1 files changed, 508 insertions, 503 deletions

diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index d4f9e2d3345..f053198e730 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -1,6 +1,4 @@
 /*
- *  net/dccp/ccids/ccid2.c
- *
  *  Copyright (c) 2005, 2006 Andrea Bittau <a.bittau@cs.ucl.ac.uk>
  *
  *  Changes to meet Linux coding standards, and DCCP infrastructure fixes.
@@ -23,254 +21,290 @@
  */
 
 /*
- * This implementation should follow: draft-ietf-dccp-ccid2-10.txt
- *
- * BUGS:
- * - sequence number wrapping
- * - jiffies wrapping
+ * This implementation should follow RFC 4341
  */
-
-#include <linux/config.h>
-#include "../ccid.h"
-#include "../dccp.h"
+#include <linux/slab.h>
+#include "../feat.h"
 #include "ccid2.h"
 
-static int ccid2_debug;
 
-#undef CCID2_DEBUG
-#ifdef CCID2_DEBUG
-#define ccid2_pr_debug(format, a...) \
-        do { if (ccid2_debug) \
-                printk(KERN_DEBUG "%s: " format, __FUNCTION__, ##a); \
-        } while (0)
+#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
+static bool ccid2_debug;
+#define ccid2_pr_debug(format, a...)	DCCP_PR_DEBUG(ccid2_debug, format, ##a)
 #else
 #define ccid2_pr_debug(format, a...)
 #endif
 
-static const int ccid2_seq_len = 128;
-
-#ifdef CCID2_DEBUG
-static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hctx)
+static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc)
 {
-	int len = 0;
-	int pipe = 0;
-	struct ccid2_seq *seqp = hctx->ccid2hctx_seqh;
-
-	/* there is data in the chain */
-	if (seqp != hctx->ccid2hctx_seqt) {
-		seqp = seqp->ccid2s_prev;
-		len++;
-		if (!seqp->ccid2s_acked)
-			pipe++;
-
-		while (seqp != hctx->ccid2hctx_seqt) {
-			struct ccid2_seq *prev = seqp->ccid2s_prev;
+	struct ccid2_seq *seqp;
+	int i;
 
-			len++;
-			if (!prev->ccid2s_acked)
-				pipe++;
+	/* check if we have space to preserve the pointer to the buffer */
+	if (hc->tx_seqbufc >= (sizeof(hc->tx_seqbuf) /
+			       sizeof(struct ccid2_seq *)))
+		return -ENOMEM;
 
-			/* packets are sent sequentially */
-			BUG_ON(seqp->ccid2s_seq <= prev->ccid2s_seq);
-			BUG_ON(seqp->ccid2s_sent < prev->ccid2s_sent);
-			BUG_ON(len > ccid2_seq_len);
+	/* allocate buffer and initialize linked list */
+	seqp = kmalloc(CCID2_SEQBUF_LEN * sizeof(struct ccid2_seq), gfp_any());
+	if (seqp == NULL)
+		return -ENOMEM;
 
-			seqp = prev;
-		}
+	for (i = 0; i < (CCID2_SEQBUF_LEN - 1); i++) {
+		seqp[i].ccid2s_next = &seqp[i + 1];
+		seqp[i + 1].ccid2s_prev = &seqp[i];
+	}
+	seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = seqp;
+	seqp->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
+
+	/* This is the first allocation.  Initiate the head and tail.  */
+	if (hc->tx_seqbufc == 0)
+		hc->tx_seqh = hc->tx_seqt = seqp;
+	else {
+		/* link the existing list with the one we just created */
+		hc->tx_seqh->ccid2s_next = seqp;
+		seqp->ccid2s_prev = hc->tx_seqh;
+
+		hc->tx_seqt->ccid2s_prev = &seqp[CCID2_SEQBUF_LEN - 1];
+		seqp[CCID2_SEQBUF_LEN - 1].ccid2s_next = hc->tx_seqt;
 	}
 
-	BUG_ON(pipe != hctx->ccid2hctx_pipe);
-	ccid2_pr_debug("len of chain=%d\n", len);
-
-	do {
-		seqp = seqp->ccid2s_prev;
-		len++;
-		BUG_ON(len > ccid2_seq_len);
-	} while (seqp != hctx->ccid2hctx_seqh);
+	/* store the original pointer to the buffer so we can free it */
+	hc->tx_seqbuf[hc->tx_seqbufc] = seqp;
+	hc->tx_seqbufc++;
 
-	BUG_ON(len != ccid2_seq_len);
-	ccid2_pr_debug("total len=%d\n", len);
+	return 0;
 }
-#else
-#define ccid2_hc_tx_check_sanity(hctx) do {} while (0)
-#endif
 
-static int ccid2_hc_tx_send_packet(struct sock *sk,
-				   struct sk_buff *skb, int len)
+static int ccid2_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 {
-	struct ccid2_hc_tx_sock *hctx;
-
-	switch (DCCP_SKB_CB(skb)->dccpd_type) {
-	case 0: /* XXX data packets from userland come through like this */
-	case DCCP_PKT_DATA:
-	case DCCP_PKT_DATAACK:
-		break;
-	/* No congestion control on other packets */
-	default:
-		return 0;
-	}
-
-        hctx = ccid2_hc_tx_sk(sk);
-
-	ccid2_pr_debug("pipe=%d cwnd=%d\n", hctx->ccid2hctx_pipe,
-		       hctx->ccid2hctx_cwnd);
-
-	if (hctx->ccid2hctx_pipe < hctx->ccid2hctx_cwnd) {
-		/* OK we can send... make sure previous packet was sent off */
-		if (!hctx->ccid2hctx_sendwait) {
-			hctx->ccid2hctx_sendwait = 1;
-			return 0;
-		}
-	}
-
-	return 100; /* XXX */
+	if (ccid2_cwnd_network_limited(ccid2_hc_tx_sk(sk)))
+		return CCID_PACKET_WILL_DEQUEUE_LATER;
+	return CCID_PACKET_SEND_AT_ONCE;
 }
 
