This implements the algorithm to update the allowed sending rate X upon
receiving feedback packets, as described in draft rfc3448bis, 4.2/4.3.
The patch further removes two irrelevant states in TX feedback handling:
* the NO_SENT state is only triggered in bidirectional mode,
costing unnecessary processing.
* the TERM (terminating) state is irrelevant.
Signed-off-by: Gerrit Renker <gerrit@xxxxxxxxxxxxxx>
Signed-off-by: Ian McDonald <ian.mcdonald@xxxxxxxxxxx>
---
net/dccp/ccids/ccid3.c | 171 ++++++++++++++++++++++++------------------------
1 files changed, 86 insertions(+), 85 deletions(-)
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 18ace1c..c631c3b 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -405,110 +405,111 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
DCCP_SKB_CB(skb)->dccpd_type == DCCP_PKT_DATAACK))
return;
+ /* ... and only in the established state */
+ switch (hctx->ccid3hctx_state) {
+ case TFRC_SSTATE_NO_FBACK: /* fall through */
+ case TFRC_SSTATE_FBACK: break;
+ default: return;
+ }
+
+ /* estimate RTT from history if ACK number is valid */
+ if (! tfrc_tx_hist_when(&t_send, &hctx->ccid3hctx_hist,
+ DCCP_SKB_CB(skb)->dccpd_ack_seq)) {
+ DCCP_WARN("%s(%p): %s with bogus ACK-%llu\n", dccp_role(sk), sk,
+ dccp_packet_name(DCCP_SKB_CB(skb)->dccpd_type),
+ (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq);
+ return;
+ }
+
opt_recv = &hctx->ccid3hctx_options_received;
- switch (hctx->ccid3hctx_state) {
- case TFRC_SSTATE_NO_FBACK:
- case TFRC_SSTATE_FBACK:
- /* estimate RTT from history if ACK number is valid */
- if (! tfrc_tx_hist_when(&t_send, &hctx->ccid3hctx_hist,
- DCCP_SKB_CB(skb)->dccpd_ack_seq)) {
- DCCP_WARN("%s(%p): %s with bogus ACK-%llu\n", dccp_role(sk), sk,
- dccp_packet_name(DCCP_SKB_CB(skb)->dccpd_type),
- (unsigned long long)DCCP_SKB_CB(skb)->dccpd_ack_seq);
- 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 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 (which is scaled by 1e6) */
+ 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 = scaled_div(1, pinv);
- /* 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;
+ /*
+ * Calculate new RTT sample and update moving average
+ */
+ now = ktime_get_real();
+ r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, t_send));
+ hctx->ccid3hctx_rtt = tfrc_ewma(hctx->ccid3hctx_rtt, r_sample, 9);
- now = ktime_get_real();
- /*
- * Calculate new RTT sample and update moving average
- */
- r_sample = dccp_sample_rtt(sk, ktime_us_delta(now, t_send));
- hctx->ccid3hctx_rtt = tfrc_ewma(hctx->ccid3hctx_rtt, r_sample, 9);
+ /*
+ * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3
+ */
+ if (hctx->ccid3hctx_state == TFRC_SSTATE_NO_FBACK) {
+
+ ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);
- if (hctx->ccid3hctx_state == TFRC_SSTATE_NO_FBACK) {
+ if (hctx->ccid3hctx_t_rto == 0) {
/*
- * Larger Initial Windows [RFC 4342, sec. 5]
+ * Initial feedback packet: Larger Initial Windows (4.2)
*/
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));
+ goto done_computing_x;
- ccid3_hc_tx_set_state(sk, TFRC_SSTATE_FBACK);
- } else {
-
- /* 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));
+ } else if (hctx->ccid3hctx_p == 0) {
+ /*
+ * First feedback after nofeedback timer expiry (4.3)
+ */
+ goto done_computing_x;
}
+ }
+ /* perform step (4) of draft rfc3448bis, section 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);
+
+done_computing_x:
+ 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);
- /* unschedule no feedback timer */
- sk_stop_timer(sk, &hctx->ccid3hctx_no_feedback_timer);
-
- /*
- * 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);
+ /*
+ * 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);
+ /*
+ * 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));
- sk_reset_timer(sk, &hctx->ccid3hctx_no_feedback_timer,
- jiffies + usecs_to_jiffies(t_nfb));
- break;
- case TFRC_SSTATE_NO_SENT: /* fall through */
- case TFRC_SSTATE_TERM: /* ignore feedback when closing */
- break;
- }
+ ccid3_pr_debug("Scheduled no feedback timer to expire in %lu jiffies"
+ "(%luus)\n", usecs_to_jiffies(t_nfb), t_nfb);
}
static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option,
--
1.5.2.2.238.g7cbf2f2-dirty
-
To unsubscribe from this list: send the line "unsubscribe dccp" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
