Kill custom in_matroute() radix mathing function removing one rte mutex lock.

Initially in_matrote() in_clsroute() in their current state was introduced by
r4105 20 years ago. Instead of deleting inactive routes immediately, we kept them
in route table, setting RTPRF_OURS flag and some expire time. After that, either
GC came or RTPRF_OURS got removed on first-packet. It was a good solution
in that days (and probably another decade after that) to keep TCP metrics.
However, after moving metrics to TCP hostcache in r122922, most of in_rmx
functionality became unused. It might had been used for flushing icmp-originated
routes before rte mutexes/refcounting, but I'm not sure about that.

So it looks like this is nearly impossible to make GC do its work nowadays:

in_rtkill() ignores non-RTPRF_OURS routes.
route can only become RTPRF_OURS after dropping last reference via rtfree()
which calls in_clsroute(), which, it turn, ignores UP and non-RTF_DYNAMIC routes.

Dynamic routes can still be installed via received redirect, but they
have default lifetime (no specific rt_expire) and no one has another trie walker
to call RTFREE() on them.

So, the changelist:
* remove custom rnh_match / rnh_close matching function.
* remove all GC functions
* partially revert r256695 (proto3 is no more used inside kernel,
  it is not possible to use rt_expire from user point of view, proto3 support
  is not complete)
* Finish r241884 (similar to this commit) and remove remaining IPv6 parts

MFC after:	1 month

7 files changed, 9 insertions, 302 deletions

diff --git a/sys/netinet/in.h b/sys/netinet/in.h
index f2dbce2..1f79761 100644
--- a/sys/netinet/in.h
+++ b/sys/netinet/in.h
@@ -619,9 +619,9 @@ int	getsourcefilter(int, uint32_t, struct sockaddr *, socklen_t,
 #ifdef notyet
 #define	IPCTL_DEFMTU		4	/* default MTU */
 #endif
-#define	IPCTL_RTEXPIRE		5	/* cloned route expiration time */
-#define	IPCTL_RTMINEXPIRE	6	/* min value for expiration time */
-#define	IPCTL_RTMAXCACHE	7	/* trigger level for dynamic expire */
+/*	IPCTL_RTEXPIRE		5	deprecated */
+/*	IPCTL_RTMINEXPIRE	6	deprecated */
+/*	IPCTL_RTMAXCACHE	7	deprecated */
 #define	IPCTL_SOURCEROUTE	8	/* may perform source routes */
 #define	IPCTL_DIRECTEDBROADCAST	9	/* may re-broadcast received packets */
 #define	IPCTL_INTRQMAXLEN	10	/* max length of netisr queue */
diff --git a/sys/netinet/in_rmx.c b/sys/netinet/in_rmx.c
index a48c9d8..a53a7ac 100644
--- a/sys/netinet/in_rmx.c
+++ b/sys/netinet/in_rmx.c
@@ -36,8 +36,6 @@ __FBSDID("$FreeBSD$");
 #include <sys/sysctl.h>
 #include <sys/socket.h>
 #include <sys/mbuf.h>
-#include <sys/syslog.h>
-#include <sys/callout.h>
 
 #include <net/if.h>
 #include <net/if_var.h>
@@ -55,8 +53,6 @@ extern int	in_inithead(void **head, int off);
 extern int	in_detachhead(void **head, int off);
 #endif
 
-#define RTPRF_OURS		RTF_PROTO3	/* set on routes we manage */
-
 /*
  * Do what we need to do when inserting a route.
  */
@@ -110,238 +106,6 @@ in_addroute(void *v_arg, void *n_arg, struct radix_node_head *head,
 	return (rn_addroute(v_arg, n_arg, head, treenodes));
 }
 