-static void ccid2_change_l_ack_ratio(struct sock *sk, int val)
+static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
+	u32 max_ratio = DIV_ROUND_UP(ccid2_hc_tx_sk(sk)->tx_cwnd, 2);
+
 	/*
-	 * XXX I don't really agree with val != 2.  If cwnd is 1, ack ratio
-	 * should be 1... it shouldn't be allowed to become 2.
-	 * -sorbo.
+	 * Ensure that Ack Ratio does not exceed ceil(cwnd/2), which is (2) from
+	 * RFC 4341, 6.1.2. We ignore the statement that Ack Ratio 2 is always
+	 * acceptable since this causes starvation/deadlock whenever cwnd < 2.
+	 * The same problem arises when Ack Ratio is 0 (ie. Ack Ratio disabled).
 	 */
-	if (val != 2) {
-		const struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
-		int max = hctx->ccid2hctx_cwnd / 2;
-
-		/* round up */
-		if (hctx->ccid2hctx_cwnd & 1)
-			max++;
-
-		if (val > max)
-			val = max;
+	if (val == 0 || val > max_ratio) {
+		DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio);
+		val = max_ratio;
 	}
-
-	ccid2_pr_debug("changing local ack ratio to %d\n", val);
-	WARN_ON(val <= 0);
-	dp->dccps_l_ack_ratio = val;
+	dccp_feat_signal_nn_change(sk, DCCPF_ACK_RATIO,
+				   min_t(u32, val, DCCPF_ACK_RATIO_MAX));
 }
 
-static void ccid2_change_cwnd(struct sock *sk, int val)
+static void ccid2_check_l_ack_ratio(struct sock *sk)
 {
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
-
-	if (val == 0)
-		val = 1;
-
-	/* XXX do we need to change ack ratio? */
-	ccid2_pr_debug("change cwnd to %d\n", val);
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 
-	BUG_ON(val < 1);
-	hctx->ccid2hctx_cwnd = val;
+	/*
+	 * After a loss, idle period, application limited period, or RTO we
+	 * need to check that the ack ratio is still less than the congestion
+	 * window. Otherwise, we will send an entire congestion window of
+	 * packets and got no response because we haven't sent ack ratio
+	 * packets yet.
+	 * If the ack ratio does need to be reduced, we reduce it to half of
+	 * the congestion window (or 1 if that's zero) instead of to the
+	 * congestion window. This prevents problems if one ack is lost.
+	 */
+	if (dccp_feat_nn_get(sk, DCCPF_ACK_RATIO) > hc->tx_cwnd)
+		ccid2_change_l_ack_ratio(sk, hc->tx_cwnd/2 ? : 1U);
 }
 
-static void ccid2_start_rto_timer(struct sock *sk);
+static void ccid2_change_l_seq_window(struct sock *sk, u64 val)
+{
+	dccp_feat_signal_nn_change(sk, DCCPF_SEQUENCE_WINDOW,
+				   clamp_val(val, DCCPF_SEQ_WMIN,
+						  DCCPF_SEQ_WMAX));
+}
 
 static void ccid2_hc_tx_rto_expire(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
-	long s;
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
-		sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer,
-			       jiffies + HZ / 5);
+		sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + HZ / 5);
 		goto out;
 	}
 
 	ccid2_pr_debug("RTO_EXPIRE\n");
 
-	ccid2_hc_tx_check_sanity(hctx);
-
 	/* back-off timer */
-	hctx->ccid2hctx_rto <<= 1;
-
-	s = hctx->ccid2hctx_rto / HZ;
-	if (s > 60)
-		hctx->ccid2hctx_rto = 60 * HZ;
-
-	ccid2_start_rto_timer(sk);
+	hc->tx_rto <<= 1;
+	if (hc->tx_rto > DCCP_RTO_MAX)
+		hc->tx_rto = DCCP_RTO_MAX;
 
 	/* adjust pipe, cwnd etc */
-	hctx->ccid2hctx_pipe = 0;
-	hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd >> 1;
-	if (hctx->ccid2hctx_ssthresh < 2)
-		hctx->ccid2hctx_ssthresh = 2;
-	ccid2_change_cwnd(sk, 1);
+	hc->tx_ssthresh = hc->tx_cwnd / 2;
+	if (hc->tx_ssthresh < 2)
+		hc->tx_ssthresh = 2;
+	hc->tx_cwnd	= 1;
+	hc->tx_pipe	= 0;
 
 	/* clear state about stuff we sent */
-	hctx->ccid2hctx_seqt	= hctx->ccid2hctx_seqh;
-	hctx->ccid2hctx_ssacks	= 0;
-	hctx->ccid2hctx_acks	= 0;
-	hctx->ccid2hctx_sent	= 0;
+	hc->tx_seqt = hc->tx_seqh;
+	hc->tx_packets_acked = 0;
 
 	/* clear ack ratio state. */
-	hctx->ccid2hctx_arsent	 = 0;
-	hctx->ccid2hctx_ackloss  = 0;
-	hctx->ccid2hctx_rpseq	 = 0;
-	hctx->ccid2hctx_rpdupack = -1;
+	hc->tx_rpseq    = 0;
+	hc->tx_rpdupack = -1;
 	ccid2_change_l_ack_ratio(sk, 1);
-	ccid2_hc_tx_check_sanity(hctx);
+
+	/* if we were blocked before, we may now send cwnd=1 packet */
+	if (sender_was_blocked)
+		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+	/* restart backed-off timer */
+	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
 }
 
-static void ccid2_start_rto_timer(struct sock *sk)
+/*
+ *	Congestion window validation (RFC 2861).
+ */
+static bool ccid2_do_cwv = true;
+module_param(ccid2_do_cwv, bool, 0644);
+MODULE_PARM_DESC(ccid2_do_cwv, "Perform RFC2861 Congestion Window Validation");
+
+/**
+ * ccid2_update_used_window  -  Track how much of cwnd is actually used
+ * This is done in addition to CWV. The sender needs to have an idea of how many
+ * packets may be in flight, to set the local Sequence Window value accordingly
+ * (RFC 4340, 7.5.2). The CWV mechanism is exploited to keep track of the
+ * maximum-used window. We use an EWMA low-pass filter to filter out noise.
+ */
+static void ccid2_update_used_window(struct ccid2_hc_tx_sock *hc, u32 new_wnd)
 {
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
+	hc->tx_expected_wnd = (3 * hc->tx_expected_wnd + new_wnd) / 4;
+}
 
-	ccid2_pr_debug("setting RTO timeout=%ld\n", hctx->ccid2hctx_rto);
+/* This borrows the code of tcp_cwnd_application_limited() */
+static void ccid2_cwnd_application_limited(struct sock *sk, const u32 now)
+{
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	/* don't reduce cwnd below the initial window (IW) */
+	u32 init_win = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache),
+	    win_used = max(hc->tx_cwnd_used, init_win);
+
+	if (win_used < hc->tx_cwnd) {
+		hc->tx_ssthresh = max(hc->tx_ssthresh,
+				     (hc->tx_cwnd >> 1) + (hc->tx_cwnd >> 2));
+		hc->tx_cwnd = (hc->tx_cwnd + win_used) >> 1;
+	}
+	hc->tx_cwnd_used  = 0;
+	hc->tx_cwnd_stamp = now;
 
-	BUG_ON(timer_pending(&hctx->ccid2hctx_rtotimer));
-	sk_reset_timer(sk, &hctx->ccid2hctx_rtotimer,
-		       jiffies + hctx->ccid2hctx_rto);
+	ccid2_check_l_ack_ratio(sk);
 }
 
