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

24 files changed, 2304 insertions, 1060 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a2c893a7475..ab65714d95f 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -304,57 +304,6 @@ tcp_low_latency - BOOLEAN
 	changed would be a Beowulf compute cluster.
 	Default: 0
 
-tcp_westwood - BOOLEAN
-        Enable TCP Westwood+ congestion control algorithm.
-	TCP Westwood+ is a sender-side only modification of the TCP Reno 
-	protocol stack that optimizes the performance of TCP congestion 
-	control. It is based on end-to-end bandwidth estimation to set 
-	congestion window and slow start threshold after a congestion 
-	episode. Using this estimation, TCP Westwood+ adaptively sets a 
-	slow start threshold and a congestion window which takes into 
-	account the bandwidth used  at the time congestion is experienced. 
-	TCP Westwood+ significantly increases fairness wrt TCP Reno in 
-	wired networks and throughput over wireless links.   
-        Default: 0
-
-tcp_vegas_cong_avoid - BOOLEAN
-	Enable TCP Vegas congestion avoidance algorithm.
-	TCP Vegas is a sender-side only change to TCP that anticipates
-	the onset of congestion by estimating the bandwidth. TCP Vegas
-	adjusts the sending rate by modifying the congestion
-	window. TCP Vegas should provide less packet loss, but it is
-	not as aggressive as TCP Reno.
-	Default:0
-
-tcp_bic - BOOLEAN
-	Enable BIC TCP congestion control algorithm.
-	BIC-TCP is a sender-side only change that ensures a linear RTT
-	fairness under large windows while offering both scalability and
-	bounded TCP-friendliness. The protocol combines two schemes
-	called additive increase and binary search increase. When the
-	congestion window is large, additive increase with a large
-	increment ensures linear RTT fairness as well as good
-	scalability. Under small congestion windows, binary search
-	increase provides TCP friendliness.
-	Default: 0
-
-tcp_bic_low_window - INTEGER
-	Sets the threshold window (in packets) where BIC TCP starts to
-	adjust the congestion window. Below this threshold BIC TCP behaves
-	the same as the default TCP Reno. 
-	Default: 14
-
-tcp_bic_fast_convergence - BOOLEAN
-	Forces BIC TCP to more quickly respond to changes in congestion
-	window. Allows two flows sharing the same connection to converge
-	more rapidly.
-	Default: 1
-
-tcp_default_win_scale - INTEGER
-	Sets the minimum window scale TCP will negotiate for on all
-	conections.
-	Default: 7
-
 tcp_tso_win_divisor - INTEGER
        This allows control over what percentage of the congestion window
        can be consumed by a single TSO frame.
@@ -368,6 +317,11 @@ tcp_frto - BOOLEAN
 	where packet loss is typically due to random radio interference
 	rather than intermediate router congestion.
 
+tcp_congestion_control - STRING
+	Set the congestion control algorithm to be used for new
+	connections. The algorithm "reno" is always available, but
+	additional choices may be available based on kernel configuration.
+
 somaxconn - INTEGER
 	Limit of socket listen() backlog, known in userspace as SOMAXCONN.
 	Defaults to 128.  See also tcp_max_syn_backlog for additional tuning
diff --git a/Documentation/networking/tcp.txt b/Documentation/networking/tcp.txt
index 71749007091..0fa30042557 100644
--- a/Documentation/networking/tcp.txt
+++ b/Documentation/networking/tcp.txt
@@ -1,5 +1,72 @@
-How the new TCP output machine [nyi] works.
+TCP protocol
+============
+
+Last updated: 21 June 2005
+
+Contents
+========
+
+- Congestion control
+- How the new TCP output machine [nyi] works
+
+Congestion control
+==================
+
+The following variables are used in the tcp_sock for congestion control:
+snd_cwnd		The size of the congestion window
+snd_ssthresh		Slow start threshold. We are in slow start if
+			snd_cwnd is less than this.
+snd_cwnd_cnt		A counter used to slow down the rate of increase
+			once we exceed slow start threshold.
+snd_cwnd_clamp		This is the maximum size that snd_cwnd can grow to.
+snd_cwnd_stamp		Timestamp for when congestion window last validated.
+snd_cwnd_used		Used as a highwater mark for how much of the
+			congestion window is in use. It is used to adjust
+			snd_cwnd down when the link is limited by the
+			application rather than the network.
+
+As of 2.6.13, Linux supports pluggable congestion control algorithms.
+A congestion control mechanism can be registered through functions in
+tcp_cong.c. The functions used by the congestion control mechanism are
+registered via passing a tcp_congestion_ops struct to
+tcp_register_congestion_control. As a minimum name, ssthresh,
+cong_avoid, min_cwnd must be valid.
 
