Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6: (1699 commits)
  bnx2/bnx2x: Unsupported Ethtool operations should return -EINVAL.
  vlan: Calling vlan_hwaccel_do_receive() is always valid.
  tproxy: use the interface primary IP address as a default value for --on-ip
  tproxy: added IPv6 support to the socket match
  cxgb3: function namespace cleanup
  tproxy: added IPv6 support to the TPROXY target
  tproxy: added IPv6 socket lookup function to nf_tproxy_core
  be2net: Changes to use only priority codes allowed by f/w
  tproxy: allow non-local binds of IPv6 sockets if IP_TRANSPARENT is enabled
  tproxy: added tproxy sockopt interface in the IPV6 layer
  tproxy: added udp6_lib_lookup function
  tproxy: added const specifiers to udp lookup functions
  tproxy: split off ipv6 defragmentation to a separate module
  l2tp: small cleanup
  nf_nat: restrict ICMP translation for embedded header
  can: mcp251x: fix generation of error frames
  can: mcp251x: fix endless loop in interrupt handler if CANINTF_MERRF is set
  can-raw: add msg_flags to distinguish local traffic
  9p: client code cleanup
  rds: make local functions/variables static
  ...

Fix up conflicts in net/core/dev.c, drivers/net/pcmcia/smc91c92_cs.c and
drivers/net/wireless/ath/ath9k/debug.c as per David

21 files changed, 410 insertions, 610 deletions

diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index 6df6f8ac9636..117fb093dcaf 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -62,22 +62,18 @@ struct ccid_operations {
 	void		(*ccid_hc_tx_exit)(struct sock *sk);
 	void		(*ccid_hc_rx_packet_recv)(struct sock *sk,
 						  struct sk_buff *skb);
-	int		(*ccid_hc_rx_parse_options)(struct sock *sk,
-						    unsigned char option,
-						    unsigned char len, u16 idx,
-						    unsigned char* value);
+	int		(*ccid_hc_rx_parse_options)(struct sock *sk, u8 pkt,
+						    u8 opt, u8 *val, u8 len);
 	int		(*ccid_hc_rx_insert_options)(struct sock *sk,
 						     struct sk_buff *skb);
 	void		(*ccid_hc_tx_packet_recv)(struct sock *sk,
 						  struct sk_buff *skb);
-	int		(*ccid_hc_tx_parse_options)(struct sock *sk,
-						    unsigned char option,
-						    unsigned char len, u16 idx,
-						    unsigned char* value);
+	int		(*ccid_hc_tx_parse_options)(struct sock *sk, u8 pkt,
+						    u8 opt, u8 *val, u8 len);
 	int		(*ccid_hc_tx_send_packet)(struct sock *sk,
 						  struct sk_buff *skb);
 	void		(*ccid_hc_tx_packet_sent)(struct sock *sk,
-						  int more, unsigned int len);
+						  unsigned int len);
 	void		(*ccid_hc_rx_get_info)(struct sock *sk,
 					       struct tcp_info *info);
 	void		(*ccid_hc_tx_get_info)(struct sock *sk,
@@ -148,10 +144,10 @@ static inline int ccid_hc_tx_send_packet(struct ccid *ccid, struct sock *sk,
 }
 
 static inline void ccid_hc_tx_packet_sent(struct ccid *ccid, struct sock *sk,
-					  int more, unsigned int len)
+					  unsigned int len)
 {
 	if (ccid->ccid_ops->ccid_hc_tx_packet_sent != NULL)
-		ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, more, len);
+		ccid->ccid_ops->ccid_hc_tx_packet_sent(sk, len);
 }
 
 static inline void ccid_hc_rx_packet_recv(struct ccid *ccid, struct sock *sk,
@@ -168,27 +164,31 @@ static inline void ccid_hc_tx_packet_recv(struct ccid *ccid, struct sock *sk,
 		ccid->ccid_ops->ccid_hc_tx_packet_recv(sk, skb);
 }
 