-/*
- * This code is the inverse of in_clsroute: on first reference, if we
- * were managing the route, stop doing so and set the expiration timer
- * back off again.
- */
-static struct radix_node *
-in_matroute(void *v_arg, struct radix_node_head *head)
-{
-	struct radix_node *rn = rn_match(v_arg, head);
-	struct rtentry *rt = (struct rtentry *)rn;
-
-	if (rt) {
-		RT_LOCK(rt);
-		if (rt->rt_flags & RTPRF_OURS) {
-			rt->rt_flags &= ~RTPRF_OURS;
-			rt->rt_expire = 0;
-		}
-		RT_UNLOCK(rt);
-	}
-	return rn;
-}
-
-static VNET_DEFINE(int, rtq_reallyold) = 60*60; /* one hour is "really old" */
-#define	V_rtq_reallyold		VNET(rtq_reallyold)
-SYSCTL_INT(_net_inet_ip, IPCTL_RTEXPIRE, rtexpire, CTLFLAG_VNET | CTLFLAG_RW,
-    &VNET_NAME(rtq_reallyold), 0,
-    "Default expiration time on dynamically learned routes");
-
-/* never automatically crank down to less */
-static VNET_DEFINE(int, rtq_minreallyold) = 10;
-#define	V_rtq_minreallyold	VNET(rtq_minreallyold)
-SYSCTL_INT(_net_inet_ip, IPCTL_RTMINEXPIRE, rtminexpire, CTLFLAG_VNET | CTLFLAG_RW,
-    &VNET_NAME(rtq_minreallyold), 0,
-    "Minimum time to attempt to hold onto dynamically learned routes");
-
-/* 128 cached routes is "too many" */
-static VNET_DEFINE(int, rtq_toomany) = 128;
-#define	V_rtq_toomany		VNET(rtq_toomany)
-SYSCTL_INT(_net_inet_ip, IPCTL_RTMAXCACHE, rtmaxcache, CTLFLAG_VNET | CTLFLAG_RW,
-    &VNET_NAME(rtq_toomany), 0,
-    "Upper limit on dynamically learned routes");
-
-/*
- * On last reference drop, mark the route as belong to us so that it can be
- * timed out.
- */
-static void
-in_clsroute(struct radix_node *rn, struct radix_node_head *head)
-{
-	struct rtentry *rt = (struct rtentry *)rn;
-
-	RT_LOCK_ASSERT(rt);
-
-	if (!(rt->rt_flags & RTF_UP))
-		return;			/* prophylactic measures */
-
-	if (rt->rt_flags & RTPRF_OURS)
-		return;
-
-	if (!(rt->rt_flags & RTF_DYNAMIC))
-		return;
-
-	/*
-	 * If rtq_reallyold is 0, just delete the route without
-	 * waiting for a timeout cycle to kill it.
-	 */
-	if (V_rtq_reallyold != 0) {
-		rt->rt_flags |= RTPRF_OURS;
-		rt->rt_expire = time_uptime + V_rtq_reallyold;
-	} else
-		rt_expunge(head, rt);
-}
-
-struct rtqk_arg {
-	struct radix_node_head *rnh;
-	int draining;
-	int killed;
-	int found;
-	int updating;
-	time_t nextstop;
-};
-
-/*
- * Get rid of old routes.  When draining, this deletes everything, even when
- * the timeout is not expired yet.  When updating, this makes sure that
- * nothing has a timeout longer than the current value of rtq_reallyold.
- */
-static int
-in_rtqkill(struct radix_node *rn, void *rock)
-{
-	struct rtqk_arg *ap = rock;
-	struct rtentry *rt = (struct rtentry *)rn;
-	int err;
-
-	RADIX_NODE_HEAD_WLOCK_ASSERT(ap->rnh);
-
-	if (rt->rt_flags & RTPRF_OURS) {
-		ap->found++;
-
-		if (ap->draining || rt->rt_expire <= time_uptime) {
-			if (rt->rt_refcnt > 0)
-				panic("rtqkill route really not free");
-
-			err = in_rtrequest(RTM_DELETE,
-					(struct sockaddr *)rt_key(rt),
-					rt->rt_gateway, rt_mask(rt),
-					rt->rt_flags | RTF_RNH_LOCKED, 0,
-					rt->rt_fibnum);
-			if (err) {
-				log(LOG_WARNING, "in_rtqkill: error %d\n", err);
-			} else {
-				ap->killed++;
-			}
-		} else {