+Private data for a congestion control mechanism is stored in tp->ca_priv.
+tcp_ca(tp) returns a pointer to this space.  This is preallocated space - it
+is important to check the size of your private data will fit this space, or
+alternatively space could be allocated elsewhere and a pointer to it could
+be stored here.
+
+There are three kinds of congestion control algorithms currently: The
+simplest ones are derived from TCP reno (highspeed, scalable) and just
+provide an alternative the congestion window calculation. More complex
+ones like BIC try to look at other events to provide better
+heuristics.  There are also round trip time based algorithms like
+Vegas and Westwood+.
+
+Good TCP congestion control is a complex problem because the algorithm
+needs to maintain fairness and performance. Please review current
+research and RFC's before developing new modules.
+
+The method that is used to determine which congestion control mechanism is
+determined by the setting of the sysctl net.ipv4.tcp_congestion_control.
+The default congestion control will be the last one registered (LIFO);
+so if you built everything as modules. the default will be reno. If you
+build with the default's from Kconfig, then BIC will be builtin (not a module)
+and it will end up the default.
+
+If you really want a particular default value then you will need
+to set it with the sysctl.  If you use a sysctl, the module will be autoloaded
+if needed and you will get the expected protocol. If you ask for an
+unknown congestion method, then the sysctl attempt will fail.
+
+If you remove a tcp congestion control module, then you will get the next
+available one. Since reno can not be built as a module, and can not be
+deleted, it will always be available.
+
+How the new TCP output machine [nyi] works.
+===========================================
 
 Data is kept on a single queue. The skb->users flag tells us if the frame is
 one that has been queued already. To add a frame we throw it on the end. Ack
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 614e939c78a..72965bfe6cf 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -333,21 +333,14 @@ enum
 	NET_TCP_FRTO=92,
 	NET_TCP_LOW_LATENCY=93,
 	NET_IPV4_IPFRAG_SECRET_INTERVAL=94,
-	NET_TCP_WESTWOOD=95,
 	NET_IPV4_IGMP_MAX_MSF=96,
 	NET_TCP_NO_METRICS_SAVE=97,
-	NET_TCP_VEGAS=98,
-	NET_TCP_VEGAS_ALPHA=99,
-	NET_TCP_VEGAS_BETA=100,
-	NET_TCP_VEGAS_GAMMA=101,
- 	NET_TCP_BIC=102,
- 	NET_TCP_BIC_FAST_CONVERGENCE=103,
-	NET_TCP_BIC_LOW_WINDOW=104,
 	NET_TCP_DEFAULT_WIN_SCALE=105,
 	NET_TCP_MODERATE_RCVBUF=106,
 	NET_TCP_TSO_WIN_DIVISOR=107,
 	NET_TCP_BIC_BETA=108,
 	NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR=109,
+	NET_TCP_CONG_CONTROL=110,
 };
 
 enum {
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 97a7c9e03df..3ea75dd6640 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -203,13 +203,6 @@ struct tcp_sack_block {
 	__u32	end_seq;
 };
 
-enum tcp_congestion_algo {
-	TCP_RENO=0,
-	TCP_VEGAS,
-	TCP_WESTWOOD,
-	TCP_BIC,
-};
-
 struct tcp_options_received {
 /*	PAWS/RTTM data	*/
 	long	ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -305,7 +298,7 @@ struct tcp_sock {
 	__u8	reordering;	/* Packet reordering metric.		*/
 	__u8	frto_counter;	/* Number of new acks after RTO */
 
-	__u8	adv_cong;	/* Using Vegas, Westwood, or BIC */
+	__u8	unused;
 	__u8	defer_accept;	/* User waits for some data after accept() */
 
 /* RTT measurement */
@@ -401,37 +394,10 @@ struct tcp_sock {
 		__u32	time;
 	} rcvq_space;
 
