Merge branch 'rt6_pmtu'

Martin KaFai Lau says:

====================
ipv6: Stop /128 route from disappearing after pmtu update

The series is separated from another patch series,
'ipv6: Only create RTF_CACHE route after encountering pmtu exception',
which can be found here:
http://thread.gmane.org/gmane.linux.network/359140

This series focus on fixing the /128 route issues.  It is currently targeted
for net-next due to the number of code churn but it is also applicable
to net (should be without conflict).  The original reported problem can be
found here:
http://thread.gmane.org/gmane.linux.network/348138

Patch 01 and 02 are to prepare the fib6 search to expect both the
RTF_CACHE clone and its original route exist at the same fib6_node.

Patch 03 fixes the /128 route disappearing bug.

Patch 04 and 05 stop rt6_info from using the inet_peer's metrics to
avoid the /128 routes (like the /128 clone and its original route)
from stepping on each others' metrics.

The second patch is by 'Steffen Klassert <steffen.klassert@secunet.com>'
which I pulled off from netdev.  The third patch is also mostly by
Steffen with one minor optimization.

Many thanks to Hannes Frederic Sowa <hannes@stressinduktion.org> on
reviewing the patches and giving advice.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 93 insertions, 99 deletions

diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 37b70e82bff8..21c2c818df3b 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2121,6 +2121,8 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
 	fn = fib6_locate(&table->tb6_root, pfx, plen, NULL, 0);
 	if (!fn)
 		goto out;
+
+	noflags |= RTF_CACHE;
 	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
 		if (rt->dst.dev->ifindex != dev->ifindex)
 			continue;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 5c48293ff062..352271154ddb 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -92,6 +92,7 @@ static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 					   struct sk_buff *skb, u32 mtu);
 static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
+static void		rt6_dst_from_metrics_check(struct rt6_info *rt);
 static int rt6_score_route(struct rt6_info *rt, int oif, int strict);
 
 #ifdef CONFIG_IPV6_ROUTE_INFO
@@ -104,65 +105,14 @@ static struct rt6_info *rt6_get_route_info(struct net *net,
 					   const struct in6_addr *gwaddr, int ifindex);
 #endif
 
-static void rt6_bind_peer(struct rt6_info *rt, int create)
-{
-	struct inet_peer_base *base;
-	struct inet_peer *peer;
-
-	base = inetpeer_base_ptr(rt->_rt6i_peer);
-	if (!base)
-		return;
-
-	peer = inet_getpeer_v6(base, &rt->rt6i_dst.addr, create);
-	if (peer) {
-		if (!rt6_set_peer(rt, peer))
-			inet_putpeer(peer);
-	}
-}
-
-static struct inet_peer *__rt6_get_peer(struct rt6_info *rt, int create)
-{
-	if (rt6_has_peer(rt))
-		return rt6_peer_ptr(rt);
-
-	rt6_bind_peer(rt, create);
-	return (rt6_has_peer(rt) ? rt6_peer_ptr(rt) : NULL);
-}
-
-static struct inet_peer *rt6_get_peer_create(struct rt6_info *rt)
-{
-	return __rt6_get_peer(rt, 1);
-}
-
 static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old)
 {
-	struct rt6_info *rt = (struct rt6_info *) dst;
-	struct inet_peer *peer;
-	u32 *p = NULL;
+	struct rt6_info *rt = (struct rt6_info *)dst;
 