+/**
+ * ccid_hc_tx_parse_options  -  Parse CCID-specific options sent by the receiver
+ * @pkt: type of packet that @opt appears on (RFC 4340, 5.1)
+ * @opt: the CCID-specific option type (RFC 4340, 5.8 and 10.3)
+ * @val: value of @opt
+ * @len: length of @val in bytes
+ */
 static inline int ccid_hc_tx_parse_options(struct ccid *ccid, struct sock *sk,
-					   unsigned char option,
-					   unsigned char len, u16 idx,
-					   unsigned char* value)
+					   u8 pkt, u8 opt, u8 *val, u8 len)
 {
-	int rc = 0;
-	if (ccid->ccid_ops->ccid_hc_tx_parse_options != NULL)
-		rc = ccid->ccid_ops->ccid_hc_tx_parse_options(sk, option, len, idx,
-						    value);
-	return rc;
+	if (ccid->ccid_ops->ccid_hc_tx_parse_options == NULL)
+		return 0;
+	return ccid->ccid_ops->ccid_hc_tx_parse_options(sk, pkt, opt, val, len);
 }
 
+/**
+ * ccid_hc_rx_parse_options  -  Parse CCID-specific options sent by the sender
+ * Arguments are analogous to ccid_hc_tx_parse_options()
+ */
 static inline int ccid_hc_rx_parse_options(struct ccid *ccid, struct sock *sk,
-					   unsigned char option,
-					   unsigned char len, u16 idx,
-					   unsigned char* value)
+					   u8 pkt, u8 opt, u8 *val, u8 len)
 {
-	int rc = 0;
-	if (ccid->ccid_ops->ccid_hc_rx_parse_options != NULL)
-		rc = ccid->ccid_ops->ccid_hc_rx_parse_options(sk, option, len, idx, value);
-	return rc;
+	if (ccid->ccid_ops->ccid_hc_rx_parse_options == NULL)
+		return 0;
+	return ccid->ccid_ops->ccid_hc_rx_parse_options(sk, pkt, opt, val, len);
 }
 
 static inline int ccid_hc_rx_insert_options(struct ccid *ccid, struct sock *sk,
diff --git a/net/dccp/ccids/Kconfig b/net/dccp/ccids/Kconfig
index 8408398cd44e..0581143cb800 100644
--- a/net/dccp/ccids/Kconfig
+++ b/net/dccp/ccids/Kconfig
@@ -47,37 +47,6 @@ config IP_DCCP_CCID3_DEBUG
 
 	  If in doubt, say N.
 
-config IP_DCCP_CCID3_RTO
-	  int "Use higher bound for nofeedback timer"
-	  default 100
-	  depends on IP_DCCP_CCID3 && EXPERIMENTAL
-	  ---help---
-	    Use higher lower bound for nofeedback timer expiration.
-
-	    The TFRC nofeedback timer normally expires after the maximum of 4
-	    RTTs and twice the current send interval (RFC 3448, 4.3). On LANs
-	    with a small RTT this can mean a high processing load and reduced
-	    performance, since then the nofeedback timer is triggered very
-	    frequently.
-
-	    This option enables to set a higher lower bound for the nofeedback
-	    value. Values in units of milliseconds can be set here.
-
-	    A value of 0 disables this feature by enforcing the value specified
-	    in RFC 3448. The following values have been suggested as bounds for
-	    experimental use:
-		* 16-20ms to match the typical multimedia inter-frame interval
-		* 100ms as a reasonable compromise [default]
-		* 1000ms corresponds to the lower TCP RTO bound (RFC 2988, 2.4)
-
-	    The default of 100ms is a compromise between a large value for
-	    efficient DCCP implementations, and a small value to avoid disrupting
-	    the network in times of congestion.
-
-	    The purpose of the nofeedback timer is to slow DCCP down when there
-	    is serious network congestion: experimenting with larger values should
-	    therefore not be performed on WANs.
-
 config IP_DCCP_TFRC_LIB
 	def_bool y if IP_DCCP_CCID3
 
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 9b3ae9922be1..d850e291f87c 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -25,59 +25,14 @@
  */
 #include <linux/slab.h>
 #include "../feat.h"
-#include "../ccid.h"
-#include "../dccp.h"
 #include "ccid2.h"
 