-/* TCP Westwood structure */
-        struct {
-                __u32    bw_ns_est;        /* first bandwidth estimation..not too smoothed 8) */
-                __u32    bw_est;           /* bandwidth estimate */
-                __u32    rtt_win_sx;       /* here starts a new evaluation... */
-                __u32    bk;
-                __u32    snd_una;          /* used for evaluating the number of acked bytes */
-                __u32    cumul_ack;
-                __u32    accounted;
-                __u32    rtt;
-                __u32    rtt_min;          /* minimum observed RTT */
-        } westwood;
-
-/* Vegas variables */
-	struct {
-		__u32	beg_snd_nxt;	/* right edge during last RTT */
-		__u32	beg_snd_una;	/* left edge  during last RTT */
-		__u32	beg_snd_cwnd;	/* saves the size of the cwnd */
-		__u8	doing_vegas_now;/* if true, do vegas for this RTT */
-		__u16	cntRTT;		/* # of RTTs measured within last RTT */
-		__u32	minRTT;		/* min of RTTs measured within last RTT (in usec) */
-		__u32	baseRTT;	/* the min of all Vegas RTT measurements seen (in usec) */
-	} vegas;
-
-	/* BI TCP Parameters */
-	struct {
-		__u32	cnt;		/* increase cwnd by 1 after this number of ACKs */
-		__u32 	last_max_cwnd;	/* last maximium snd_cwnd */
-		__u32	last_cwnd;	/* the last snd_cwnd */
-		__u32   last_stamp;     /* time when updated last_cwnd */
-	} bictcp;
+	/* Pluggable TCP congestion control hook */
+	struct tcp_congestion_ops *ca_ops;
+	u32	ca_priv[16];
+#define TCP_CA_PRIV_SIZE	(16*sizeof(u32))
 };
 
 static inline struct tcp_sock *tcp_sk(const struct sock *sk)
@@ -439,6 +405,11 @@ static inline struct tcp_sock *tcp_sk(const struct sock *sk)
 	return (struct tcp_sock *)sk;
 }
 
+static inline void *tcp_ca(const struct tcp_sock *tp)
+{
+	return (void *) tp->ca_priv;
+}
+
 #endif
 
 #endif	/* _LINUX_TCP_H */
diff --git a/include/linux/tcp_diag.h b/include/linux/tcp_diag.h
index ceee962e1d1..7a599674394 100644
--- a/include/linux/tcp_diag.h
+++ b/include/linux/tcp_diag.h
@@ -99,9 +99,10 @@ enum
 	TCPDIAG_MEMINFO,
 	TCPDIAG_INFO,
 	TCPDIAG_VEGASINFO,
+	TCPDIAG_CONG,
 };
 
-#define TCPDIAG_MAX TCPDIAG_VEGASINFO
+#define TCPDIAG_MAX TCPDIAG_CONG
 
 
 /* TCPDIAG_MEM */
@@ -123,5 +124,4 @@ struct tcpvegas_info {
 	__u32	tcpv_minrtt;
 };
 
-
 #endif /* _TCP_DIAG_H_ */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f730935b824..e427cf35915 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -505,25 +505,6 @@ static __inline__ int tcp_sk_listen_hashfn(struct sock *sk)
 #else
 # define TCP_TW_RECYCLE_TICK (12+2-TCP_TW_RECYCLE_SLOTS_LOG)
 #endif
-
-#define BICTCP_BETA_SCALE    1024	/* Scale factor beta calculation
-					 * max_cwnd = snd_cwnd * beta
-					 */
-#define BICTCP_MAX_INCREMENT 32		/*
-					 * Limit on the amount of
-					 * increment allowed during
-					 * binary search.
-					 */
-#define BICTCP_FUNC_OF_MIN_INCR 11	/*
-					 * log(B/Smin)/log(B/(B-1))+1,
-					 * Smin:min increment
-					 * B:log factor
-					 */
-#define BICTCP_B		4	 /*
-					  * In binary search,
-					  * go to point (max+min)/N
-					  */
-
 /*
  *	TCP option
  */
@@ -596,16 +577,7 @@ extern int sysctl_tcp_adv_win_scale;
 extern int sysctl_tcp_tw_reuse;
 extern int sysctl_tcp_frto;
 extern int sysctl_tcp_low_latency;
-extern int sysctl_tcp_westwood;
-extern int sysctl_tcp_vegas_cong_avoid;
-extern int sysctl_tcp_vegas_alpha;
-extern int sysctl_tcp_vegas_beta;
-extern int sysctl_tcp_vegas_gamma;
 extern int sysctl_tcp_nometrics_save;
-extern int sysctl_tcp_bic;
-extern int sysctl_tcp_bic_fast_convergence;
-extern int sysctl_tcp_bic_low_window;
-extern int sysctl_tcp_bic_beta;
 extern int sysctl_tcp_moderate_rcvbuf;
 extern int sysctl_tcp_tso_win_divisor;
 
