bring in KAME IPv6 code, dated 19991208.

replaces NRL IPv6 layer.  reuses NRL pcb layer.  no IPsec-on-v6 support.
see sys/netinet6/{TODO,IMPLEMENTATION} for more details.

GENERIC configuration should work fine as before.  GENERIC.v6 works fine
as well, but you'll need KAME userland tools to play with IPv6 (will be
bringed into soon).

4 files changed, 377 insertions, 16 deletions

diff --git a/sys/kern/uipc_domain.c b/sys/kern/uipc_domain.c
index 9d5a23865f8..3695d21f72d 100644
--- a/sys/kern/uipc_domain.c
+++ b/sys/kern/uipc_domain.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: uipc_domain.c,v 1.8 1999/03/30 00:19:05 niklas Exp $	*/
+/*	$OpenBSD: uipc_domain.c,v 1.9 1999/12/08 06:50:17 itojun Exp $	*/
 /*	$NetBSD: uipc_domain.c,v 1.14 1996/02/09 19:00:44 christos Exp $	*/
 
 /*
@@ -67,9 +67,12 @@ domaininit()
 	register struct protosw *pr;
 
 #undef unix
+	/*
+	 * KAME NOTE: ADDDOMAIN(route) is moved to the last part so that
+	 * it will be initialized as the *first* element.  confusing!
+	 */
 #ifndef lint
 	ADDDOMAIN(unix);
-	ADDDOMAIN(route);
 #ifdef INET
 	ADDDOMAIN(inet);
 #endif
@@ -100,6 +103,12 @@ domaininit()
 	ADDDOMAIN(imp);
 #endif
 #endif
+#ifdef IPSEC
+#ifdef __KAME__
+	ADDDOMAIN(key);
+#endif
+#endif
+	ADDDOMAIN(route);
 #endif
 
 	for (dp = domains; dp; dp = dp->dom_next) {
@@ -177,14 +186,15 @@ net_sysctl(name, namelen, oldp, oldlenp, newp, newlen, p)
 	int family, protocol;
 
 	/*
-	 * All sysctl names at this level are nonterminal;
-	 * next two components are protocol family and protocol number,
-	 * then at least one addition component.
+	 * All sysctl names at this level are nonterminal.
+	 * PF_KEY: next component is protocol family, and then at least one
+	 *	additional component.
+	 * usually: next two components are protocol family and protocol
+	 *	number, then at least one addition component.
 	 */
-	if (namelen < 3)
+	if (namelen < 2)
 		return (EISDIR);		/* overloaded */
 	family = name[0];
-	protocol = name[1];
 