-static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len)
+/* This borrows the code of tcp_cwnd_restart() */
+static void ccid2_cwnd_restart(struct sock *sk, const u32 now)
 {
-	struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
-	u64 seq;
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	u32 cwnd = hc->tx_cwnd, restart_cwnd,
+	    iwnd = rfc3390_bytes_to_packets(dccp_sk(sk)->dccps_mss_cache);
 
-	ccid2_hc_tx_check_sanity(hctx);
+	hc->tx_ssthresh = max(hc->tx_ssthresh, (cwnd >> 1) + (cwnd >> 2));
 
-	BUG_ON(!hctx->ccid2hctx_sendwait);
-	hctx->ccid2hctx_sendwait = 0;
-	hctx->ccid2hctx_pipe++;
-	BUG_ON(hctx->ccid2hctx_pipe < 0);
+	/* don't reduce cwnd below the initial window (IW) */
+	restart_cwnd = min(cwnd, iwnd);
+	cwnd >>= (now - hc->tx_lsndtime) / hc->tx_rto;
+	hc->tx_cwnd = max(cwnd, restart_cwnd);
 
-	/* There is an issue.  What if another packet is sent between
-	 * packet_send() and packet_sent().  Then the sequence number would be
-	 * wrong.
-	 * -sorbo.
-	 */
-	seq = dp->dccps_gss;
+	hc->tx_cwnd_stamp = now;
+	hc->tx_cwnd_used  = 0;
 
-	hctx->ccid2hctx_seqh->ccid2s_seq   = seq;
-	hctx->ccid2hctx_seqh->ccid2s_acked = 0;
-	hctx->ccid2hctx_seqh->ccid2s_sent  = jiffies;
-	hctx->ccid2hctx_seqh = hctx->ccid2hctx_seqh->ccid2s_next;
+	ccid2_check_l_ack_ratio(sk);
+}
+
+static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len)
+{
+	struct dccp_sock *dp = dccp_sk(sk);
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	const u32 now = ccid2_time_stamp;
+	struct ccid2_seq *next;
+
+	/* slow-start after idle periods (RFC 2581, RFC 2861) */
+	if (ccid2_do_cwv && !hc->tx_pipe &&
+	    (s32)(now - hc->tx_lsndtime) >= hc->tx_rto)
+		ccid2_cwnd_restart(sk, now);
+
+	hc->tx_lsndtime = now;
+	hc->tx_pipe    += 1;
+
+	/* see whether cwnd was fully used (RFC 2861), update expected window */
+	if (ccid2_cwnd_network_limited(hc)) {
+		ccid2_update_used_window(hc, hc->tx_cwnd);
+		hc->tx_cwnd_used  = 0;
+		hc->tx_cwnd_stamp = now;
+	} else {
+		if (hc->tx_pipe > hc->tx_cwnd_used)
+			hc->tx_cwnd_used = hc->tx_pipe;
 
-	ccid2_pr_debug("cwnd=%d pipe=%d\n", hctx->ccid2hctx_cwnd,
-		       hctx->ccid2hctx_pipe);
+		ccid2_update_used_window(hc, hc->tx_cwnd_used);
 
-	if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt) {
-		/* XXX allocate more space */
-		WARN_ON(1);
+		if (ccid2_do_cwv && (s32)(now - hc->tx_cwnd_stamp) >= hc->tx_rto)
+			ccid2_cwnd_application_limited(sk, now);
 	}
 
-	hctx->ccid2hctx_sent++;
+	hc->tx_seqh->ccid2s_seq   = dp->dccps_gss;
+	hc->tx_seqh->ccid2s_acked = 0;
+	hc->tx_seqh->ccid2s_sent  = now;
+
+	next = hc->tx_seqh->ccid2s_next;
+	/* check if we need to alloc more space */
+	if (next == hc->tx_seqt) {
+		if (ccid2_hc_tx_alloc_seq(hc)) {
+			DCCP_CRIT("packet history - out of memory!");
+			/* FIXME: find a more graceful way to bail out */
+			return;
+		}
+		next = hc->tx_seqh->ccid2s_next;
+		BUG_ON(next == hc->tx_seqt);
+	}
+	hc->tx_seqh = next;
 
+	ccid2_pr_debug("cwnd=%d pipe=%d\n", hc->tx_cwnd, hc->tx_pipe);
+
+	/*
+	 * FIXME: The code below is broken and the variables have been removed
+	 * from the socket struct. The `ackloss' variable was always set to 0,
+	 * and with arsent there are several problems:
+	 *  (i) it doesn't just count the number of Acks, but all sent packets;
+	 *  (ii) it is expressed in # of packets, not # of windows, so the
+	 *  comparison below uses the wrong formula: Appendix A of RFC 4341
+	 *  comes up with the number K = cwnd / (R^2 - R) of consecutive windows
+	 *  of data with no lost or marked Ack packets. If arsent were the # of
+	 *  consecutive Acks received without loss, then Ack Ratio needs to be
+	 *  decreased by 1 when
+	 *	      arsent >=  K * cwnd / R  =  cwnd^2 / (R^3 - R^2)
+	 *  where cwnd / R is the number of Acks received per window of data
+	 *  (cf. RFC 4341, App. A). The problems are that
+	 *  - arsent counts other packets as well;
+	 *  - the comparison uses a formula different from RFC 4341;
+	 *  - computing a cubic/quadratic equation each time is too complicated.
+	 *  Hence a different algorithm is needed.
+	 */
+#if 0
 	/* Ack Ratio.  Need to maintain a concept of how many windows we sent */
-	hctx->ccid2hctx_arsent++;
+	hc->tx_arsent++;
 	/* We had an ack loss in this window... */
-	if (hctx->ccid2hctx_ackloss) {
-		if (hctx->ccid2hctx_arsent >= hctx->ccid2hctx_cwnd) {
-			hctx->ccid2hctx_arsent	= 0;
-			hctx->ccid2hctx_ackloss	= 0;
+	if (hc->tx_ackloss) {
+		if (hc->tx_arsent >= hc->tx_cwnd) {
+			hc->tx_arsent  = 0;
+			hc->tx_ackloss = 0;
 		}
 	} else {
 		/* No acks lost up to now... */
@@ -280,227 +314,203 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, int len)
 			int denom = dp->dccps_l_ack_ratio * dp->dccps_l_ack_ratio -
 				    dp->dccps_l_ack_ratio;
 
-			denom = hctx->ccid2hctx_cwnd * hctx->ccid2hctx_cwnd / denom;
+			denom = hc->tx_cwnd * hc->tx_cwnd / denom;
 