-	if (!(rt->dst.flags & DST_HOST))
+	if (rt->rt6i_flags & RTF_CACHE)
+		return NULL;
+	else
 		return dst_cow_metrics_generic(dst, old);
-
-	peer = rt6_get_peer_create(rt);
-	if (peer) {
-		u32 *old_p = __DST_METRICS_PTR(old);
-		unsigned long prev, new;
-
-		p = peer->metrics;
-		if (inet_metrics_new(peer) ||
-		    (old & DST_METRICS_FORCE_OVERWRITE))
-			memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
-
-		new = (unsigned long) p;
-		prev = cmpxchg(&dst->_metrics, old, new);
-
-		if (prev != old) {
-			p = __DST_METRICS_PTR(prev);
-			if (prev & DST_METRICS_READ_ONLY)
-				p = NULL;
-		}
-	}
-	return p;
 }
 
 static inline const void *choose_neigh_daddr(struct rt6_info *rt,
@@ -311,7 +261,6 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 		struct dst_entry *dst = &rt->dst;
 
 		memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
-		rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
 		INIT_LIST_HEAD(&rt->rt6i_siblings);
 	}
 	return rt;
@@ -323,8 +272,7 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 	struct inet6_dev *idev = rt->rt6i_idev;
 	struct dst_entry *from = dst->from;
 
-	if (!(rt->dst.flags & DST_HOST))
-		dst_destroy_metrics_generic(dst);
+	dst_destroy_metrics_generic(dst);
 
 	if (idev) {
 		rt->rt6i_idev = NULL;
@@ -333,11 +281,6 @@ static void ip6_dst_destroy(struct dst_entry *dst)
 
 	dst->from = NULL;
 	dst_release(from);
-
-	if (rt6_has_peer(rt)) {
-		struct inet_peer *peer = rt6_peer_ptr(rt);
-		inet_putpeer(peer);
-	}
 }
 
 static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
@@ -652,15 +595,33 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
 				     u32 metric, int oif, int strict,
 				     bool *do_rr)
 {
-	struct rt6_info *rt, *match;
+	struct rt6_info *rt, *match, *cont;
 	int mpri = -1;
 
 	match = NULL;
-	for (rt = rr_head; rt && rt->rt6i_metric == metric;
-	     rt = rt->dst.rt6_next)
+	cont = NULL;
+	for (rt = rr_head; rt; rt = rt->dst.rt6_next) {
+		if (rt->rt6i_metric != metric) {
+			cont = rt;
+			break;
+		}
+
 		match = find_match(rt, oif, strict, &mpri, match, do_rr);
-	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
-	     rt = rt->dst.rt6_next)
+	}
+
+	for (rt = fn->leaf; rt && rt != rr_head; rt = rt->dst.rt6_next) {
+		if (rt->rt6i_metric != metric) {
+			cont = rt;
+			break;
+		}
+
+		match = find_match(rt, oif, strict, &mpri, match, do_rr);
+	}
+
+	if (match || !cont)
+		return match;
+
+	for (rt = cont; rt; rt = rt->dst.rt6_next)
 		match = find_match(rt, oif, strict, &mpri, match, do_rr);
 
 	return match;
@@ -959,7 +920,7 @@ redo_rt6_select:
 
 	if (!(rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)))
 		nrt = rt6_alloc_cow(rt, &fl6->daddr, &fl6->saddr);
-	else if (!(rt->dst.flags & DST_HOST))
+	else if (!(rt->dst.flags & DST_HOST) || !(rt->dst.flags & RTF_LOCAL))
 		nrt = rt6_alloc_clone(rt, &fl6->daddr);
 	else
 		goto out2;
@@ -985,6 +946,7 @@ redo_rt6_select:
 	goto redo_fib6_lookup_lock;
 
 out2:
+	rt6_dst_from_metrics_check(rt);
 	rt->dst.lastuse = jiffies;
 	rt->dst.__use++;
 
@@ -1059,7 +1021,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
 		new = &rt->dst;
 
 		memset(new + 1, 0, sizeof(*rt) - sizeof(*new));
-		rt6_init_peer(rt, net->ipv6.peers);
 
 		new->__use = 1;
 		new->input = dst_discard;
@@ -1093,6 +1054,13 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori
  *	Destination cache support functions
  */
 
+static void rt6_dst_from_metrics_check(struct rt6_info *rt)
+{
+	if (rt->dst.from &&
+	    dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(rt->dst.from))
+		dst_init_metrics(&rt->dst, dst_metrics_ptr(rt->dst.from), true);
+}
+
 static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 {
 	struct rt6_info *rt;
@@ -1109,6 +1077,8 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	if (rt6_check_expired(rt))
 		return NULL;
 