@@ -1136,6 +1108,80 @@ static inline void tcp_packets_out_dec(struct tcp_sock *tp,
 	tp->packets_out -= tcp_skb_pcount(skb);
 }
 
+/* Events passed to congestion control interface */
+enum tcp_ca_event {
+	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
+	CA_EVENT_CWND_RESTART,	/* congestion window restart */
+	CA_EVENT_COMPLETE_CWR,	/* end of congestion recovery */
+	CA_EVENT_FRTO,		/* fast recovery timeout */
+	CA_EVENT_LOSS,		/* loss timeout */
+	CA_EVENT_FAST_ACK,	/* in sequence ack */
+	CA_EVENT_SLOW_ACK,	/* other ack */
+};
+
+/*
+ * Interface for adding new TCP congestion control handlers
+ */
+#define TCP_CA_NAME_MAX	16
+struct tcp_congestion_ops {
+	struct list_head	list;
+
+	/* initialize private data (optional) */
+	void (*init)(struct tcp_sock *tp);
+	/* cleanup private data  (optional) */
+	void (*release)(struct tcp_sock *tp);
+
+	/* return slow start threshold (required) */
+	u32 (*ssthresh)(struct tcp_sock *tp);
+	/* lower bound for congestion window (optional) */
+	u32 (*min_cwnd)(struct tcp_sock *tp);
+	/* do new cwnd calculation (required) */
+	void (*cong_avoid)(struct tcp_sock *tp, u32 ack,
+			   u32 rtt, u32 in_flight, int good_ack);
+	/* round trip time sample per acked packet (optional) */
+	void (*rtt_sample)(struct tcp_sock *tp, u32 usrtt);
+	/* call before changing ca_state (optional) */
+	void (*set_state)(struct tcp_sock *tp, u8 new_state);
+	/* call when cwnd event occurs (optional) */
+	void (*cwnd_event)(struct tcp_sock *tp, enum tcp_ca_event ev);
+	/* new value of cwnd after loss (optional) */
+	u32  (*undo_cwnd)(struct tcp_sock *tp);
+	/* hook for packet ack accounting (optional) */
+	void (*pkts_acked)(struct tcp_sock *tp, u32 num_acked);
+	/* get info for tcp_diag (optional) */
+	void (*get_info)(struct tcp_sock *tp, u32 ext, struct sk_buff *skb);
+
+	char 		name[TCP_CA_NAME_MAX];
+	struct module 	*owner;
+};
+
+extern int tcp_register_congestion_control(struct tcp_congestion_ops *type);
+extern void tcp_unregister_congestion_control(struct tcp_congestion_ops *type);
+
+extern void tcp_init_congestion_control(struct tcp_sock *tp);
+extern void tcp_cleanup_congestion_control(struct tcp_sock *tp);
+extern int tcp_set_default_congestion_control(const char *name);
+extern void tcp_get_default_congestion_control(char *name);
+
+extern struct tcp_congestion_ops tcp_reno;
+extern u32 tcp_reno_ssthresh(struct tcp_sock *tp);
+extern void tcp_reno_cong_avoid(struct tcp_sock *tp, u32 ack,
+				u32 rtt, u32 in_flight, int flag);
+extern u32 tcp_reno_min_cwnd(struct tcp_sock *tp);
+
+static inline void tcp_set_ca_state(struct tcp_sock *tp, u8 ca_state)
+{
+	if (tp->ca_ops->set_state)
+		tp->ca_ops->set_state(tp, ca_state);
+	tp->ca_state = ca_state;
+}
+
+static inline void tcp_ca_event(struct tcp_sock *tp, enum tcp_ca_event event)
+{
+	if (tp->ca_ops->cwnd_event)
+		tp->ca_ops->cwnd_event(tp, event);
+}
+
 /* This determines how many packets are "in the network" to the best
  * of our knowledge.  In many cases it is conservative, but where
  * detailed information is available from the receiver (via SACK
@@ -1155,91 +1201,6 @@ static __inline__ unsigned int tcp_packets_in_flight(const struct tcp_sock *tp)
 	return (tp->packets_out - tp->left_out + tp->retrans_out);
 }
 
