(oldstate),
		       ccid3_rx_state_name(state));
	WARN_ON(state == oldstate);
	hcrx->ccid3hcrx_state = state;
}

static inline void ccid3_hc_rx_update_s(struct ccid3_hc_rx_sock *hcrx, int len)
{
	if (unlikely(len == 0))	/* don't update on empty packets (e.g. ACKs) */
		ccid3_pr_debug("Packet payload length is 0 - not updating\n");
	else
		hcrx->ccid3hcrx_s = hcrx->ccid3hcrx_s == 0 ? len :
				    (9 * hcrx->ccid3hcrx_s + len) / 10;
}

static void ccid3_hc_rx_send_feedback(struct sock *sk)
{
	struct ccid3_hc_rx_sock *hcrx = ccid3_hc_rx_sk(sk);
	struct dccp_sock *dp = dccp_sk(sk);
	struct dccp_rx_hist_entry *packet;
	ktime_t now;
	suseconds_t delta;

	ccid3_pr_debug("%s(%p) - entry \n", dccp_role(sk), sk);

	now = ktime_get_real();

	switch (hcrx->ccid3hcrx_state) {
	case TFRC_RSTATE_NO_DATA:
		hcrx->ccid3hcrx_x_recv = 0;
		break;
	case TFRC_RSTATE_DATA:
		delta = ktime_us_delta(now,
				       hcrx->ccid3hcrx_tstamp_last_feedback);
		DCCP_BUG_ON(delta < 0);
		hcrx->ccid3hcrx_x_recv =
			scaled_div32(hcrx->ccid3hcrx_bytes_recv, delta);
		break;
	case TFRC_RSTATE_TERM:
		DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk);
		return;
	}