+	rt6_dst_from_metrics_check(rt);
+
 	return dst;
 }
 
@@ -1154,14 +1124,14 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
 	struct rt6_info *rt6 = (struct rt6_info *)dst;
 
 	dst_confirm(dst);
-	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
+	if (mtu < dst_mtu(dst) && (rt6->rt6i_flags & RTF_CACHE)) {
 		struct net *net = dev_net(dst->dev);
 
 		rt6->rt6i_flags |= RTF_MODIFIED;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 
-		dst_metric_set(dst, RTAX_MTU, mtu);
+		rt6->rt6i_pmtu = mtu;
 		rt6_update_expires(rt6, net->ipv6.sysctl.ip6_rt_mtu_expires);
 	}
 }
@@ -1341,12 +1311,17 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 
 static unsigned int ip6_mtu(const struct dst_entry *dst)
 {
+	const struct rt6_info *rt = (const struct rt6_info *)dst;
+	unsigned int mtu = rt->rt6i_pmtu;
 	struct inet6_dev *idev;
-	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
 
 	if (mtu)
 		goto out;
 
+	mtu = dst_metric_raw(dst, RTAX_MTU);
+	if (mtu)
+		goto out;
+
 	mtu = IPV6_MIN_MTU;
 
 	rcu_read_lock();
@@ -1590,10 +1565,8 @@ int ip6_route_add(struct fib6_config *cfg)
 
 	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
 	rt->rt6i_dst.plen = cfg->fc_dst_len;
-	if (rt->rt6i_dst.plen == 128) {
+	if (rt->rt6i_dst.plen == 128)
 		rt->dst.flags |= DST_HOST;
-		dst_metrics_set_force_overwrite(&rt->dst);
-	}
 
 #ifdef CONFIG_IPV6_SUBTREES
 	ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
@@ -1785,6 +1758,9 @@ static int ip6_route_del(struct fib6_config *cfg)
 
 	if (fn) {
 		for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
+			if ((rt->rt6i_flags & RTF_CACHE) &&
+			    !(cfg->fc_flags & RTF_CACHE))
+				continue;
 			if (cfg->fc_ifindex &&
 			    (!rt->dst.dev ||
 			     rt->dst.dev->ifindex != cfg->fc_ifindex))
@@ -1926,12 +1902,27 @@ out:
  *	Misc support functions
  */
 
+static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from)
+{
+	BUG_ON(from->dst.from);
+
+	rt->rt6i_flags &= ~RTF_EXPIRES;
+	dst_hold(&from->dst);
+	rt->dst.from = &from->dst;
+	dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true);
+}
+
 static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 				    const struct in6_addr *dest)
 {
 	struct net *net = dev_net(ort->dst.dev);
-	struct rt6_info *rt = ip6_dst_alloc(net, ort->dst.dev, 0,
-					    ort->rt6i_table);
+	struct rt6_info *rt;
+
+	if (ort->rt6i_flags & RTF_CACHE)
+		ort = (struct rt6_info *)ort->dst.from;
+
+	rt = ip6_dst_alloc(net, ort->dst.dev, 0,
+			   ort->rt6i_table);
 
 	if (rt) {
 		rt->dst.input = ort->dst.input;
@@ -1940,7 +1931,6 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
 
