Provide new socket option TCP_CCALGOOPT, which stands for TCP congestion

control algorithm options.  The argument is variable length and is opaque
to TCP, forwarded directly to the algorithm's ctl_output method.

Provide new includes directory netinet/cc, where algorithm specific
headers can be installed.

The new API doesn't yet have any in tree consumers.

The original code written by lstewart.
Reviewed by:	rrs, emax
Sponsored by:	Netflix
Differential Revision:	https://reviews.freebsd.org/D711

8 files changed, 70 insertions, 6 deletions

diff --git a/etc/mtree/BSD.include.dist b/etc/mtree/BSD.include.dist
index bb0b26d..88e80e6 100644
--- a/etc/mtree/BSD.include.dist
+++ b/etc/mtree/BSD.include.dist
@@ -270,6 +270,8 @@
         ..
     ..
     netinet
+        cc
+        ..
     ..
     netinet6
     ..
diff --git a/include/Makefile b/include/Makefile
index c75de6e..8033de1 100644
--- a/include/Makefile
+++ b/include/Makefile
@@ -53,6 +53,7 @@ LSUBDIRS=	cam/ata cam/scsi \
 	geom/raid geom/raid3 geom/shsec geom/stripe geom/virstor \
 	net/altq \
 	netgraph/atm netgraph/netflow \
+	netinet/cc \
 	security/audit \
 	security/mac_biba security/mac_bsdextended security/mac_lomac \
 	security/mac_mls security/mac_partition \
diff --git a/share/man/man4/mod_cc.4 b/share/man/man4/mod_cc.4
index f5f4493..4712a39 100644
--- a/share/man/man4/mod_cc.4
+++ b/share/man/man4/mod_cc.4
@@ -30,7 +30,7 @@
 .\"
 .\" $FreeBSD$
 .\"
-.Dd January 12, 2015
+.Dd January 21, 2016
 .Dt MOD_CC 4
 .Os
 .Sh NAME
@@ -49,7 +49,9 @@ using the
 facility.
 .Pp
 The default algorithm is NewReno, and all connections use the default unless
-explicitly overridden using the TCP_CONGESTION socket option (see
+explicitly overridden using the
+.Dv TCP_CONGESTION
+socket option (see
 .Xr tcp 4
 for details).
 The default can be changed using a
@@ -57,6 +59,14 @@ The default can be changed using a
 MIB variable detailed in the
 .Sx MIB Variables
 section below.
+.Pp
+Algorithm specific parameters can be set or queried using the
+.Dv TCP_CCALGOOPT
+socket option (see
+.Xr tcp 4
+for details).
+Callers must pass a pointer to an algorithm specific data, and specify
+its size.
 .Sh MIB Variables
 The framework exposes the following variables in the
 .Va net.inet.tcp.cc
diff --git a/share/man/man4/tcp.4 b/share/man/man4/tcp.4
index 8c5887f..de993e7 100644
--- a/share/man/man4/tcp.4
+++ b/share/man/man4/tcp.4
@@ -34,7 +34,7 @@
 .\"     From: @(#)tcp.4	8.1 (Berkeley) 6/5/93
 .\" $FreeBSD$
 .\"
-.Dd October 27, 2015
+.Dd January 21, 2016
 .Dt TCP 4
 .Os
 .Sh NAME
@@ -137,6 +137,11 @@ send window size,
 receive window size,
 and
 bandwidth-controlled window space.
+.It Dv TCP_CCALGOOPT
+Set or query congestion control algorithm specific parameters.
+See
+.Xr mod_cc 4
+for details.
 .It Dv TCP_CONGESTION
 Select or query the congestion control algorithm that TCP will use for the
 connection.
diff --git a/share/man/man9/mod_cc.9 b/share/man/man9/mod_cc.9
index f1cd5be..05205ed 100644
--- a/share/man/man9/mod_cc.9
+++ b/share/man/man9/mod_cc.9
@@ -31,7 +31,7 @@
 .\"
 .\" $FreeBSD$
 .\"
-.Dd December 26, 2014
+.Dd January 21, 2016
 .Dt MOD_CC 9
 .Os
 .Sh NAME
@@ -40,7 +40,8 @@
 .Nm CCV
 .Nd Modular Congestion Control
 .Sh SYNOPSIS
-.In netinet/cc.h
+.In netinet/tcp.h
+.In netinet/tcp_cc.h
 .In netinet/cc/cc_module.h
 .Fn DECLARE_CC_MODULE "ccname" "ccalgo"
 .Fn CCV "ccv" "what"
@@ -74,6 +75,7 @@ struct cc_algo {
 	void	(*cong_signal) (struct cc_var *ccv, uint32_t type);
 	void	(*post_recovery) (struct cc_var *ccv);
 	void	(*after_idle) (struct cc_var *ccv);
+	int	(*ctl_output)(struct cc_var *, struct sockopt *, void *);
 };
 .Ed
 .Pp
@@ -166,6 +168,20 @@ function is called when data transfer resumes after an idle period.
 It should be implemented to adjust state as required.
 .Pp
 The
+.Va ctl_output
+function is called when
+.Xr getsockopt 2
+or
+.Xr setsockopt 2
+is called on a
+.Xr tcp 4
+socket with the
+.Va struct sockopt
+pointer forwarded unmodified from the TCP control, and a
+.Va void *
+pointer to algorithm specific argument.
+.Pp
+The
 .Fn DECLARE_CC_MODULE
 macro provides a convenient wrapper around the
 .Xr DECLARE_MODULE 9
diff --git a/sys/netinet/tcp.h b/sys/netinet/tcp.h
index bfc8073..4703810 100644
--- a/sys/netinet/tcp.h
+++ b/sys/netinet/tcp.h
@@ -165,6 +165,7 @@ struct tcphdr {
 #define TCP_MD5SIG	16	/* use MD5 digests (RFC2385) */
 #define	TCP_INFO	32	/* retrieve tcp_info structure */
 #define	TCP_CONGESTION	64	/* get/set congestion control algorithm */
+#define	TCP_CCALGOOPT	65	/* get/set cc algorithm specific options */
 #define	TCP_KEEPINIT	128	/* N, time to establish connection */
 #define	TCP_KEEPIDLE	256	/* L,N,X start keeplives after this period */
 #define	TCP_KEEPINTVL	512	/* L,N interval between keepalives */
diff --git a/sys/netinet/tcp_cc.h b/sys/netinet/tcp_cc.h
index 4a2b0c8..d90cd19 100644
--- a/sys/netinet/tcp_cc.h
+++ b/sys/netinet/tcp_cc.h
@@ -151,6 +151,9 @@ struct cc_algo {
 	/* Called for an additional ECN processing apart from RFC3168. */
 	void	(*ecnpkt_handler)(struct cc_var *ccv);
 