-			if (hctx->ccid2hctx_arsent >= denom) {
+			if (hc->tx_arsent >= denom) {
 				ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio - 1);
-				hctx->ccid2hctx_arsent = 0;
+				hc->tx_arsent = 0;
 			}
 		} else {
 			/* we can't increase ack ratio further [1] */
-			hctx->ccid2hctx_arsent = 0; /* or maybe set it to cwnd*/
+			hc->tx_arsent = 0; /* or maybe set it to cwnd*/
 		}
 	}
+#endif
 
-	/* setup RTO timer */
-	if (!timer_pending(&hctx->ccid2hctx_rtotimer))
-		ccid2_start_rto_timer(sk);
+	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 
-#ifdef CCID2_DEBUG
-	ccid2_pr_debug("pipe=%d\n", hctx->ccid2hctx_pipe);
-	ccid2_pr_debug("Sent: seq=%llu\n", seq);
+#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
 	do {
-		struct ccid2_seq *seqp = hctx->ccid2hctx_seqt;
+		struct ccid2_seq *seqp = hc->tx_seqt;
 
-		while (seqp != hctx->ccid2hctx_seqh) {
-			ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n",
-			       	       seqp->ccid2s_seq, seqp->ccid2s_acked,
-				       seqp->ccid2s_sent);
+		while (seqp != hc->tx_seqh) {
+			ccid2_pr_debug("out seq=%llu acked=%d time=%u\n",
+				       (unsigned long long)seqp->ccid2s_seq,
+				       seqp->ccid2s_acked, seqp->ccid2s_sent);
 			seqp = seqp->ccid2s_next;
 		}
 	} while (0);
 	ccid2_pr_debug("=========\n");
-	ccid2_hc_tx_check_sanity(hctx);
 #endif
 }
 
-/* XXX Lame code duplication!
- * returns -1 if none was found.
- * else returns the next offset to use in the function call.
+/**
+ * ccid2_rtt_estimator - Sample RTT and compute RTO using RFC2988 algorithm
+ * This code is almost identical with TCP's tcp_rtt_estimator(), since
+ * - it has a higher sampling frequency (recommended by RFC 1323),
+ * - the RTO does not collapse into RTT due to RTTVAR going towards zero,
+ * - it is simple (cf. more complex proposals such as Eifel timer or research
+ *   which suggests that the gain should be set according to window size),
+ * - in tests it was found to work well with CCID2 [gerrit].
  */
-static int ccid2_ackvector(struct sock *sk, struct sk_buff *skb, int offset,
-			   unsigned char **vec, unsigned char *veclen)
+static void ccid2_rtt_estimator(struct sock *sk, const long mrtt)
 {
-        const struct dccp_hdr *dh = dccp_hdr(skb);
-        unsigned char *options = (unsigned char *)dh + dccp_hdr_len(skb);
-        unsigned char *opt_ptr;
-        const unsigned char *opt_end = (unsigned char *)dh +
-                                        (dh->dccph_doff * 4);
-        unsigned char opt, len;
-        unsigned char *value;
-
-	BUG_ON(offset < 0);
-	options += offset;
-	opt_ptr = options;
-	if (opt_ptr >= opt_end)
-		return -1;
-
-	while (opt_ptr != opt_end) {
-                opt   = *opt_ptr++;
-                len   = 0;
-                value = NULL;
-
-                /* Check if this isn't a single byte option */
-                if (opt > DCCPO_MAX_RESERVED) {
-                        if (opt_ptr == opt_end)
-                                goto out_invalid_option;
-
-                        len = *opt_ptr++;
-                        if (len < 3)
-                                goto out_invalid_option;
-                        /*
-                         * Remove the type and len fields, leaving
-                         * just the value size
-                         */
-                        len     -= 2;
-                        value   = opt_ptr;
-                        opt_ptr += len;
-
-                        if (opt_ptr > opt_end)
-                                goto out_invalid_option;
-                }
-
-		switch (opt) {
-		case DCCPO_ACK_VECTOR_0:
-		case DCCPO_ACK_VECTOR_1:
-			*vec	= value;
-			*veclen = len;
-			return offset + (opt_ptr - options);
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	long m = mrtt ? : 1;
+
+	if (hc->tx_srtt == 0) {
+		/* First measurement m */
+		hc->tx_srtt = m << 3;
+		hc->tx_mdev = m << 1;
+
+		hc->tx_mdev_max = max(hc->tx_mdev, tcp_rto_min(sk));
+		hc->tx_rttvar   = hc->tx_mdev_max;
+
+		hc->tx_rtt_seq  = dccp_sk(sk)->dccps_gss;
+	} else {
+		/* Update scaled SRTT as SRTT += 1/8 * (m - SRTT) */
+		m -= (hc->tx_srtt >> 3);
+		hc->tx_srtt += m;
+
+		/* Similarly, update scaled mdev with regard to |m| */
+		if (m < 0) {
+			m = -m;
+			m -= (hc->tx_mdev >> 2);
+			/*
+			 * This neutralises RTO increase when RTT < SRTT - mdev
+			 * (see P. Sarolahti, A. Kuznetsov,"Congestion Control
+			 * in Linux TCP", USENIX 2002, pp. 49-62).
+			 */
+			if (m > 0)
+				m >>= 3;
+		} else {
+			m -= (hc->tx_mdev >> 2);
 		}
-	}
+		hc->tx_mdev += m;
 
-	return -1;
+		if (hc->tx_mdev > hc->tx_mdev_max) {
+			hc->tx_mdev_max = hc->tx_mdev;
+			if (hc->tx_mdev_max > hc->tx_rttvar)
+				hc->tx_rttvar = hc->tx_mdev_max;
+		}
 
-out_invalid_option:
-	BUG_ON(1); /* should never happen... options were previously parsed ! */
-	return -1;
-}
+		/*
+		 * Decay RTTVAR at most once per flight, exploiting that
+		 *  1) pipe <= cwnd <= Sequence_Window = W  (RFC 4340, 7.5.2)
+		 *  2) AWL = GSS-W+1 <= GAR <= GSS          (RFC 4340, 7.5.1)
+		 * GAR is a useful bound for FlightSize = pipe.
+		 * AWL is probably too low here, as it over-estimates pipe.
+		 */
+		if (after48(dccp_sk(sk)->dccps_gar, hc->tx_rtt_seq)) {
+			if (hc->tx_mdev_max < hc->tx_rttvar)
+				hc->tx_rttvar -= (hc->tx_rttvar -
+						  hc->tx_mdev_max) >> 2;
+			hc->tx_rtt_seq  = dccp_sk(sk)->dccps_gss;
+			hc->tx_mdev_max = tcp_rto_min(sk);
+		}
+	}
 