-			if (ap->updating &&
-			    (rt->rt_expire - time_uptime > V_rtq_reallyold))
-				rt->rt_expire = time_uptime + V_rtq_reallyold;
-			ap->nextstop = lmin(ap->nextstop, rt->rt_expire);
-		}
-	}
-
-	return 0;
-}
-
-#define RTQ_TIMEOUT	60*10	/* run no less than once every ten minutes */
-static VNET_DEFINE(int, rtq_timeout) = RTQ_TIMEOUT;
-static VNET_DEFINE(struct callout, rtq_timer);
-
-#define	V_rtq_timeout		VNET(rtq_timeout)
-#define	V_rtq_timer		VNET(rtq_timer)
-
-static void in_rtqtimo_one(void *rock);
-
-static void
-in_rtqtimo(void *rock)
-{
-	CURVNET_SET((struct vnet *) rock);
-	int fibnum;
-	void *newrock;
-	struct timeval atv;
-
-	for (fibnum = 0; fibnum < rt_numfibs; fibnum++) {
-		newrock = rt_tables_get_rnh(fibnum, AF_INET);
-		if (newrock != NULL)
-			in_rtqtimo_one(newrock);
-	}
-	atv.tv_usec = 0;
-	atv.tv_sec = V_rtq_timeout;
-	callout_reset(&V_rtq_timer, tvtohz(&atv), in_rtqtimo, rock);
-	CURVNET_RESTORE();
-}
-
-static void
-in_rtqtimo_one(void *rock)
-{
-	struct radix_node_head *rnh = rock;
-	struct rtqk_arg arg;
-	static time_t last_adjusted_timeout = 0;
-
-	arg.found = arg.killed = 0;
-	arg.rnh = rnh;
-	arg.nextstop = time_uptime + V_rtq_timeout;
-	arg.draining = arg.updating = 0;
-	RADIX_NODE_HEAD_LOCK(rnh);
-	rnh->rnh_walktree(rnh, in_rtqkill, &arg);
-	RADIX_NODE_HEAD_UNLOCK(rnh);
-
-	/*
-	 * Attempt to be somewhat dynamic about this:
-	 * If there are ``too many'' routes sitting around taking up space,
-	 * then crank down the timeout, and see if we can't make some more
-	 * go away.  However, we make sure that we will never adjust more
-	 * than once in rtq_timeout seconds, to keep from cranking down too
-	 * hard.
-	 */
-	if ((arg.found - arg.killed > V_rtq_toomany) &&
-	    (time_uptime - last_adjusted_timeout >= V_rtq_timeout) &&
-	    V_rtq_reallyold > V_rtq_minreallyold) {
-		V_rtq_reallyold = 2 * V_rtq_reallyold / 3;
-		if (V_rtq_reallyold < V_rtq_minreallyold) {
-			V_rtq_reallyold = V_rtq_minreallyold;
-		}
-
-		last_adjusted_timeout = time_uptime;
-#ifdef DIAGNOSTIC
-		log(LOG_DEBUG, "in_rtqtimo: adjusted rtq_reallyold to %d\n",
-		    V_rtq_reallyold);
-#endif
-		arg.found = arg.killed = 0;
-		arg.updating = 1;
-		RADIX_NODE_HEAD_LOCK(rnh);
-		rnh->rnh_walktree(rnh, in_rtqkill, &arg);
-		RADIX_NODE_HEAD_UNLOCK(rnh);
-	}
-
-}
-
-void
-in_rtqdrain(void)
-{
-	VNET_ITERATOR_DECL(vnet_iter);
-	struct radix_node_head *rnh;
-	struct rtqk_arg arg;
-	int 	fibnum;
-
-	VNET_LIST_RLOCK_NOSLEEP();
-	VNET_FOREACH(vnet_iter) {
-		CURVNET_SET(vnet_iter);
-
-		for ( fibnum = 0; fibnum < rt_numfibs; fibnum++) {
-			rnh = rt_tables_get_rnh(fibnum, AF_INET);
-			arg.found = arg.killed = 0;
-			arg.rnh = rnh;
-			arg.nextstop = 0;
-			arg.draining = 1;
-			arg.updating = 0;
-			RADIX_NODE_HEAD_LOCK(rnh);
-			rnh->rnh_walktree(rnh, in_rtqkill, &arg);
-			RADIX_NODE_HEAD_UNLOCK(rnh);
-		}
-		CURVNET_RESTORE();
-	}
-	VNET_LIST_RUNLOCK_NOSLEEP();
-}
-
-void
-in_setmatchfunc(struct radix_node_head *rnh, int val)
-{
-
-	rnh->rnh_matchaddr = (val != 0) ? rn_match : in_matroute;
-}
-
 static int _in_rt_was_here;
 /*
  * Initialize our routing tree.
@@ -358,11 +122,7 @@ in_inithead(void **head, int off)
 	RADIX_NODE_HEAD_LOCK_INIT(rnh);
 