 	if (family == 0)
 		return (0);
@@ -193,6 +203,23 @@ net_sysctl(name, namelen, oldp, oldlenp, newp, newlen, p)
 			goto found;
 	return (ENOPROTOOPT);
 found:
+	switch (family) {
+#ifdef IPSEC
+#ifdef __KAME__
+	case PF_KEY:
+		pr = dp->dom_protosw;
+		if (pr->pr_sysctl)
+			return ((*pr->pr_sysctl)(name + 1, namelen - 1,
+				oldp, oldlenp, newp, newlen));
+		return (ENOPROTOOPT);
+#endif
+#endif
+	default:
+		break;
+	}
+	if (namelen < 3)
+		return (EISDIR);		/* overloaded */
+	protocol = name[1];
 	for (pr = dp->dom_protosw; pr < dp->dom_protoswNPROTOSW; pr++)
 		if (pr->pr_protocol == protocol && pr->pr_sysctl)
 			return ((*pr->pr_sysctl)(name + 2, namelen - 2,
diff --git a/sys/kern/uipc_mbuf2.c b/sys/kern/uipc_mbuf2.c
new file mode 100644
index 00000000000..6b9816e1f40
--- /dev/null
+++ b/sys/kern/uipc_mbuf2.c
@@ -0,0 +1,277 @@
+/*	$NetBSD: uipc_mbuf.c,v 1.40 1999/04/01 00:23:25 thorpej Exp $	*/
+
+/*
+ * Copyright (C) 1999 WIDE Project.
+ * All rights reserved.
+ * 
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the project nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * 
+ * THIS SOFTWARE IS PROVIDED BY THE PROJECT AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE PROJECT OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ */
+
+/*
+ * Copyright (c) 1982, 1986, 1988, 1991, 1993
+ *	The Regents of the University of California.  All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. All advertising materials mentioning features or use of this software
+ *    must display the following acknowledgement:
+ *	This product includes software developed by the University of
+ *	California, Berkeley and its contributors.
+ * 4. Neither the name of the University nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ *	@(#)uipc_mbuf.c	8.4 (Berkeley) 2/14/95
+ */
+
+#define PULLDOWN_STAT
+/*#define PULLDOWN_DEBUG*/
+
+#ifdef PULLDOWN_STAT
+#if defined(__NetBSD__) || (defined(__FreeBSD__) && __FreeBSD__ >= 3)
+#include "opt_inet.h"
+#endif
+#endif
+
+#include <sys/param.h>
+#include <sys/systm.h>
+#include <sys/proc.h>
+#include <sys/malloc.h>
+#include <sys/mbuf.h>
+#if defined(PULLDOWN_STAT) && defined(INET6)
+#include <netinet/in.h>
+#include <netinet6/ip6.h>
+#include <netinet6/ip6_var.h>
+#endif
+
+/*
+ * ensure that [off, off + len) is contiguous on the mbuf chain "m".
+ * packet chain before "off" is kept untouched.
+ * if offp == NULL, the target will start at <retval, 0> on resulting chain.
+ * if offp != NULL, the target will start at <retval, *offp> on resulting chain.
+ *
+ * on error return (NULL return value), original "m" will be freed.
+ *
+ * XXX M_TRAILINGSPACE/M_LEADINGSPACE on shared cluster (sharedcluster)
+ */
+struct mbuf *
+m_pulldown(m, off, len, offp)
+	struct mbuf *m;
+	int off, len;
+	int *offp;
+{
+	struct mbuf *n, *o;
+	int hlen, tlen, olen;
+	int sharedcluster;
+
+	/* check invalid arguments. */
+	if (m == NULL)
+		panic("m == NULL in m_pulldown()");
+	if (len > MCLBYTES) {
+		m_freem(m);
+		return NULL;	/* impossible */
+	}
+
+#if defined(PULLDOWN_STAT) && defined(INET6)
+	ip6stat.ip6s_pulldown++;
+#endif
+
+#ifdef PULLDOWN_DEBUG
+    {
+	struct mbuf *t;
+	printf("before:");
+	for (t = m; t; t = t->m_next)
+		printf(" %d", t->m_len);
+	printf("\n");
+    }
+#endif
+	n = m;
+	while (n != NULL && off > 0) {
+		if (n->m_len > off)
+			break;
+		off -= n->m_len;
+		n = n->m_next;
+	}
+	if (!n) {
+		m_freem(m);
+		return NULL;	/* mbuf chain too short */
+	}
+
+	/*
+	 * the target data is on <n, off>.
+	 * if we got enough data on the mbuf "n", we're done.
+	 */
+	if ((off == 0 || offp) && len <= n->m_len - off)
+		goto ok;
+
+#if defined(PULLDOWN_STAT) && defined(INET6)
+	ip6stat.ip6s_pulldown_copy++;
+#endif
+
+	/*
+	 * when len < n->m_len - off and off != 0, it is a special case.
+	 * len bytes from <n, off> sits in single mbuf, but the caller does
+	 * not like the starting position (off).
+	 * chop the current mbuf into two pieces, set off to 0.
+	 */
+	if (len < n->m_len - off) {
+		o = m_copym(n, off, n->m_len - off, M_DONTWAIT);
+		if (o == NULL) {
+			m_freem(m);
+			return NULL;	/* ENOBUFS */
+		}
+		n->m_len = off;
+		o->m_next = n->m_next;
+		n->m_next = o;
+		n = n->m_next;
+		off = 0;
+		goto ok;
+	}
+
+	/*
+	 * we need to take hlen from <n, off> and tlen from <n->m_next, 0>,
+	 * and construct contiguous mbuf with m_len == len.
+	 * note that hlen + tlen == len, and tlen > 0.
+	 */
+	hlen = n->m_len - off;
+	tlen = len - hlen;
+
+	/*
+	 * ensure that we have enough trailing data on mbuf chain.
+	 * if not, we can do nothing about the chain.
+	 */
+	olen = 0;
+	for (o = n->m_next; o != NULL; o = o->m_next)
+		olen += o->m_len;
+	if (hlen + olen < len) {
+		m_freem(m);
+		return NULL;	/* mbuf chain too short */
+	}
+
+	/*
+	 * easy cases first.
+	 * we need to use m_copydata() to get data from <n->m_next, 0>.
+	 */
+	if ((n->m_flags & M_EXT) == 0)
+		sharedcluster = 0;
+	else {
+#ifdef __bsdi__
+		if (n->m_ext.ext_func)
+#else
+		if (n->m_ext.ext_free)
+#endif
+			sharedcluster = 1;
+#ifdef __NetBSD__
+		else if (MCLISREFERENCED(n))
+#else
+		else if (mclrefcnt[mtocl(n->m_ext.ext_buf)] > 1)
+#endif
+			sharedcluster = 1;
+		else
+			sharedcluster = 0;
+	}
+	if ((off == 0 || offp) && M_TRAILINGSPACE(n) >= tlen
+	 && !sharedcluster) {
+		m_copydata(n->m_next, 0, tlen, mtod(n, caddr_t) + n->m_len);
+		n->m_len += tlen;
+		m_adj(n->m_next, tlen);
+		goto ok;
+	}
+	if ((off == 0 || offp) && M_LEADINGSPACE(n->m_next) >= hlen
+	 && !sharedcluster) {
+		n->m_next->m_data -= hlen;
+		n->m_next->m_len += hlen;
+		bcopy(mtod(n, caddr_t) + off, mtod(n->m_next, caddr_t), hlen);
+		n->m_len -= hlen;
+		n = n->m_next;
+		off = 0;
+		goto ok;
+	}
+
+	/*
+	 * now, we need to do the hard way.  don't m_copy as there's no room
+	 * on both end.
+	 */
+#if defined(PULLDOWN_STAT) && defined(INET6)
+	ip6stat.ip6s_pulldown_alloc++;
+#endif
+	MGET(o, M_DONTWAIT, m->m_type);
+	if (o == NULL) {
+		m_freem(m);
+		return NULL;	/* ENOBUFS */
+	}
+	if (len > MHLEN) {	/* use MHLEN just for safety */
+		MCLGET(o, M_DONTWAIT);
+		if ((o->m_flags & M_EXT) == 0) {
+			m_freem(m);
+			m_free(o);
+			return NULL;	/* ENOBUFS */
+		}
+	}
+	/* get hlen from <n, off> into <o, 0> */
+	o->m_len = hlen;
+	bcopy(mtod(n, caddr_t) + off, mtod(o, caddr_t), hlen);
+	n->m_len -= hlen;
+	/* get tlen from <n->m_next, 0> into <o, hlen> */
+	m_copydata(n->m_next, 0, tlen, mtod(o, caddr_t) + o->m_len);
+	o->m_len += tlen;
+	m_adj(n->m_next, tlen);
+	o->m_next = n->m_next;
+	n->m_next = o;
+	n = o;
+	off = 0;
+
+ok:
+#ifdef PULLDOWN_DEBUG
+    {
+	struct mbuf *t;
+	printf("after:");
+	for (t = m; t; t = t->m_next)
+		printf("%c%d", t == n ? '*' : ' ', t->m_len);
+	printf(" (off=%d)\n", off);
+    }
+#endif
+	if (offp)
+		*offp = off;
+	return n;
+}
diff --git a/sys/kern/uipc_socket2.c b/sys/kern/uipc_socket2.c
index e1ea890769f..d7f6702fedd 100644
--- a/sys/kern/uipc_socket2.c
+++ b/sys/kern/uipc_socket2.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: uipc_socket2.c,v 1.10 1999/02/19 15:06:52 millert Exp $	*/
+/*	$OpenBSD: uipc_socket2.c,v 1.11 1999/12/08 06:50:17 itojun Exp $	*/
 /*	$NetBSD: uipc_socket2.c,v 1.11 1996/02/04 02:17:55 christos Exp $	*/
 