-static void ccid2_hc_tx_kill_rto_timer(struct sock *sk)
-{
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
+	/*
+	 * Set RTO from SRTT and RTTVAR
+	 * As in TCP, 4 * RTTVAR >= TCP_RTO_MIN, giving a minimum RTO of 200 ms.
+	 * This agrees with RFC 4341, 5:
+	 *	"Because DCCP does not retransmit data, DCCP does not require
+	 *	 TCP's recommended minimum timeout of one second".
+	 */
+	hc->tx_rto = (hc->tx_srtt >> 3) + hc->tx_rttvar;
 
-	sk_stop_timer(sk, &hctx->ccid2hctx_rtotimer);
-	ccid2_pr_debug("deleted RTO timer\n");
+	if (hc->tx_rto > DCCP_RTO_MAX)
+		hc->tx_rto = DCCP_RTO_MAX;
 }
 
-static inline void ccid2_new_ack(struct sock *sk,
-			         struct ccid2_seq *seqp,
-				 unsigned int *maxincr)
+static void ccid2_new_ack(struct sock *sk, struct ccid2_seq *seqp,
+			  unsigned int *maxincr)
 {
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
-
-	/* slow start */
-	if (hctx->ccid2hctx_cwnd < hctx->ccid2hctx_ssthresh) {
-		hctx->ccid2hctx_acks = 0;
-
-		/* We can increase cwnd at most maxincr [ack_ratio/2] */
-		if (*maxincr) {
-			/* increase every 2 acks */
-			hctx->ccid2hctx_ssacks++;
-			if (hctx->ccid2hctx_ssacks == 2) {
-				ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1);
-				hctx->ccid2hctx_ssacks = 0;
-				*maxincr = *maxincr - 1;
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	struct dccp_sock *dp = dccp_sk(sk);
+	int r_seq_used = hc->tx_cwnd / dp->dccps_l_ack_ratio;
+
+	if (hc->tx_cwnd < dp->dccps_l_seq_win &&
+	    r_seq_used < dp->dccps_r_seq_win) {
+		if (hc->tx_cwnd < hc->tx_ssthresh) {
+			if (*maxincr > 0 && ++hc->tx_packets_acked >= 2) {
+				hc->tx_cwnd += 1;
+				*maxincr    -= 1;
+				hc->tx_packets_acked = 0;
 			}
-		} else {
-			/* increased cwnd enough for this single ack */
-			hctx->ccid2hctx_ssacks = 0;
-		}
-	} else {
-		hctx->ccid2hctx_ssacks = 0;
-		hctx->ccid2hctx_acks++;
-
-		if (hctx->ccid2hctx_acks >= hctx->ccid2hctx_cwnd) {
-			ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd + 1);
-			hctx->ccid2hctx_acks = 0;
+		} else if (++hc->tx_packets_acked >= hc->tx_cwnd) {
+			hc->tx_cwnd += 1;
+			hc->tx_packets_acked = 0;
 		}
 	}
 
-	/* update RTO */
-	if (hctx->ccid2hctx_srtt == -1 ||
-	    (jiffies - hctx->ccid2hctx_lastrtt) >= hctx->ccid2hctx_srtt) {
-		unsigned long r = jiffies - seqp->ccid2s_sent;
-		int s;
-
-		/* first measurement */
-		if (hctx->ccid2hctx_srtt == -1) {
-			ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n",
-			       	       r, jiffies, seqp->ccid2s_seq);
-			hctx->ccid2hctx_srtt = r;
-			hctx->ccid2hctx_rttvar = r >> 1;
-		} else {
-			/* RTTVAR */
-			long tmp = hctx->ccid2hctx_srtt - r;
-			if (tmp < 0)
-				tmp *= -1;
-
-			tmp >>= 2;
-			hctx->ccid2hctx_rttvar *= 3;
-			hctx->ccid2hctx_rttvar >>= 2;
-			hctx->ccid2hctx_rttvar += tmp;
-
-			/* SRTT */
-			hctx->ccid2hctx_srtt *= 7;
-			hctx->ccid2hctx_srtt >>= 3;
-			tmp = r >> 3;
-			hctx->ccid2hctx_srtt += tmp;
-		}
-		s = hctx->ccid2hctx_rttvar << 2;
-		/* clock granularity is 1 when based on jiffies */
-		if (!s)
-			s = 1;
-		hctx->ccid2hctx_rto = hctx->ccid2hctx_srtt + s;
-
-		/* must be at least a second */
-		s = hctx->ccid2hctx_rto / HZ;
-		/* DCCP doesn't require this [but I like it cuz my code sux] */
-#if 1
-		if (s < 1)
-			hctx->ccid2hctx_rto = HZ;
-#endif
-		/* max 60 seconds */
-		if (s > 60)
-			hctx->ccid2hctx_rto = HZ * 60;
+	/*
+	 * Adjust the local sequence window and the ack ratio to allow about
+	 * 5 times the number of packets in the network (RFC 4340 7.5.2)
+	 */
+	if (r_seq_used * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_r_seq_win)
+		ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio * 2);
+	else if (r_seq_used * CCID2_WIN_CHANGE_FACTOR < dp->dccps_r_seq_win/2)
+		ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio / 2 ? : 1U);
+
+	if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR >= dp->dccps_l_seq_win)
+		ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win * 2);
+	else if (hc->tx_cwnd * CCID2_WIN_CHANGE_FACTOR < dp->dccps_l_seq_win/2)
+		ccid2_change_l_seq_window(sk, dp->dccps_l_seq_win / 2);
 
-		hctx->ccid2hctx_lastrtt = jiffies;
+	/*
+	 * FIXME: RTT is sampled several times per acknowledgment (for each
+	 * entry in the Ack Vector), instead of once per Ack (as in TCP SACK).
+	 * This causes the RTT to be over-estimated, since the older entries
+	 * in the Ack Vector have earlier sending times.
+	 * The cleanest solution is to not use the ccid2s_sent field at all
+	 * and instead use DCCP timestamps: requires changes in other places.
+	 */
+	ccid2_rtt_estimator(sk, ccid2_time_stamp - seqp->ccid2s_sent);
+}
 
-		ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n",
-		       	       hctx->ccid2hctx_srtt, hctx->ccid2hctx_rttvar,
-		       	       hctx->ccid2hctx_rto, HZ, r);
-		hctx->ccid2hctx_sent = 0;
+static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp)
+{
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+
+	if ((s32)(seqp->ccid2s_sent - hc->tx_last_cong) < 0) {
+		ccid2_pr_debug("Multiple losses in an RTT---treating as one\n");
+		return;
 	}
 
-	/* we got a new ack, so re-start RTO timer */
-	ccid2_hc_tx_kill_rto_timer(sk);
-	ccid2_start_rto_timer(sk);
+	hc->tx_last_cong = ccid2_time_stamp;
+
+	hc->tx_cwnd      = hc->tx_cwnd / 2 ? : 1U;
+	hc->tx_ssthresh  = max(hc->tx_cwnd, 2U);
+
+	ccid2_check_l_ack_ratio(sk);
 }
 
