This commit marks the first formal contribution of the "Five New TCP Congestion

Control Algorithms for FreeBSD" FreeBSD Foundation funded project. More details
about the project are available at: http://caia.swin.edu.au/freebsd/5cc/

- Add a KPI and supporting infrastructure to allow modular congestion control
  algorithms to be used in the net stack. Algorithms can maintain per-connection
  state if required, and connections maintain their own algorithm pointer, which
  allows different connections to concurrently use different algorithms. The
  TCP_CONGESTION socket option can be used with getsockopt()/setsockopt() to
  programmatically query or change the congestion control algorithm respectively
  from within an application at runtime.

- Integrate the framework with the TCP stack in as least intrusive a manner as
  possible. Care was also taken to develop the framework in a way that should
  allow integration with other congestion aware transport protocols (e.g. SCTP)
  in the future. The hope is that we will one day be able to share a single set
  of congestion control algorithm modules between all congestion aware transport
  protocols.

- Introduce a new congestion recovery (TF_CONGRECOVERY) state into the TCP stack
  and use it to decouple the meaning of recovery from a congestion event and
  recovery from packet loss (TF_FASTRECOVERY) a la RFC2581. ECN and delay based
  congestion control protocols don't generally need to recover from packet loss
  and need a different way to note a congestion recovery episode within the
  stack.

- Remove the net.inet.tcp.newreno sysctl, which simplifies some portions of code
  and ensures the stack always uses the appropriate mechanisms for recovering
  from packet loss during a congestion recovery episode.

- Extract the NewReno congestion control algorithm from the TCP stack and
  massage it into module form. NewReno is always built into the kernel and will
  remain the default algorithm for the forseeable future. Implementations of
  additional different algorithms will become available in the near future.

- Bump __FreeBSD_version to 900025 and note in UPDATING that rebuilding code
  that relies on the size of "struct tcpcb" is required.

Many thanks go to the Cisco University Research Program Fund at Community
Foundation Silicon Valley and the FreeBSD Foundation. Their support of our work
at the Centre for Advanced Internet Architectures, Swinburne University of
Technology is greatly appreciated.

In collaboration with:	David Hayes <dahayes at swin edu au> and
			Grenville Armitage <garmitage at swin edu au>
Sponsored by:	Cisco URP, FreeBSD Foundation
Reviewed by:	rpaulo
Tested by:	David Hayes (and many others over the years)
MFC after:	3 months

1 files changed, 24 insertions, 6 deletions

diff --git a/sys/netinet/tcp_var.h b/sys/netinet/tcp_var.h
index 0b28681..442c736 100644
--- a/sys/netinet/tcp_var.h
+++ b/sys/netinet/tcp_var.h
@@ -195,9 +195,11 @@ struct tcpcb {
 	struct toe_usrreqs *t_tu;	/* offload operations vector */
 	void	*t_toe;			/* TOE pcb pointer */
 	int	t_bytes_acked;		/* # bytes acked during current RTT */
+	struct cc_algo	*cc_algo;	/* congestion control algorithm */
+	struct cc_var	*ccv;
 
 	int	t_ispare;		/* explicit pad for 64bit alignment */
-	void	*t_pspare2[6];		/* 2 CC / 4 TBD */
+	void	*t_pspare2[4];		/* 4 TBD */
 	uint64_t _pad[12];		/* 7 UTO, 5 TBD (1-2 CC/RTT?) */
 };
 
@@ -230,10 +232,22 @@ struct tcpcb {
 #define	TF_ECN_PERMIT	0x4000000	/* connection ECN-ready */
 #define	TF_ECN_SND_CWR	0x8000000	/* ECN CWR in queue */
 #define	TF_ECN_SND_ECE	0x10000000	/* ECN ECE in queue */
+#define	TF_CONGRECOVERY	0x20000000	/* congestion recovery mode */
+#define	TF_WASCRECOVERY	0x40000000	/* was in congestion recovery */
 