-/*
- * Which congestion algorithim is in use on the connection.
- */
-#define tcp_is_vegas(__tp)	((__tp)->adv_cong == TCP_VEGAS)
-#define tcp_is_westwood(__tp)	((__tp)->adv_cong == TCP_WESTWOOD)
-#define tcp_is_bic(__tp)	((__tp)->adv_cong == TCP_BIC)
-
-/* Recalculate snd_ssthresh, we want to set it to:
- *
- * Reno:
- * 	one half the current congestion window, but no
- *	less than two segments
- *
- * BIC:
- *	behave like Reno until low_window is reached,
- *	then increase congestion window slowly
- */
-static inline __u32 tcp_recalc_ssthresh(struct tcp_sock *tp)
-{
-	if (tcp_is_bic(tp)) {
-		if (sysctl_tcp_bic_fast_convergence &&
-		    tp->snd_cwnd < tp->bictcp.last_max_cwnd)
-			tp->bictcp.last_max_cwnd = (tp->snd_cwnd * 
-						    (BICTCP_BETA_SCALE
-						     + sysctl_tcp_bic_beta))
-				/ (2 * BICTCP_BETA_SCALE);
-		else
-			tp->bictcp.last_max_cwnd = tp->snd_cwnd;
-
-		if (tp->snd_cwnd > sysctl_tcp_bic_low_window)
-			return max((tp->snd_cwnd * sysctl_tcp_bic_beta)
-				   / BICTCP_BETA_SCALE, 2U);
-	}
-
-	return max(tp->snd_cwnd >> 1U, 2U);
-}
-
-/* Stop taking Vegas samples for now. */
-#define tcp_vegas_disable(__tp)	((__tp)->vegas.doing_vegas_now = 0)
-    
-static inline void tcp_vegas_enable(struct tcp_sock *tp)
-{
-	/* There are several situations when we must "re-start" Vegas:
-	 *
-	 *  o when a connection is established
-	 *  o after an RTO
-	 *  o after fast recovery
-	 *  o when we send a packet and there is no outstanding
-	 *    unacknowledged data (restarting an idle connection)
-	 *
-	 * In these circumstances we cannot do a Vegas calculation at the
-	 * end of the first RTT, because any calculation we do is using
-	 * stale info -- both the saved cwnd and congestion feedback are
-	 * stale.
-	 *
-	 * Instead we must wait until the completion of an RTT during
-	 * which we actually receive ACKs.
-	 */
-    
-	/* Begin taking Vegas samples next time we send something. */
-	tp->vegas.doing_vegas_now = 1;
-     
-	/* Set the beginning of the next send window. */
-	tp->vegas.beg_snd_nxt = tp->snd_nxt;
-
-	tp->vegas.cntRTT = 0;
-	tp->vegas.minRTT = 0x7fffffff;
-}
-
-/* Should we be taking Vegas samples right now? */
-#define tcp_vegas_enabled(__tp)	((__tp)->vegas.doing_vegas_now)
-
-extern void tcp_ca_init(struct tcp_sock *tp);
-
-static inline void tcp_set_ca_state(struct tcp_sock *tp, u8 ca_state)
-{
-	if (tcp_is_vegas(tp)) {
-		if (ca_state == TCP_CA_Open) 
-			tcp_vegas_enable(tp);
-		else
-			tcp_vegas_disable(tp);
-	}
-	tp->ca_state = ca_state;
-}
-
 /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd.
  * The exception is rate halving phase, when cwnd is decreasing towards
  * ssthresh.
@@ -1288,7 +1249,7 @@ static inline void tcp_cwnd_validate(struct sock *sk, struct tcp_sock *tp)
 static inline void __tcp_enter_cwr(struct tcp_sock *tp)
 {
 	tp->undo_marker = 0;
-	tp->snd_ssthresh = tcp_recalc_ssthresh(tp);
+	tp->snd_ssthresh = tp->ca_ops->ssthresh(tp);
 	tp->snd_cwnd = min(tp->snd_cwnd,
 			   tcp_packets_in_flight(tp) + 1U);
 	tp->snd_cwnd_cnt = 0;
@@ -1876,52 +1837,4 @@ struct tcp_iter_state {
 extern int tcp_proc_register(struct tcp_seq_afinfo *afinfo);
 extern void tcp_proc_unregister(struct tcp_seq_afinfo *afinfo);
 