 
 #ifdef CONFIG_IP_DCCP_CCID2_DEBUG
 static int ccid2_debug;
 #define ccid2_pr_debug(format, a...)	DCCP_PR_DEBUG(ccid2_debug, format, ##a)
-
-static void ccid2_hc_tx_check_sanity(const struct ccid2_hc_tx_sock *hc)
-{
-	int len = 0;
-	int pipe = 0;
-	struct ccid2_seq *seqp = hc->tx_seqh;
-
-	/* there is data in the chain */
-	if (seqp != hc->tx_seqt) {
-		seqp = seqp->ccid2s_prev;
-		len++;
-		if (!seqp->ccid2s_acked)
-			pipe++;
-
-		while (seqp != hc->tx_seqt) {
-			struct ccid2_seq *prev = seqp->ccid2s_prev;
-
-			len++;
-			if (!prev->ccid2s_acked)
-				pipe++;
-
-			/* packets are sent sequentially */
-			BUG_ON(dccp_delta_seqno(seqp->ccid2s_seq,
-						prev->ccid2s_seq ) >= 0);
-			BUG_ON(time_before(seqp->ccid2s_sent,
-					   prev->ccid2s_sent));
-
-			seqp = prev;
-		}
-	}
-
-	BUG_ON(pipe != hc->tx_pipe);
-	ccid2_pr_debug("len of chain=%d\n", len);
-
-	do {
-		seqp = seqp->ccid2s_prev;
-		len++;
-	} while (seqp != hc->tx_seqh);
-
-	ccid2_pr_debug("total len=%d\n", len);
-	BUG_ON(len != hc->tx_seqbufc * CCID2_SEQBUF_LEN);
-}
 #else
 #define ccid2_pr_debug(format, a...)
-#define ccid2_hc_tx_check_sanity(hc)
 #endif
 
 static int ccid2_hc_tx_alloc_seq(struct ccid2_hc_tx_sock *hc)
@@ -156,19 +111,10 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
 	dp->dccps_l_ack_ratio = val;
 }
 
-static void ccid2_change_srtt(struct ccid2_hc_tx_sock *hc, long val)
-{
-	ccid2_pr_debug("change SRTT to %ld\n", val);
-	hc->tx_srtt = val;
-}
-
-static void ccid2_start_rto_timer(struct sock *sk);
-
 static void ccid2_hc_tx_rto_expire(unsigned long data)
 {
 	struct sock *sk = (struct sock *)data;
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-	long s;
 
 	bh_lock_sock(sk);
 	if (sock_owned_by_user(sk)) {
@@ -178,23 +124,19 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 
 	ccid2_pr_debug("RTO_EXPIRE\n");
 
-	ccid2_hc_tx_check_sanity(hc);
-
 	/* back-off timer */
 	hc->tx_rto <<= 1;
+	if (hc->tx_rto > DCCP_RTO_MAX)
+		hc->tx_rto = DCCP_RTO_MAX;
 
-	s = hc->tx_rto / HZ;
-	if (s > 60)
-		hc->tx_rto = 60 * HZ;
-
-	ccid2_start_rto_timer(sk);
+	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 
 	/* adjust pipe, cwnd etc */
 	hc->tx_ssthresh = hc->tx_cwnd / 2;
 	if (hc->tx_ssthresh < 2)
 		hc->tx_ssthresh = 2;
-	hc->tx_cwnd	 = 1;
-	hc->tx_pipe	 = 0;
+	hc->tx_cwnd	= 1;
+	hc->tx_pipe	= 0;
 
 	/* clear state about stuff we sent */
 	hc->tx_seqt = hc->tx_seqh;
@@ -204,23 +146,12 @@ static void ccid2_hc_tx_rto_expire(unsigned long data)
 	hc->tx_rpseq    = 0;
 	hc->tx_rpdupack = -1;
 	ccid2_change_l_ack_ratio(sk, 1);
-	ccid2_hc_tx_check_sanity(hc);
 out:
 	bh_unlock_sock(sk);
 	sock_put(sk);
 }
 