-static void ccid2_hc_tx_dec_pipe(struct sock *sk)
+static int ccid2_hc_tx_parse_options(struct sock *sk, u8 packet_type,
+				     u8 option, u8 *optval, u8 optlen)
 {
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
-
-	hctx->ccid2hctx_pipe--;
-	BUG_ON(hctx->ccid2hctx_pipe < 0);
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 
-	if (hctx->ccid2hctx_pipe == 0)
-		ccid2_hc_tx_kill_rto_timer(sk);
+	switch (option) {
+	case DCCPO_ACK_VECTOR_0:
+	case DCCPO_ACK_VECTOR_1:
+		return dccp_ackvec_parsed_add(&hc->tx_av_chunks, optval, optlen,
+					      option - DCCPO_ACK_VECTOR_0);
+	}
+	return 0;
 }
 
 static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	const bool sender_was_blocked = ccid2_cwnd_network_limited(hc);
+	struct dccp_ackvec_parsed *avp;
 	u64 ackno, seqno;
 	struct ccid2_seq *seqp;
-	unsigned char *vector;
-	unsigned char veclen;
-	int offset = 0;
 	int done = 0;
-	int loss = 0;
 	unsigned int maxincr = 0;
 
-	ccid2_hc_tx_check_sanity(hctx);
 	/* check reverse path congestion */
 	seqno = DCCP_SKB_CB(skb)->dccpd_seq;
 
@@ -509,68 +519,81 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 	 * -sorbo.
 	 */
 	/* need to bootstrap */
-	if (hctx->ccid2hctx_rpdupack == -1) {
-		hctx->ccid2hctx_rpdupack = 0;
-		hctx->ccid2hctx_rpseq = seqno;
+	if (hc->tx_rpdupack == -1) {
+		hc->tx_rpdupack = 0;
+		hc->tx_rpseq    = seqno;
 	} else {
 		/* check if packet is consecutive */
-		if ((hctx->ccid2hctx_rpseq + 1) == seqno)
-			hctx->ccid2hctx_rpseq++;
+		if (dccp_delta_seqno(hc->tx_rpseq, seqno) == 1)
+			hc->tx_rpseq = seqno;
 		/* it's a later packet */
-		else if (after48(seqno, hctx->ccid2hctx_rpseq)) {
-			hctx->ccid2hctx_rpdupack++;
+		else if (after48(seqno, hc->tx_rpseq)) {
+			hc->tx_rpdupack++;
 
 			/* check if we got enough dupacks */
-			if (hctx->ccid2hctx_rpdupack >=
-			    hctx->ccid2hctx_numdupack) {
-				hctx->ccid2hctx_rpdupack = -1; /* XXX lame */
-				hctx->ccid2hctx_rpseq = 0;
-
-				ccid2_change_l_ack_ratio(sk, dp->dccps_l_ack_ratio << 1);
+			if (hc->tx_rpdupack >= NUMDUPACK) {
+				hc->tx_rpdupack = -1; /* XXX lame */
+				hc->tx_rpseq    = 0;
+#ifdef __CCID2_COPES_GRACEFULLY_WITH_ACK_CONGESTION_CONTROL__
+				/*
+				 * FIXME: Ack Congestion Control is broken; in
+				 * the current state instabilities occurred with
+				 * Ack Ratios greater than 1; causing hang-ups
+				 * and long RTO timeouts. This needs to be fixed
+				 * before opening up dynamic changes. -- gerrit
+				 */
+				ccid2_change_l_ack_ratio(sk, 2 * dp->dccps_l_ack_ratio);
+#endif
 			}
 		}
 	}
 
 	/* check forward path congestion */
-	/* still didn't send out new data packets */
-	if (hctx->ccid2hctx_seqh == hctx->ccid2hctx_seqt)
+	if (dccp_packet_without_ack(skb))
 		return;
 
-	switch (DCCP_SKB_CB(skb)->dccpd_type) {
-	case DCCP_PKT_ACK:
-	case DCCP_PKT_DATAACK:
-		break;
-	default:
-		return;
-	}
+	/* still didn't send out new data packets */
+	if (hc->tx_seqh == hc->tx_seqt)
+		goto done;
 
 	ackno = DCCP_SKB_CB(skb)->dccpd_ack_seq;
-	seqp = hctx->ccid2hctx_seqh->ccid2s_prev;
+	if (after48(ackno, hc->tx_high_ack))
+		hc->tx_high_ack = ackno;
+
+	seqp = hc->tx_seqt;
+	while (before48(seqp->ccid2s_seq, ackno)) {
+		seqp = seqp->ccid2s_next;
+		if (seqp == hc->tx_seqh) {
+			seqp = hc->tx_seqh->ccid2s_prev;
+			break;
+		}
+	}
 
-	/* If in slow-start, cwnd can increase at most Ack Ratio / 2 packets for
-	 * this single ack.  I round up.
-	 * -sorbo.
+	/*
+	 * In slow-start, cwnd can increase up to a maximum of Ack Ratio/2
+	 * packets per acknowledgement. Rounding up avoids that cwnd is not
+	 * advanced when Ack Ratio is 1 and gives a slight edge otherwise.
 	 */
-	maxincr = dp->dccps_l_ack_ratio >> 1;
-	maxincr++;
+	if (hc->tx_cwnd < hc->tx_ssthresh)
+		maxincr = DIV_ROUND_UP(dp->dccps_l_ack_ratio, 2);
 
 	/* go through all ack vectors */
-	while ((offset = ccid2_ackvector(sk, skb, offset,
-					 &vector, &veclen)) != -1) {
+	list_for_each_entry(avp, &hc->tx_av_chunks, node) {
 		/* go through this ack vector */
-		while (veclen--) {
-			const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
-			u64 ackno_end_rl;
-
-			dccp_set_seqno(&ackno_end_rl, ackno - rl);
-			ccid2_pr_debug("ackvec start:%llu end:%llu\n", ackno,
-				       ackno_end_rl);
+		for (; avp->len--; avp->vec++) {
+			u64 ackno_end_rl = SUB48(ackno,
+						 dccp_ackvec_runlen(avp->vec));
+
+			ccid2_pr_debug("ackvec %llu |%u,%u|\n",
+				       (unsigned long long)ackno,
+				       dccp_ackvec_state(avp->vec) >> 6,
+				       dccp_ackvec_runlen(avp->vec));
 			/* if the seqno we are analyzing is larger than the
 			 * current ackno, then move towards the tail of our
 			 * seqnos.
 			 */
 			while (after48(seqp->ccid2s_seq, ackno)) {
-				if (seqp == hctx->ccid2hctx_seqt) {
+				if (seqp == hc->tx_seqt) {
 					done = 1;
 					break;
 				}
@@ -583,36 +606,33 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 			 * run length
 			 */
 			while (between48(seqp->ccid2s_seq,ackno_end_rl,ackno)) {
-				const u8 state = (*vector &
-						  DCCP_ACKVEC_STATE_MASK) >> 6;
+				const u8 state = dccp_ackvec_state(avp->vec);
 