-/* TCP Westwood functions and constants */
-
-#define TCP_WESTWOOD_INIT_RTT  (20*HZ)           /* maybe too conservative?! */
-#define TCP_WESTWOOD_RTT_MIN   (HZ/20)           /* 50ms */
-
-static inline void tcp_westwood_update_rtt(struct tcp_sock *tp, __u32 rtt_seq)
-{
-        if (tcp_is_westwood(tp))
-                tp->westwood.rtt = rtt_seq;
-}
-
-static inline __u32 __tcp_westwood_bw_rttmin(const struct tcp_sock *tp)
-{
-        return max((tp->westwood.bw_est) * (tp->westwood.rtt_min) /
-		   (__u32) (tp->mss_cache_std),
-		   2U);
-}
-
-static inline __u32 tcp_westwood_bw_rttmin(const struct tcp_sock *tp)
-{
-	return tcp_is_westwood(tp) ? __tcp_westwood_bw_rttmin(tp) : 0;
-}
-
-static inline int tcp_westwood_ssthresh(struct tcp_sock *tp)
-{
-	__u32 ssthresh = 0;
-
-	if (tcp_is_westwood(tp)) {
-		ssthresh = __tcp_westwood_bw_rttmin(tp);
-		if (ssthresh)
-			tp->snd_ssthresh = ssthresh;  
-	}
-
-	return (ssthresh != 0);
-}
-
-static inline int tcp_westwood_cwnd(struct tcp_sock *tp)
-{
-	__u32 cwnd = 0;
-
-	if (tcp_is_westwood(tp)) {
-		cwnd = __tcp_westwood_bw_rttmin(tp);
-		if (cwnd)
-			tp->snd_cwnd = cwnd;
-	}
-
-	return (cwnd != 0);
-}
 #endif	/* _TCP_H */
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 567b03b1c34..690e88ba248 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -433,5 +433,95 @@ config IP_TCPDIAG
 config IP_TCPDIAG_IPV6
 	def_bool (IP_TCPDIAG=y && IPV6=y) || (IP_TCPDIAG=m && IPV6)
 