-#define IN_FASTRECOVERY(tp)	(tp->t_flags & TF_FASTRECOVERY)
-#define ENTER_FASTRECOVERY(tp)	tp->t_flags |= TF_FASTRECOVERY
-#define EXIT_FASTRECOVERY(tp)	tp->t_flags &= ~TF_FASTRECOVERY
+#define	IN_FASTRECOVERY(t_flags)	(t_flags & TF_FASTRECOVERY)
+#define	ENTER_FASTRECOVERY(t_flags)	t_flags |= TF_FASTRECOVERY
+#define	EXIT_FASTRECOVERY(t_flags)	t_flags &= ~TF_FASTRECOVERY
+
+#define	IN_CONGRECOVERY(t_flags)	(t_flags & TF_CONGRECOVERY)
+#define	ENTER_CONGRECOVERY(t_flags)	t_flags |= TF_CONGRECOVERY
+#define	EXIT_CONGRECOVERY(t_flags)	t_flags &= ~TF_CONGRECOVERY
+
+#define	IN_RECOVERY(t_flags) (t_flags & (TF_CONGRECOVERY | TF_FASTRECOVERY))
+#define	ENTER_RECOVERY(t_flags) t_flags |= (TF_CONGRECOVERY | TF_FASTRECOVERY)
+#define	EXIT_RECOVERY(t_flags) t_flags &= ~(TF_CONGRECOVERY | TF_FASTRECOVERY)
+
+#define	BYTES_THIS_ACK(tp, th)	(th->th_ack - tp->snd_una)
 
 /*
  * Flags for the t_oobflags field.
@@ -562,10 +576,11 @@ VNET_DECLARE(int, tcp_mssdflt);	/* XXX */
 VNET_DECLARE(int, tcp_minmss);
 VNET_DECLARE(int, tcp_delack_enabled);
 VNET_DECLARE(int, tcp_do_rfc3390);
-VNET_DECLARE(int, tcp_do_newreno);
 VNET_DECLARE(int, path_mtu_discovery);
 VNET_DECLARE(int, ss_fltsz);
 VNET_DECLARE(int, ss_fltsz_local);
+VNET_DECLARE(int, tcp_do_rfc3465);
+VNET_DECLARE(int, tcp_abc_l_var);
 #define	V_tcb			VNET(tcb)
 #define	V_tcbinfo		VNET(tcbinfo)
 #define	V_tcpstat		VNET(tcpstat)
@@ -573,10 +588,11 @@ VNET_DECLARE(int, ss_fltsz_local);
 #define	V_tcp_minmss		VNET(tcp_minmss)
 #define	V_tcp_delack_enabled	VNET(tcp_delack_enabled)
 #define	V_tcp_do_rfc3390	VNET(tcp_do_rfc3390)
-#define	V_tcp_do_newreno	VNET(tcp_do_newreno)
 #define	V_path_mtu_discovery	VNET(path_mtu_discovery)
 #define	V_ss_fltsz		VNET(ss_fltsz)
 #define	V_ss_fltsz_local	VNET(ss_fltsz_local)
+#define	V_tcp_do_rfc3465	VNET(tcp_do_rfc3465)
+#define	V_tcp_abc_l_var		VNET(tcp_abc_l_var)
 
 VNET_DECLARE(int, tcp_do_sack);			/* SACK enabled/disabled */
 VNET_DECLARE(int, tcp_sc_rst_sock_fail);	/* RST on sock alloc failure */
@@ -678,6 +694,8 @@ void	 tcp_free_sackholes(struct tcpcb *tp);
 int	 tcp_newreno(struct tcpcb *, struct tcphdr *);
 u_long	 tcp_seq_subtract(u_long, u_long );
 
+void	cc_cong_signal(struct tcpcb *tp, struct tcphdr *th, uint32_t type);
+
 #endif /* _KERNEL */
 
 #endif /* _NETINET_TCP_VAR_H_ */