 	rnh->rnh_addaddr = in_addroute;
-	in_setmatchfunc(rnh, V_drop_redirect);
-	rnh->rnh_close = in_clsroute;
 	if (_in_rt_was_here == 0 ) {
-		callout_init(&V_rtq_timer, CALLOUT_MPSAFE);
-		callout_reset(&V_rtq_timer, 1, in_rtqtimo, curvnet);
 		_in_rt_was_here = 1;
 	}
 	return 1;
@@ -373,7 +133,6 @@ int
 in_detachhead(void **head, int off)
 {
 
-	callout_drain(&V_rtq_timer);
 	return (1);
 }
 #endif
diff --git a/sys/netinet/in_var.h b/sys/netinet/in_var.h
index 6f0dcbf..16edeb1 100644
--- a/sys/netinet/in_var.h
+++ b/sys/netinet/in_var.h
@@ -407,7 +407,6 @@ int	in_leavegroup_locked(struct in_multi *,
 	    /*const*/ struct in_mfilter *);
 int	in_control(struct socket *, u_long, caddr_t, struct ifnet *,
 	    struct thread *);
-void	in_rtqdrain(void);
 int	in_addprefix(struct in_ifaddr *, int);
 int	in_scrubprefix(struct in_ifaddr *, u_int);
 void	ip_input(struct mbuf *);
@@ -426,7 +425,6 @@ void	 in_rtredirect(struct sockaddr *, struct sockaddr *,
 	    struct sockaddr *, int, struct sockaddr *, u_int);
 int	 in_rtrequest(int, struct sockaddr *,
 	    struct sockaddr *, struct sockaddr *, int, struct rtentry **, u_int);
-void	in_setmatchfunc(struct radix_node_head *, int);
 
 #if 0
 int	 in_rt_getifa(struct rt_addrinfo *, u_int fibnum);
diff --git a/sys/netinet/ip_icmp.c b/sys/netinet/ip_icmp.c
index 25ccb4f..845c6ec 100644
--- a/sys/netinet/ip_icmp.c
+++ b/sys/netinet/ip_icmp.c
@@ -115,6 +115,9 @@ SYSCTL_UINT(_net_inet_icmp, OID_AUTO, maskfake, CTLFLAG_VNET | CTLFLAG_RW,
 	"Fake reply to ICMP Address Mask Request packets.");
 
 VNET_DEFINE(int, drop_redirect) = 0;
+#define	V_drop_redirect			VNET(drop_redirect)
+SYSCTL_INT(_net_inet_icmp, OID_AUTO, drop_redirect, CTLFLAG_VNET | CTLFLAG_RW,
+	&VNET_NAME(drop_redirect), 0, "Ignore ICMP redirects");
 
 static VNET_DEFINE(int, log_redirect) = 0;
 #define	V_log_redirect			VNET(log_redirect)
@@ -163,39 +166,6 @@ static void	icmp_send(struct mbuf *, struct mbuf *);
 
 extern	struct protosw inetsw[];
 