-static void ccid2_start_rto_timer(struct sock *sk)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
-	ccid2_pr_debug("setting RTO timeout=%ld\n", hc->tx_rto);
-
-	BUG_ON(timer_pending(&hc->tx_rtotimer));
-	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
-}
-
-static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len)
+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);
@@ -230,7 +161,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len)
 
 	hc->tx_seqh->ccid2s_seq   = dp->dccps_gss;
 	hc->tx_seqh->ccid2s_acked = 0;
-	hc->tx_seqh->ccid2s_sent  = jiffies;
+	hc->tx_seqh->ccid2s_sent  = ccid2_time_stamp;
 
 	next = hc->tx_seqh->ccid2s_next;
 	/* check if we need to alloc more space */
@@ -296,23 +227,20 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, int more, unsigned int len)
 	}
 #endif
 
-	/* setup RTO timer */
-	if (!timer_pending(&hc->tx_rtotimer))
-		ccid2_start_rto_timer(sk);
+	sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto);
 
 #ifdef CONFIG_IP_DCCP_CCID2_DEBUG
 	do {
 		struct ccid2_seq *seqp = hc->tx_seqt;
 
 		while (seqp != hc->tx_seqh) {
-			ccid2_pr_debug("out seq=%llu acked=%d time=%lu\n",
+			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(hc);
 #endif
 }
 
@@ -378,17 +306,87 @@ out_invalid_option:
 	return -1;
 }
 
-static void ccid2_hc_tx_kill_rto_timer(struct sock *sk)
+/**
+ * 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 void ccid2_rtt_estimator(struct sock *sk, const long mrtt)
 {
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
+	long m = mrtt ? : 1;
 
-	sk_stop_timer(sk, &hc->tx_rtotimer);
-	ccid2_pr_debug("deleted RTO timer\n");
+	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;
+
+		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;
+		}
+
+		/*
+		 * 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);
+		}
+	}
+
+	/*
+	 * 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;
+
+	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 *hc = ccid2_hc_tx_sk(sk);
 
@@ -402,93 +400,27 @@ static inline void ccid2_new_ack(struct sock *sk,
 			hc->tx_cwnd += 1;
 			hc->tx_packets_acked = 0;
 	}
-
-	/* update RTO */
-	if (hc->tx_srtt == -1 ||
-	    time_after(jiffies, hc->tx_lastrtt + hc->tx_srtt)) {
-		unsigned long r = (long)jiffies - (long)seqp->ccid2s_sent;
-		int s;
-
-		/* first measurement */
-		if (hc->tx_srtt == -1) {
-			ccid2_pr_debug("R: %lu Time=%lu seq=%llu\n",
-				       r, jiffies,
-				       (unsigned long long)seqp->ccid2s_seq);
-			ccid2_change_srtt(hc, r);
-			hc->tx_rttvar = r >> 1;
-		} else {
-			/* RTTVAR */
-			long tmp = hc->tx_srtt - r;
-			long srtt;
-
-			if (tmp < 0)
-				tmp *= -1;
-
-			tmp >>= 2;
-			hc->tx_rttvar *= 3;
-			hc->tx_rttvar >>= 2;
-			hc->tx_rttvar += tmp;
-
-			/* SRTT */
-			srtt = hc->tx_srtt;
-			srtt *= 7;
-			srtt >>= 3;
-			tmp = r >> 3;
-			srtt += tmp;
-			ccid2_change_srtt(hc, srtt);
-		}
-		s = hc->tx_rttvar << 2;
-		/* clock granularity is 1 when based on jiffies */
-		if (!s)
-			s = 1;
-		hc->tx_rto = hc->tx_srtt + s;
-
-		/* must be at least a second */
-		s = hc->tx_rto / HZ;
-		/* DCCP doesn't require this [but I like it cuz my code sux] */
-#if 1
-		if (s < 1)
-			hc->tx_rto = HZ;
-#endif
-		/* max 60 seconds */
-		if (s > 60)
-			hc->tx_rto = HZ * 60;
-
-		hc->tx_lastrtt = jiffies;
-
-		ccid2_pr_debug("srtt: %ld rttvar: %ld rto: %ld (HZ=%d) R=%lu\n",
-			       hc->tx_srtt, hc->tx_rttvar,
-			       hc->tx_rto, HZ, r);
-	}
-
-	/* we got a new ack, so re-start RTO timer */
-	ccid2_hc_tx_kill_rto_timer(sk);
-	ccid2_start_rto_timer(sk);
-}
-
-static void ccid2_hc_tx_dec_pipe(struct sock *sk)
-{
-	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
-
-	if (hc->tx_pipe == 0)
-		DCCP_BUG("pipe == 0");
-	else
-		hc->tx_pipe--;
-
-	if (hc->tx_pipe == 0)
-		ccid2_hc_tx_kill_rto_timer(sk);
+	/*
+	 * 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);
 }
 