 				/* new packet received or marked */
-				if (state != DCCP_ACKVEC_STATE_NOT_RECEIVED &&
+				if (state != DCCPAV_NOT_RECEIVED &&
 				    !seqp->ccid2s_acked) {
-				    	if (state ==
-					    DCCP_ACKVEC_STATE_ECN_MARKED) {
-						loss = 1;
-					} else
+					if (state == DCCPAV_ECN_MARKED)
+						ccid2_congestion_event(sk,
+								       seqp);
+					else
 						ccid2_new_ack(sk, seqp,
 							      &maxincr);
 
 					seqp->ccid2s_acked = 1;
 					ccid2_pr_debug("Got ack for %llu\n",
-					       	       seqp->ccid2s_seq);
-					ccid2_hc_tx_dec_pipe(sk);
+						       (unsigned long long)seqp->ccid2s_seq);
+					hc->tx_pipe--;
 				}
-				if (seqp == hctx->ccid2hctx_seqt) {
+				if (seqp == hc->tx_seqt) {
 					done = 1;
 					break;
 				}
-				seqp = seqp->ccid2s_next;
+				seqp = seqp->ccid2s_prev;
 			}
 			if (done)
 				break;
 
-
-			dccp_set_seqno(&ackno, ackno_end_rl - 1);
-			vector++;
+			ackno = SUB48(ackno_end_rl, 1);
 		}
 		if (done)
 			break;
@@ -621,15 +641,22 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 	/* The state about what is acked should be correct now
 	 * Check for NUMDUPACK
 	 */
-	seqp = hctx->ccid2hctx_seqh->ccid2s_prev;
+	seqp = hc->tx_seqt;
+	while (before48(seqp->ccid2s_seq, hc->tx_high_ack)) {
+		seqp = seqp->ccid2s_next;
+		if (seqp == hc->tx_seqh) {
+			seqp = hc->tx_seqh->ccid2s_prev;
+			break;
+		}
+	}
 	done = 0;
 	while (1) {
 		if (seqp->ccid2s_acked) {
 			done++;
-			if (done == hctx->ccid2hctx_numdupack)
+			if (done == NUMDUPACK)
 				break;
 		}
-		if (seqp == hctx->ccid2hctx_seqt)
+		if (seqp == hc->tx_seqt)
 			break;
 		seqp = seqp->ccid2s_prev;
 	}
@@ -637,143 +664,121 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 	/* If there are at least 3 acknowledgements, anything unacknowledged
 	 * below the last sequence number is considered lost
 	 */
-	if (done == hctx->ccid2hctx_numdupack) {
+	if (done == NUMDUPACK) {
 		struct ccid2_seq *last_acked = seqp;
 
 		/* check for lost packets */
 		while (1) {
 			if (!seqp->ccid2s_acked) {
-				loss = 1;
-				ccid2_hc_tx_dec_pipe(sk);
+				ccid2_pr_debug("Packet lost: %llu\n",
+					       (unsigned long long)seqp->ccid2s_seq);
+				/* XXX need to traverse from tail -> head in
+				 * order to detect multiple congestion events in
+				 * one ack vector.
+				 */
+				ccid2_congestion_event(sk, seqp);
+				hc->tx_pipe--;
 			}
-			if (seqp == hctx->ccid2hctx_seqt)
+			if (seqp == hc->tx_seqt)
 				break;
 			seqp = seqp->ccid2s_prev;
 		}
 
-		hctx->ccid2hctx_seqt = last_acked;
+		hc->tx_seqt = last_acked;
 	}
 
 	/* trim acked packets in tail */
-	while (hctx->ccid2hctx_seqt != hctx->ccid2hctx_seqh) {
-		if (!hctx->ccid2hctx_seqt->ccid2s_acked)
+	while (hc->tx_seqt != hc->tx_seqh) {
+		if (!hc->tx_seqt->ccid2s_acked)
 			break;
 
-		hctx->ccid2hctx_seqt = hctx->ccid2hctx_seqt->ccid2s_next;
+		hc->tx_seqt = hc->tx_seqt->ccid2s_next;
 	}
 
-	if (loss) {
-		/* XXX do bit shifts guarantee a 0 as the new bit? */
-		ccid2_change_cwnd(sk, hctx->ccid2hctx_cwnd >> 1);
-		hctx->ccid2hctx_ssthresh = hctx->ccid2hctx_cwnd;
-		if (hctx->ccid2hctx_ssthresh < 2)
-			hctx->ccid2hctx_ssthresh = 2;
-	}
-
-	ccid2_hc_tx_check_sanity(hctx);
+	/* restart RTO timer if not all outstanding data has been acked */
+	if (hc->tx_pipe == 0)
+		sk_stop_timer(sk, &hc->tx_rtotimer);
+	else
+		sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
+done:
+	/* check if incoming Acks allow pending packets to be sent */
+	if (sender_was_blocked && !ccid2_cwnd_network_limited(hc))
+		tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet);
+	dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks);
 }
 
 static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
 {
-        struct ccid2_hc_tx_sock *hctx = ccid_priv(ccid);
-	int seqcount = ccid2_seq_len;
-	int i;
+	struct ccid2_hc_tx_sock *hc = ccid_priv(ccid);
+	struct dccp_sock *dp = dccp_sk(sk);
+	u32 max_ratio;
 
-	/* XXX init variables with proper values */
-	hctx->ccid2hctx_cwnd	  = 1;
-	hctx->ccid2hctx_ssthresh  = 10;
-	hctx->ccid2hctx_numdupack = 3;
+	/* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */
+	hc->tx_ssthresh = ~0U;
+
+	/* Use larger initial windows (RFC 4341, section 5). */
+	hc->tx_cwnd = rfc3390_bytes_to_packets(dp->dccps_mss_cache);
+	hc->tx_expected_wnd = hc->tx_cwnd;
+
+	/* Make sure that Ack Ratio is enabled and within bounds. */
+	max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2);
+	if (dp->dccps_l_ack_ratio == 0 || dp->dccps_l_ack_ratio > max_ratio)
+		dp->dccps_l_ack_ratio = max_ratio;
 