+# TCP Reno is builtin (required as fallback)
+menu "TCP congestion control"
+	depends on INET
+
+config TCP_CONG_BIC
+	tristate "Binary Increase Congestion (BIC) control"
+	depends on INET
+	default y
+	---help---
+	BIC-TCP is a sender-side only change that ensures a linear RTT
+	fairness under large windows while offering both scalability and
+	bounded TCP-friendliness. The protocol combines two schemes
+	called additive increase and binary search increase. When the
+	congestion window is large, additive increase with a large
+	increment ensures linear RTT fairness as well as good
+	scalability. Under small congestion windows, binary search
+	increase provides TCP friendliness.
+	See http://www.csc.ncsu.edu/faculty/rhee/export/bitcp/
+
+config TCP_CONG_WESTWOOD
+	tristate "TCP Westwood+"
+	depends on INET
+	default m
+	---help---
+	TCP Westwood+ is a sender-side only modification of the TCP Reno
+	protocol stack that optimizes the performance of TCP congestion
+	control. It is based on end-to-end bandwidth estimation to set
+	congestion window and slow start threshold after a congestion
+	episode. Using this estimation, TCP Westwood+ adaptively sets a
+	slow start threshold and a congestion window which takes into
+	account the bandwidth used  at the time congestion is experienced.
+	TCP Westwood+ significantly increases fairness wrt TCP Reno in
+	wired networks and throughput over wireless links.
+
+config TCP_CONG_HTCP
+        tristate "H-TCP"
+	depends on INET
+        default m
+	---help---
+	H-TCP is a send-side only modifications of the TCP Reno
+	protocol stack that optimizes the performance of TCP
+	congestion control for high speed network links. It uses a
+	modeswitch to change the alpha and beta parameters of TCP Reno
+	based on network conditions and in a way so as to be fair with
+	other Reno and H-TCP flows.
+
+config TCP_CONG_HSTCP
+	tristate "High Speed TCP"
+	depends on INET && EXPERIMENTAL
+	default n
+	---help---
+	Sally Floyd's High Speed TCP (RFC 3649) congestion control.
+	A modification to TCP's congestion control mechanism for use
+	with large congestion windows. A table indicates how much to
+	increase the congestion window by when an ACK is received.
+ 	For more detail	see http://www.icir.org/floyd/hstcp.html
+
+config TCP_CONG_HYBLA
+	tristate "TCP-Hybla congestion control algorithm"
+	depends on INET && EXPERIMENTAL
+	default n
+	---help---
+	TCP-Hybla is a sender-side only change that eliminates penalization of
+	long-RTT, large-bandwidth connections, like when satellite legs are
+	involved, expecially when sharing a common bottleneck with normal
+	terrestrial connections.
+
+config TCP_CONG_VEGAS
+	tristate "TCP Vegas"
+	depends on INET && EXPERIMENTAL
+	default n
+	---help---
+	TCP Vegas is a sender-side only change to TCP that anticipates
+	the onset of congestion by estimating the bandwidth. TCP Vegas
+	adjusts the sending rate by modifying the congestion
+	window. TCP Vegas should provide less packet loss, but it is
+	not as aggressive as TCP Reno.
+
+config TCP_CONG_SCALABLE
+	tristate "Scalable TCP"
+	depends on INET && EXPERIMENTAL
+	default n
+	---help---
+	Scalable TCP is a sender-side only change to TCP which uses a
+	MIMD congestion control algorithm which has some nice scaling
+	properties, though is known to have fairness issues.
+	See http://www-lce.eng.cam.ac.uk/~ctk21/scalable/
+
+endmenu
+
 source "net/ipv4/ipvs/Kconfig"
 
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 65d57d8e1ad..5718cdb3a61 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -5,7 +5,8 @@
 obj-y     := utils.o route.o inetpeer.o protocol.o \
 	     ip_input.o ip_fragment.o ip_forward.o ip_options.o \
 	     ip_output.o ip_sockglue.o \
-	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o tcp_minisocks.o \
+	     tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
+	     tcp_minisocks.o tcp_cong.o \
 	     datagram.o raw.o udp.o arp.o icmp.o devinet.o af_inet.o igmp.o \
 	     sysctl_net_ipv4.o fib_frontend.o fib_semantics.o
 
@@ -30,6 +31,13 @@ obj-$(CONFIG_NETFILTER)	+= netfilter/
 obj-$(CONFIG_IP_VS) += ipvs/
 obj-$(CONFIG_IP_TCPDIAG) += tcp_diag.o 
 obj-$(CONFIG_IP_ROUTE_MULTIPATH_CACHED) += multipath.o
+obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o
+obj-$(CONFIG_TCP_CONG_WESTWOOD) += tcp_westwood.o
+obj-$(CONFIG_TCP_CONG_HSTCP) += tcp_highspeed.o
+obj-$(CONFIG_TCP_CONG_HYBLA) += tcp_hybla.o
+obj-$(CONFIG_TCP_CONG_HTCP) += tcp_htcp.o
+obj-$(CONFIG_TCP_CONG_VEGAS) += tcp_vegas.o
+obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o
 
 obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \
 		      xfrm4_output.o
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 23068bddbf0..e3289453241 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -118,6 +118,45 @@ static int ipv4_sysctl_forward_strategy(ctl_table *table,
 	return 1;
 }
 