 		rt->rt6i_dst.addr = *dest;
 		rt->rt6i_dst.plen = 128;
-		dst_copy_metrics(&rt->dst, &ort->dst);
 		rt->dst.error = ort->dst.error;
 		rt->rt6i_idev = ort->rt6i_idev;
 		if (rt->rt6i_idev)
@@ -2372,11 +2362,20 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
 	   PMTU discouvery.
 	 */
 	if (rt->dst.dev == arg->dev &&
-	    !dst_metric_locked(&rt->dst, RTAX_MTU) &&
-	    (dst_mtu(&rt->dst) >= arg->mtu ||
-	     (dst_mtu(&rt->dst) < arg->mtu &&
-	      dst_mtu(&rt->dst) == idev->cnf.mtu6))) {
-		dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
+	    !dst_metric_locked(&rt->dst, RTAX_MTU)) {
+		if (rt->rt6i_flags & RTF_CACHE) {
+			/* For RTF_CACHE with rt6i_pmtu == 0
+			 * (i.e. a redirected route),
+			 * the metrics of its rt->dst.from has already
+			 * been updated.
+			 */
+			if (rt->rt6i_pmtu && rt->rt6i_pmtu > arg->mtu)
+				rt->rt6i_pmtu = arg->mtu;
+		} else if (dst_mtu(&rt->dst) >= arg->mtu ||
+			   (dst_mtu(&rt->dst) < arg->mtu &&
+			    dst_mtu(&rt->dst) == idev->cnf.mtu6)) {
+			dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
+		}
 	}
 	return 0;
 }
@@ -2433,6 +2432,9 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_type == RTN_LOCAL)
 		cfg->fc_flags |= RTF_LOCAL;
 
+	if (rtm->rtm_flags & RTM_F_CLONED)
+		cfg->fc_flags |= RTF_CACHE;
+
 	cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
 	cfg->fc_nlinfo.nlh = nlh;
 	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);
@@ -2603,6 +2605,7 @@ static int rt6_fill_node(struct net *net,
 			 int iif, int type, u32 portid, u32 seq,
 			 int prefix, int nowait, unsigned int flags)
 {
+	u32 metrics[RTAX_MAX];
 	struct rtmsg *rtm;
 	struct nlmsghdr *nlh;
 	long expires;
@@ -2716,7 +2719,10 @@ static int rt6_fill_node(struct net *net,
 			goto nla_put_failure;
 	}
 
-	if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
+	memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics));
+	if (rt->rt6i_pmtu)
+		metrics[RTAX_MTU - 1] = rt->rt6i_pmtu;
+	if (rtnetlink_put_metrics(skb, metrics) < 0)
 		goto nla_put_failure;
 
 	if (rt->rt6i_flags & RTF_GATEWAY) {
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index f337a908a76a..6ae256b4c55a 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -71,13 +71,6 @@ static int xfrm6_get_tos(const struct flowi *fl)
 	return 0;
 }
 
-static void xfrm6_init_dst(struct net *net, struct xfrm_dst *xdst)
-{
-	struct rt6_info *rt = (struct rt6_info *)xdst;
-
-	rt6_init_peer(rt, net->ipv6.peers);
-}
-
 static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst,
 			   int nfheader_len)
 {
@@ -106,8 +99,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
 		return -ENODEV;
 	}
 
-	rt6_transfer_peer(&xdst->u.rt6, rt);
-
 	/* Sheit... I remember I did this right. Apparently,
 	 * it was magically lost, so this code needs audit */
 	xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
@@ -255,10 +246,6 @@ static void xfrm6_dst_destroy(struct dst_entry *dst)
 	if (likely(xdst->u.rt6.rt6i_idev))
 		in6_dev_put(xdst->u.rt6.rt6i_idev);
 	dst_destroy_metrics_generic(dst);
-	if (rt6_has_peer(&xdst->u.rt6)) {
-		struct inet_peer *peer = rt6_peer_ptr(&xdst->u.rt6);
-		inet_putpeer(peer);
-	}
 	xfrm_dst_destroy(xdst);
 }
 
@@ -308,7 +295,6 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
 	.get_saddr =		xfrm6_get_saddr,
 	.decode_session =	_decode_session6,
 	.get_tos =		xfrm6_get_tos,
-	.init_dst =		xfrm6_init_dst,
 	.init_path =		xfrm6_init_path,
 	.fill_dst =		xfrm6_fill_dst,
 	.blackhole_route =	ip6_blackhole_route,