-static int
-sysctl_net_icmp_drop_redir(SYSCTL_HANDLER_ARGS)
-{
-	int error, new;
-	int i;
-	struct radix_node_head *rnh;
-
-	new = V_drop_redirect;
-	error = sysctl_handle_int(oidp, &new, 0, req);
-	if (error == 0 && req->newptr) {
-		new = (new != 0) ? 1 : 0;
-
-		if (new == V_drop_redirect)
-			return (0);
-
-		for (i = 0; i < rt_numfibs; i++) {
-			if ((rnh = rt_tables_get_rnh(i, AF_INET)) == NULL)
-				continue;
-			RADIX_NODE_HEAD_LOCK(rnh);
-			in_setmatchfunc(rnh, new);
-			RADIX_NODE_HEAD_UNLOCK(rnh);
-		}
-		
-		V_drop_redirect = new;
-	}
-
-	return (error);
-}
-
-SYSCTL_PROC(_net_inet_icmp, OID_AUTO, drop_redirect,
-    CTLFLAG_VNET | CTLTYPE_INT | CTLFLAG_RW, 0, 0,
-    sysctl_net_icmp_drop_redir, "I", "Ignore ICMP redirects");
-
 /*
  * Kernel module interface for updating icmpstat.  The argument is an index
  * into icmpstat treated as an array of u_long.  While this encodes the
diff --git a/sys/netinet/ip_input.c b/sys/netinet/ip_input.c
index 6f48d93..d0229b2 100644
--- a/sys/netinet/ip_input.c
+++ b/sys/netinet/ip_input.c
@@ -1330,7 +1330,6 @@ ip_drain(void)
 	}
 	IPQ_UNLOCK();
 	VNET_LIST_RUNLOCK_NOSLEEP();
-	in_rtqdrain();
 }
 
 /*
diff --git a/sys/netinet6/in6.h b/sys/netinet6/in6.h
index 7187aec..95b4a0c 100644
--- a/sys/netinet6/in6.h
+++ b/sys/netinet6/in6.h
@@ -593,9 +593,9 @@ struct ip6_mtuinfo {
 #define IPV6CTL_MAPPED_ADDR	23
 #endif
 #define IPV6CTL_V6ONLY		24
-#define IPV6CTL_RTEXPIRE	25	/* cloned route expiration time */
-#define IPV6CTL_RTMINEXPIRE	26	/* min value for expiration time */
-#define IPV6CTL_RTMAXCACHE	27	/* trigger level for dynamic expire */
+/*	IPV6CTL_RTEXPIRE	25	deprecated */
+/*	IPV6CTL_RTMINEXPIRE	26	deprecated */
+/*	IPV6CTL_RTMAXCACHE	27	deprecated */
 
 #define IPV6CTL_USETEMPADDR	32	/* use temporary addresses (RFC3041) */
 #define IPV6CTL_TEMPPLTIME	33	/* preferred lifetime for tmpaddrs */
diff --git a/sys/netinet6/in6_rmx.c b/sys/netinet6/in6_rmx.c
index c96db6f..1403647 100644
--- a/sys/netinet6/in6_rmx.c
+++ b/sys/netinet6/in6_rmx.c
@@ -66,7 +66,6 @@ __FBSDID("$FreeBSD$");
 #include <sys/systm.h>
 #include <sys/kernel.h>
 #include <sys/lock.h>
-#include <sys/sysctl.h>
 #include <sys/queue.h>
 #include <sys/socket.h>
 #include <sys/socketvar.h>
@@ -179,24 +178,6 @@ in6_addroute(void *v_arg, void *n_arg, struct radix_node_head *head,
 	return (ret);
 }
 
-SYSCTL_DECL(_net_inet6_ip6);
-
-static VNET_DEFINE(int, rtq_toomany6) = 128;
-	/* 128 cached routes is ``too many'' */
-#define	V_rtq_toomany6			VNET(rtq_toomany6)
-SYSCTL_INT(_net_inet6_ip6, IPV6CTL_RTMAXCACHE, rtmaxcache, CTLFLAG_VNET | CTLFLAG_RW,
-    &VNET_NAME(rtq_toomany6) , 0, "");
-
-struct rtqk_arg {
-	struct radix_node_head *rnh;
-	int mode;
-	int updating;
-	int draining;
-	int killed;
-	int found;
-	time_t nextstop;
-};
-
 /*
  * Age old PMTUs.
  */