 	/* XXX init ~ to window size... */
-	hctx->ccid2hctx_seqbuf = kmalloc(sizeof(*hctx->ccid2hctx_seqbuf) *
-					 seqcount, gfp_any());
-	if (hctx->ccid2hctx_seqbuf == NULL)
+	if (ccid2_hc_tx_alloc_seq(hc))
 		return -ENOMEM;
 
-	for (i = 0; i < (seqcount - 1); i++) {
-		hctx->ccid2hctx_seqbuf[i].ccid2s_next =
-					&hctx->ccid2hctx_seqbuf[i + 1];
-		hctx->ccid2hctx_seqbuf[i + 1].ccid2s_prev =
-					&hctx->ccid2hctx_seqbuf[i];
-	}
-	hctx->ccid2hctx_seqbuf[seqcount - 1].ccid2s_next =
-					hctx->ccid2hctx_seqbuf;
-	hctx->ccid2hctx_seqbuf->ccid2s_prev =
-					&hctx->ccid2hctx_seqbuf[seqcount - 1];
-
-	hctx->ccid2hctx_seqh	 = hctx->ccid2hctx_seqbuf;
-	hctx->ccid2hctx_seqt	 = hctx->ccid2hctx_seqh;
-	hctx->ccid2hctx_sent	 = 0;
-	hctx->ccid2hctx_rto	 = 3 * HZ;
-	hctx->ccid2hctx_srtt	 = -1;
-	hctx->ccid2hctx_rttvar	 = -1;
-	hctx->ccid2hctx_lastrtt  = 0;
-	hctx->ccid2hctx_rpdupack = -1;
-
-	hctx->ccid2hctx_rtotimer.function = &ccid2_hc_tx_rto_expire;
-	hctx->ccid2hctx_rtotimer.data	  = (unsigned long)sk;
-	init_timer(&hctx->ccid2hctx_rtotimer);
-
-	ccid2_hc_tx_check_sanity(hctx);
+	hc->tx_rto	 = DCCP_TIMEOUT_INIT;
+	hc->tx_rpdupack  = -1;
+	hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_time_stamp;
+	hc->tx_cwnd_used = 0;
+	setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire,
+			(unsigned long)sk);
+	INIT_LIST_HEAD(&hc->tx_av_chunks);
 	return 0;
 }
 
 static void ccid2_hc_tx_exit(struct sock *sk)
 {
-        struct ccid2_hc_tx_sock *hctx = ccid2_hc_tx_sk(sk);
+	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	int i;
+
+	sk_stop_timer(sk, &hc->tx_rtotimer);
 
-	ccid2_hc_tx_kill_rto_timer(sk);
-	kfree(hctx->ccid2hctx_seqbuf);
-	hctx->ccid2hctx_seqbuf = NULL;
+	for (i = 0; i < hc->tx_seqbufc; i++)
+		kfree(hc->tx_seqbuf[i]);
+	hc->tx_seqbufc = 0;
 }
 
 static void ccid2_hc_rx_packet_recv(struct sock *sk, struct sk_buff *skb)
 {
-	const struct dccp_sock *dp = dccp_sk(sk);
-	struct ccid2_hc_rx_sock *hcrx = ccid2_hc_rx_sk(sk);
-
-	switch (DCCP_SKB_CB(skb)->dccpd_type) {
-	case DCCP_PKT_DATA:
-	case DCCP_PKT_DATAACK:
-		hcrx->ccid2hcrx_data++;
-		if (hcrx->ccid2hcrx_data >= dp->dccps_r_ack_ratio) {
-			dccp_send_ack(sk);
-			hcrx->ccid2hcrx_data = 0;
-		}
-		break;
-	}
-}
+	struct ccid2_hc_rx_sock *hc = ccid2_hc_rx_sk(sk);
 
-static struct ccid_operations ccid2 = {
-	.ccid_id		= 2,
-	.ccid_name		= "ccid2",
-	.ccid_owner		= THIS_MODULE,
-	.ccid_hc_tx_obj_size	= sizeof(struct ccid2_hc_tx_sock),
-	.ccid_hc_tx_init	= ccid2_hc_tx_init,
-	.ccid_hc_tx_exit	= ccid2_hc_tx_exit,
-	.ccid_hc_tx_send_packet	= ccid2_hc_tx_send_packet,
-	.ccid_hc_tx_packet_sent	= ccid2_hc_tx_packet_sent,
-	.ccid_hc_tx_packet_recv	= ccid2_hc_tx_packet_recv,
-	.ccid_hc_rx_obj_size	= sizeof(struct ccid2_hc_rx_sock),
-	.ccid_hc_rx_packet_recv	= ccid2_hc_rx_packet_recv,
-};
-
-module_param(ccid2_debug, int, 0444);
-MODULE_PARM_DESC(ccid2_debug, "Enable debug messages");
+	if (!dccp_data_packet(skb))
+		return;
 
-static __init int ccid2_module_init(void)
-{
-	return ccid_register(&ccid2);
+	if (++hc->rx_num_data_pkts >= dccp_sk(sk)->dccps_r_ack_ratio) {
+		dccp_send_ack(sk);
+		hc->rx_num_data_pkts = 0;
+	}
 }
-module_init(ccid2_module_init);
 
-static __exit void ccid2_module_exit(void)
-{
-	ccid_unregister(&ccid2);
-}
-module_exit(ccid2_module_exit);
+struct ccid_operations ccid2_ops = {
+	.ccid_id		  = DCCPC_CCID2,
+	.ccid_name		  = "TCP-like",
+	.ccid_hc_tx_obj_size	  = sizeof(struct ccid2_hc_tx_sock),
+	.ccid_hc_tx_init	  = ccid2_hc_tx_init,
+	.ccid_hc_tx_exit	  = ccid2_hc_tx_exit,
+	.ccid_hc_tx_send_packet	  = ccid2_hc_tx_send_packet,
+	.ccid_hc_tx_packet_sent	  = ccid2_hc_tx_packet_sent,
+	.ccid_hc_tx_parse_options = ccid2_hc_tx_parse_options,
+	.ccid_hc_tx_packet_recv	  = ccid2_hc_tx_packet_recv,
+	.ccid_hc_rx_obj_size	  = sizeof(struct ccid2_hc_rx_sock),
+	.ccid_hc_rx_packet_recv	  = ccid2_hc_rx_packet_recv,
+};
 
-MODULE_AUTHOR("Andrea Bittau <a.bittau@cs.ucl.ac.uk>");
-MODULE_DESCRIPTION("DCCP TCP-Like (CCID2) CCID");
-MODULE_LICENSE("GPL");
-MODULE_ALIAS("net-dccp-ccid-2");
+#ifdef CONFIG_IP_DCCP_CCID2_DEBUG
+module_param(ccid2_debug, bool, 0644);
+MODULE_PARM_DESC(ccid2_debug, "Enable CCID-2 debug messages");
+#endif