+static int proc_tcp_congestion_control(ctl_table *ctl, int write, struct file * filp,
+				       void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	char val[TCP_CA_NAME_MAX];
+	ctl_table tbl = {
+		.data = val,
+		.maxlen = TCP_CA_NAME_MAX,
+	};
+	int ret;
+
+	tcp_get_default_congestion_control(val);
+
+	ret = proc_dostring(&tbl, write, filp, buffer, lenp, ppos);
+	if (write && ret == 0)
+		ret = tcp_set_default_congestion_control(val);
+	return ret;
+}
+
+int sysctl_tcp_congestion_control(ctl_table *table, int __user *name, int nlen,
+				  void __user *oldval, size_t __user *oldlenp,
+				  void __user *newval, size_t newlen,
+				  void **context)
+{
+	char val[TCP_CA_NAME_MAX];
+	ctl_table tbl = {
+		.data = val,
+		.maxlen = TCP_CA_NAME_MAX,
+	};
+	int ret;
+
+	tcp_get_default_congestion_control(val);
+	ret = sysctl_string(&tbl, name, nlen, oldval, oldlenp, newval, newlen,
+			    context);
+	if (ret == 0 && newval && newlen)
+		ret = tcp_set_default_congestion_control(val);
+	return ret;
+}
+
+
 ctl_table ipv4_table[] = {
         {
 		.ctl_name	= NET_IPV4_TCP_TIMESTAMPS,
@@ -612,70 +651,6 @@ ctl_table ipv4_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 	{
-		.ctl_name	= NET_TCP_WESTWOOD, 
-		.procname	= "tcp_westwood",
-		.data		= &sysctl_tcp_westwood,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_VEGAS,
-		.procname	= "tcp_vegas_cong_avoid",
-		.data		= &sysctl_tcp_vegas_cong_avoid,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_VEGAS_ALPHA,
-		.procname	= "tcp_vegas_alpha",
-		.data		= &sysctl_tcp_vegas_alpha,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_VEGAS_BETA,
-		.procname	= "tcp_vegas_beta",
-		.data		= &sysctl_tcp_vegas_beta,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_VEGAS_GAMMA,
-		.procname	= "tcp_vegas_gamma",
-		.data		= &sysctl_tcp_vegas_gamma,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_BIC,
-		.procname	= "tcp_bic",
-		.data		= &sysctl_tcp_bic,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_BIC_FAST_CONVERGENCE,
-		.procname	= "tcp_bic_fast_convergence",
-		.data		= &sysctl_tcp_bic_fast_convergence,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
-		.ctl_name	= NET_TCP_BIC_LOW_WINDOW,
-		.procname	= "tcp_bic_low_window",
-		.data		= &sysctl_tcp_bic_low_window,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
-	},
-	{
 		.ctl_name	= NET_TCP_MODERATE_RCVBUF,
 		.procname	= "tcp_moderate_rcvbuf",
 		.data		= &sysctl_tcp_moderate_rcvbuf,
@@ -692,13 +667,14 @@ ctl_table ipv4_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 	{
-		.ctl_name	= NET_TCP_BIC_BETA,
-		.procname	= "tcp_bic_beta",
-		.data		= &sysctl_tcp_bic_beta,
-		.maxlen		= sizeof(int),
+		.ctl_name	= NET_TCP_CONG_CONTROL,
+		.procname	= "tcp_congestion_control",
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.maxlen		= TCP_CA_NAME_MAX,
+		.proc_handler	= &proc_tcp_congestion_control,
+		.strategy	= &sysctl_tcp_congestion_control,
 	},
+
 	{ .ctl_name = 0 }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 674bbd8cfd3..f3dbc8dc126 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2333,6 +2333,8 @@ void __init tcp_init(void)
 	printk(KERN_INFO "TCP: Hash tables configured "
 	       "(established %d bind %d)\n",
 	       tcp_ehash_size << 1, tcp_bhash_size);
+
+	tcp_register_congestion_control(&tcp_reno);
 }
 
 EXPORT_SYMBOL(tcp_accept);
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
new file mode 100644
index 00000000000..ec38d45d664
--- /dev/null
+++ b/net/ipv4/tcp_bic.c
@@ -0,0 +1,331 @@
+/*
+ * Binary Increase Congestion control for TCP
+ *
+ * This is from the implementation of BICTCP in
+ * Lison-Xu, Kahaled Harfoush, and Injong Rhee.
+ *  "Binary Increase Congestion Control for Fast, Long Dist