 /*
@@ -778,3 +778,40 @@ sbdroprecord(sb)
 		} while ((m = mn) != NULL);
 	}
 }
+
+/*
+ * Create a "control" mbuf containing the specified data
+ * with the specified type for presentation on a socket buffer.
+ */
+struct mbuf *
+sbcreatecontrol(p, size, type, level)
+	caddr_t p;
+	register int size;
+	int type, level;
+{
+	register struct cmsghdr *cp;
+	struct mbuf *m;
+
+	if (size + sizeof(*cp) > MCLBYTES) {
+		printf("sbcreatecontrol: message too large %d\n", size);
+		return NULL;
+	}
+
+	if ((m = m_get(M_DONTWAIT, MT_CONTROL)) == NULL)
+		return ((struct mbuf *) NULL);
+	if (size + sizeof(*cp) > MLEN) {
+		MCLGET(m, M_DONTWAIT);
+		if ((m->m_flags & M_EXT) == 0) {
+			m_free(m);
+			return NULL;
+		}
+	}
+	cp = mtod(m, struct cmsghdr *);
+	bcopy(p, CMSG_DATA(cp), size);
+	size += sizeof(*cp);
+	m->m_len = size;
+	cp->cmsg_len = size;
+	cp->cmsg_level = level;
+	cp->cmsg_type = type;
+	return (m);
+}
diff --git a/sys/kern/uipc_syscalls.c b/sys/kern/uipc_syscalls.c
index 555cddb2b52..f5103797f94 100644
--- a/sys/kern/uipc_syscalls.c
+++ b/sys/kern/uipc_syscalls.c
@@ -1,4 +1,4 @@
-/*	$OpenBSD: uipc_syscalls.c,v 1.28 1999/07/13 15:17:51 provos Exp $	*/
+/*	$OpenBSD: uipc_syscalls.c,v 1.29 1999/12/08 06:50:17 itojun Exp $	*/
 /*	$NetBSD: uipc_syscalls.c,v 1.19 1996/02/09 19:00:48 christos Exp $	*/
 