+	/* Called for {get|set}sockopt() on a TCP socket with TCP_CCALGOOPT. */
+	int     (*ctl_output)(struct cc_var *, struct sockopt *, void *);
+
 	STAILQ_ENTRY (cc_algo) entries;
 };
 
diff --git a/sys/netinet/tcp_usrreq.c b/sys/netinet/tcp_usrreq.c
index 29e92b2..4b3150b 100644
--- a/sys/netinet/tcp_usrreq.c
+++ b/sys/netinet/tcp_usrreq.c
@@ -1480,7 +1480,33 @@ tcp_default_ctloutput(struct socket *so, struct sockopt *sopt, struct inpcb *inp
 	struct	tcp_info ti;
 	struct cc_algo *algo;
 	char	*buf;
-	
+
+	/*
+	 * For TCP_CCALGOOPT forward the control to CC module, for both
+	 * SOPT_SET and SOPT_GET.
+	 */
+	switch (sopt->sopt_name) {
+	case TCP_CCALGOOPT:
+		INP_WUNLOCK(inp);
+		buf = malloc(sopt->sopt_valsize, M_TEMP, M_WAITOK | M_ZERO);
+		error = sooptcopyin(sopt, buf, sopt->sopt_valsize,
+		    sopt->sopt_valsize);
+		if (error) {
+			free(buf, M_TEMP);
+			return (error);
+		}
+		INP_WLOCK_RECHECK(inp);
+		if (CC_ALGO(tp)->ctl_output != NULL)
+			error = CC_ALGO(tp)->ctl_output(tp->ccv, sopt, buf);
+		else
+			error = ENOENT;
+		INP_WUNLOCK(inp);
+		if (error == 0 && sopt->sopt_dir == SOPT_GET)
+			error = sooptcopyout(sopt, buf, sopt->sopt_valsize);
+		free(buf, M_TEMP);
+		return (error);
+	}
+
 	switch (sopt->sopt_dir) {
 	case SOPT_SET:
 		switch (sopt->sopt_name) {