 static void ccid2_congestion_event(struct sock *sk, struct ccid2_seq *seqp)
 {
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 
-	if (time_before(seqp->ccid2s_sent, hc->tx_last_cong)) {
+	if ((s32)(seqp->ccid2s_sent - hc->tx_last_cong) < 0) {
 		ccid2_pr_debug("Multiple losses in an RTT---treating as one\n");
 		return;
 	}
 
-	hc->tx_last_cong = jiffies;
+	hc->tx_last_cong = ccid2_time_stamp;
 
 	hc->tx_cwnd      = hc->tx_cwnd / 2 ? : 1U;
 	hc->tx_ssthresh  = max(hc->tx_cwnd, 2U);
@@ -510,7 +442,6 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 	int done = 0;
 	unsigned int maxincr = 0;
 
-	ccid2_hc_tx_check_sanity(hc);
 	/* check reverse path congestion */
 	seqno = DCCP_SKB_CB(skb)->dccpd_seq;
 
@@ -620,7 +551,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 					seqp->ccid2s_acked = 1;
 					ccid2_pr_debug("Got ack for %llu\n",
 						       (unsigned long long)seqp->ccid2s_seq);
-					ccid2_hc_tx_dec_pipe(sk);
+					hc->tx_pipe--;
 				}
 				if (seqp == hc->tx_seqt) {
 					done = 1;
@@ -677,7 +608,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 				 * one ack vector.
 				 */
 				ccid2_congestion_event(sk, seqp);
-				ccid2_hc_tx_dec_pipe(sk);
+				hc->tx_pipe--;
 			}
 			if (seqp == hc->tx_seqt)
 				break;
@@ -695,7 +626,11 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 		hc->tx_seqt = hc->tx_seqt->ccid2s_next;
 	}
 
-	ccid2_hc_tx_check_sanity(hc);
+	/* 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);
 }
 
 static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
@@ -707,12 +642,8 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
 	/* RFC 4341, 5: initialise ssthresh to arbitrarily high (max) value */
 	hc->tx_ssthresh = ~0U;
 
-	/*
-	 * RFC 4341, 5: "The cwnd parameter is initialized to at most four
-	 * packets for new connections, following the rules from [RFC3390]".
-	 * We need to convert the bytes of RFC3390 into the packets of RFC 4341.
-	 */
-	hc->tx_cwnd = clamp(4380U / dp->dccps_mss_cache, 2U, 4U);
+	/* Use larger initial windows (RFC 4341, section 5). */
+	hc->tx_cwnd = rfc3390_bytes_to_packets(dp->dccps_mss_cache);
 
 	/* Make sure that Ack Ratio is enabled and within bounds. */
 	max_ratio = DIV_ROUND_UP(hc->tx_cwnd, 2);
@@ -723,15 +654,11 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk)
 	if (ccid2_hc_tx_alloc_seq(hc))
 		return -ENOMEM;
 
-	hc->tx_rto	 = 3 * HZ;
-	ccid2_change_srtt(hc, -1);
-	hc->tx_rttvar    = -1;
+	hc->tx_rto	 = DCCP_TIMEOUT_INIT;
 	hc->tx_rpdupack  = -1;
-	hc->tx_last_cong = jiffies;
+	hc->tx_last_cong = ccid2_time_stamp;
 	setup_timer(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire,
 			(unsigned long)sk);
-
-	ccid2_hc_tx_check_sanity(hc);
 	return 0;
 }
 
@@ -740,7 +667,7 @@ static void ccid2_hc_tx_exit(struct sock *sk)
 	struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk);
 	int i;
 