 /*
@@ -718,12 +718,25 @@ recvit(p, s, mp, namelenp, retsize)
 		if (len <= 0 || control == 0)
 			len = 0;
 		else {
-			if (len >= control->m_len)
-				len = control->m_len;
-			else
-				mp->msg_flags |= MSG_CTRUNC;
-			error = copyout((caddr_t)mtod(control, caddr_t),
-			    (caddr_t)mp->msg_control, (unsigned)len);
+			struct mbuf *m = control;
+			caddr_t p = (caddr_t)mp->msg_control;
+
+			do {
+				i = m->m_len;
+				if (len < i) {
+					mp->msg_flags |= MSG_CTRUNC;
+					i = len;
+				}
+				error = copyout(mtod(m, caddr_t), p,
+				    (unsigned)i);
+				if (m->m_next)
+					i = ALIGN(i);
+				p += i;
+				len -= i;
+				if (error != 0 || len <= 0)
+					break;
+			} while ((m = m->m_next) != NULL);
+			len = p - (caddr_t)mp->msg_control;
 		}
 		mp->msg_controllen = len;
 	}
@@ -774,10 +787,17 @@ sys_setsockopt(p, v, retval)
 
 	if ((error = getsock(p->p_fd, SCARG(uap, s), &fp)) != 0)
 		return (error);
-	if (SCARG(uap, valsize) > MLEN)
+	if (SCARG(uap, valsize) > MCLBYTES)
 		return (EINVAL);
 	if (SCARG(uap, val)) {
 		m = m_get(M_WAIT, MT_SOOPTS);
+		if (SCARG(uap, valsize) > MLEN) {
+			MCLGET(m, M_DONTWAIT);
+			if ((m->m_flags & M_EXT) == 0) {
+				m_freem(m);
+				return (ENOBUFS);
+			}
+		}
 		if (m == NULL)
 			return (ENOBUFS);
 		error = copyin(SCARG(uap, val), mtod(m, caddr_t),