-	ccid2_hc_tx_kill_rto_timer(sk);
+	sk_stop_timer(sk, &hc->tx_rtotimer);
 
 	for (i = 0; i < hc->tx_seqbufc; i++)
 		kfree(hc->tx_seqbuf[i]);
diff --git a/net/dccp/ccids/ccid2.h b/net/dccp/ccids/ccid2.h
index 1ec6a30103bb..9731c2dc1487 100644
--- a/net/dccp/ccids/ccid2.h
+++ b/net/dccp/ccids/ccid2.h
@@ -18,18 +18,23 @@
 #ifndef _DCCP_CCID2_H_
 #define _DCCP_CCID2_H_
 
-#include <linux/dccp.h>
 #include <linux/timer.h>
 #include <linux/types.h>
 #include "../ccid.h"
+#include "../dccp.h"
+
+/*
+ * CCID-2 timestamping faces the same issues as TCP timestamping.
+ * Hence we reuse/share as much of the code as possible.
+ */
+#define ccid2_time_stamp	tcp_time_stamp
+
 /* NUMDUPACK parameter from RFC 4341, p. 6 */
 #define NUMDUPACK	3
 
-struct sock;
-
 struct ccid2_seq {
 	u64			ccid2s_seq;
-	unsigned long		ccid2s_sent;
+	u32			ccid2s_sent;
 	int			ccid2s_acked;
 	struct ccid2_seq	*ccid2s_prev;
 	struct ccid2_seq	*ccid2s_next;
@@ -42,7 +47,12 @@ struct ccid2_seq {
  * struct ccid2_hc_tx_sock - CCID2 TX half connection
  * @tx_{cwnd,ssthresh,pipe}: as per RFC 4341, section 5
  * @tx_packets_acked:	     Ack counter for deriving cwnd growth (RFC 3465)
- * @tx_lastrtt:		     time RTT was last measured
+ * @tx_srtt:		     smoothed RTT estimate, scaled by 2^3
+ * @tx_mdev:		     smoothed RTT variation, scaled by 2^2
+ * @tx_mdev_max:	     maximum of @mdev during one flight
+ * @tx_rttvar:		     moving average/maximum of @mdev_max
+ * @tx_rto:		     RTO value deriving from SRTT and RTTVAR (RFC 2988)
+ * @tx_rtt_seq:		     to decay RTTVAR at most once per flight
  * @tx_rpseq:		     last consecutive seqno
  * @tx_rpdupack:	     dupacks since rpseq
  */
@@ -55,14 +65,19 @@ struct ccid2_hc_tx_sock {
 	int			tx_seqbufc;
 	struct ccid2_seq	*tx_seqh;
 	struct ccid2_seq	*tx_seqt;
-	long			tx_rto;
-	long			tx_srtt;
-	long			tx_rttvar;
-	unsigned long		tx_lastrtt;
+
+	/* RTT measurement: variables/principles are the same as in TCP */
+	u32			tx_srtt,
+				tx_mdev,
+				tx_mdev_max,
+				tx_rttvar,
+				tx_rto;
+	u64			tx_rtt_seq:48;
 	struct timer_list	tx_rtotimer;
+
 	u64			tx_rpseq;
 	int			tx_rpdupack;
-	unsigned long		tx_last_cong;
+	u32			tx_last_cong;
 	u64			tx_high_ack;
 };
 
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index 95f752986497..3060a60ed5ab 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -54,7 +54,6 @@ static const char *ccid3_tx_state_name(enum ccid3_hc_tx_states state)
 	[TFRC_SSTATE_NO_SENT]  = "NO_SENT",
 	[TFRC_SSTATE_NO_FBACK] = "NO_FBACK",
 	[TFRC_SSTATE_FBACK]    = "FBACK",
-	[TFRC_SSTATE_TERM]     = "TERM",
 	};
 
 	return ccid3_state_names[state];
@@ -91,19 +90,16 @@ static inline u64 rfc3390_initial_rate(struct sock *sk)
 	return scaled_div(w_init << 6, hc->tx_rtt);
 }
 
-/*
- * Recalculate t_ipi and delta (should be called whenever X changes)
+/**
+ * ccid3_update_send_interval  -  Calculate new t_ipi = s / X_inst
+ * This respects the granularity of X_inst (64 * bytes/second).
  */
 static void ccid3_update_send_interval(struct ccid3_hc_tx_sock *hc)
 {
-	/* Calculate new t_ipi = s / X_inst (X_inst is in 64 * bytes/second) */
 	hc->tx_t_ipi = scaled_div32(((u64)hc->tx_s) << 6, hc->tx_x);
 
-	/* Calculate new delta by delta = min(t_ipi / 2, t_gran / 2) */
-	hc->tx_delta = min_t(u32, hc->tx_t_ipi / 2, TFRC_OPSYS_HALF_TIME_GRAN);
-
-	ccid3_pr_debug("t_ipi=%u, delta=%u, s=%u, X=%u\n", hc->tx_t_ipi,
-		       hc->tx_delta, hc->tx_s, (unsigned)(hc->tx_x >> 6));
+	ccid3_pr_debug("t_ipi=%u, s=%u, X=%u\n", hc->tx_t_ipi,
+		       hc->tx_s, (unsigned)(hc->tx_x >> 6));
 }
 
 static u32 ccid3_hc_tx_idle_rtt(struct ccid3_hc_tx_sock *hc, ktime_t now)
@@ -211,16 +207,19 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
 	ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk,
 		       ccid3_tx_state_name(hc->tx_state));
 
+	/* Ignore and do not restart after leaving the established state */
+	if ((1 << sk->sk_state) & ~(DCCPF_OPEN | DCCPF_PARTOPEN))
+		goto out;
+
+	/* Reset feedback state to "no feedback received" */
 	if (hc->tx_state == TFRC_SSTATE_FBACK)
 		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK);
-	else if (hc->tx_state != TFRC_SSTATE_NO_FBACK)
-		goto out;
 
 	/*
 	 * Determine new allowed sending rate X as per draft rfc3448bis-00, 4.4
+	 * RTO is 0 if and only if no feedback has been received yet.
 	 */
-	if (hc->tx_t_rto == 0 ||	/* no feedback received yet */
-	    hc->tx_p == 0) {
+	if (hc->tx_t_rto == 0 || hc->tx_p == 0) {
 
 		/* halve send rate directly */
 		hc->tx_x = max(hc->tx_x / 2,
@@ -256,7 +255,7 @@ static void ccid3_hc_tx_no_feedback_timer(unsigned long data)
 	 * Set new timeout for the nofeedback timer.
 	 * See comments in packet_recv() regarding the value of t_RTO.
 	 */
-	if (unlikely(hc->tx_t_rto == 0))	/* no feedback yet */
+	if (unlikely(hc->tx_t_rto == 0))	/* no feedback received yet */
 		t_nfb = TFRC_INITIAL_TIMEOUT;
 	else
 		t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi);
@@ -290,8 +289,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(skb->len == 0))
 		return -EBADMSG;
 
-	switch (hc->tx_state) {
-	case TFRC_SSTATE_NO_SENT:
+	if (hc->tx_state == TFRC_SSTATE_NO_SENT) {
 		sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies +
 			       usecs_to_jiffies(TFRC_INITIAL_TIMEOUT)));
 		hc->tx_last_win_count	= 0;
@@ -326,27 +324,22 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 		ccid3_update_send_interval(hc);
 
 		ccid3_hc_tx_set_state(sk, TFRC_SSTATE_NO_FBACK);
-		break;
-	case TFRC_SSTATE_NO_FBACK:
-	case TFRC_SSTATE_FBACK:
+
+	} else {
 		delay = ktime_us_delta(hc->tx_t_nom, now);
 		ccid3_pr_debug("delay=%ld\n", (long)delay);
 		/*
-		 *	Scheduling of packet transmissions [RFC 3448, 4.6]
+		 *	Scheduling of packet transmissions (RFC 5348, 8.3)
 		 *
 		 * if (t_now > t_nom - delta)
 		 *       // send the packet now
 		 * else
 		 *       // send the packet in (t_nom - t_now) milliseconds.
 		 */
-		if (delay - (s64)hc->tx_delta >= 1000)
-			return (u32)delay / 1000L;
+		if (delay >= TFRC_T_DELTA)
+			return (u32)delay / USEC_PER_MSEC;
 
 		ccid3_hc_tx_update_win_count(hc, now);
-		break;
-	case TFRC_SSTATE_TERM:
-		DCCP_BUG("%s(%p) - Illegal state TERM", dccp_role(sk), sk);
-		return -EINVAL;
 	}
 
 	/* prepare to send now (add options etc.) */
@@ -358,8 +351,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
 	return 0;
 }
 
-static void ccid3_hc_tx_packet_sent(struct sock *sk, int more,
-				    unsigned int len)
+static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len)
 {
 	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
 
@@ -372,48 +364,34 @@ static void ccid3_hc_tx_packet_sent(struct sock *sk, int more,
 static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb)
 {
 	struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk);
-	struct ccid3_options_received *opt_recv;
+	struct tfrc_tx_hist_entry *acked;
 	ktime_t now;
 	unsigned long t_nfb;
-	u32 pinv, r_sample;
+	u32 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;
-	/* ... and only in the established state */
-	if (hc->tx_state != TFRC_SSTATE_FBACK &&
-	    hc->tx_state != TFRC_SSTATE_NO_FBACK)
-		return;
-
-	opt_recv = &hc->tx_options_received;
-	now = ktime_get_real();
-
-	/* Estimate RTT from history if ACK number is valid */
-	r_sample = tfrc_tx_hist_rtt(hc->tx_hist,
-				    DCCP_SKB_CB(skb)->dccpd_ack_seq, now);
-	if (r_sample == 0) {
-		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 */
-	hc->tx_x_recv = opt_recv->ccid3or_receive_rate;
-	hc->tx_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   */
-		hc->tx_p = 0;
-	else				       /* can not exceed 100% */
-		hc->tx_p = scaled_div(1, pinv);
 	/*
-	 * Validate new RTT sample and update moving average
+	 * Locate the acknowledged packet in the TX history.
+	 *
+	 * Returning "entry not found" here can for instance happen when
+	 *  - the host has not sent out anything (e.g. a passive server),
+	 *  - the Ack is outdated (packet with higher Ack number was received),
+	 *  - it is a bogus Ack (for a packet not sent on this connection).
 	 */
-	r_sample = dccp_sample_rtt(sk, r_sample);
+	acked = tfrc_tx_hist_find_entry(hc->tx_hist, dccp_hdr_ack_seq(skb));
+	if (acked == NULL)
+		return;
+	/* For the sake of RTT sampling, ignore/remove all older entries */
+	tfrc_tx_hist_purge(&acked->next);
+
+	/* Update the moving average for the RTT estimate (RFC 3448, 4.3) */
+	now	  = ktime_get_real();
+	r_sample  = dccp_sample_rtt(sk, ktime_us_delta(now, acked->stamp));
 	hc->tx_rtt = tfrc_ewma(hc->tx_rtt, r_sample, 9);
+
 	/*
 	 * Update allowed sending rate X as per draft rfc3448bis-00, 4.2/3
 	 */
@@ -461,13 +439,12 @@ done_computing_x:
 	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.
+	 * Update timeout interval for the nofeedback timer. In order to control
+	 * rate halving on networks with very low RTTs (<= 1 ms), use per-route
+	 * tunable RTAX_RTO_MIN value as the lower bound.
 	 */
-	hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt, (CONFIG_IP_DCCP_CCID3_RTO *
-						       (USEC_PER_SEC / 1000)));
+	hc->tx_t_rto = max_t(u32, 4 * hc->tx_rtt,
+				  USEC_PER_SEC/HZ * tcp_rto_min(sk));
 	/*
 	 * Schedule no feedback timer to expire in
 	 * max(t_RTO, 2 * s/X)  =  max(t_RTO, 2 * t_ipi)
@@ -482,66 +459,41 @@ done_computing_x:
 			   jiffies + usecs_to_jiffies(t_nfb));
 }
 
-static int ccid3_hc_tx_parse_options(struct sock *sk, unsigned char option,
-				     unsigned char len, u16 idx,
-				     unsigned char *value)
+static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type,
+				     u8 option, u8 *optval, u8 optlen)
 {
-	int rc = 0;
-	const struc