1 files changed, 225 insertions, 83 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 155138d8ec8b..94cdbc55ca7e 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -91,6 +91,7 @@
 #include <linux/rcupdate.h>
 #include <linux/times.h>
 #include <linux/slab.h>
+#include <linux/prefetch.h>
 #include <net/dst.h>
 #include <net/net_namespace.h>
 #include <net/protocol.h>
@@ -112,7 +113,7 @@
 #include <net/secure_seq.h>
 
 #define RT_FL_TOS(oldflp4) \
-    ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)))
+	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
 
 #define IP_MAX_MTU	0xFFF0
 
@@ -120,6 +121,7 @@
 
 static int ip_rt_max_size;
 static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
+static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_redirect_number __read_mostly	= 9;
 static int ip_rt_redirect_load __read_mostly	= HZ / 50;
@@ -131,6 +133,10 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 static int rt_chain_length_max __read_mostly	= 20;
+static int redirect_genid;
+
+static struct delayed_work expires_work;
+static unsigned long expires_ljiffies;
 
 /*
  *	Interface to generic destination cache.
@@ -138,7 +144,7 @@ static int rt_chain_length_max __read_mostly	= 20;
 
 static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
 static unsigned int	 ipv4_default_advmss(const struct dst_entry *dst);
-static unsigned int	 ipv4_default_mtu(const struct dst_entry *dst);
+static unsigned int	 ipv4_mtu(const struct dst_entry *dst);
 static void		 ipv4_dst_destroy(struct dst_entry *dst);
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
@@ -193,7 +199,7 @@ static struct dst_ops ipv4_dst_ops = {
 	.gc =			rt_garbage_collect,
 	.check =		ipv4_dst_check,
 	.default_advmss =	ipv4_default_advmss,
-	.default_mtu =		ipv4_default_mtu,
+	.mtu =			ipv4_mtu,
 	.cow_metrics =		ipv4_cow_metrics,
 	.destroy =		ipv4_dst_destroy,
 	.ifdown =		ipv4_dst_ifdown,
@@ -416,9 +422,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 	else {
 		struct rtable *r = v;
 		struct neighbour *n;
-		int len;
+		int len, HHUptod;
 
+		rcu_read_lock();
 		n = dst_get_neighbour(&r->dst);
+		HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
+		rcu_read_unlock();
+
 		seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
 			      "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
 			r->dst.dev ? r->dst.dev->name : "*",
@@ -432,7 +442,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v)
 			      dst_metric(&r->dst, RTAX_RTTVAR)),
 			r->rt_key_tos,
 			-1,
-			(n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0,
+			HHUptod,
 			r->rt_spec_dst, &len);
 
 		seq_printf(seq, "%*s\n", 127 - len, "");
@@ -825,6 +835,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth)
 	return ONE;
 }
 
+static void rt_check_expire(void)
+{
+	static unsigned int rover;
+	unsigned int i = rover, goal;
+	struct rtable *rth;
+	struct rtable __rcu **rthp;
+	unsigned long samples = 0;
+	unsigned long sum = 0, sum2 = 0;
+	unsigned long delta;
+	u64 mult;
+
+	delta = jiffies - expires_ljiffies;
+	expires_ljiffies = jiffies;
+	mult = ((u64)delta) << rt_hash_log;
+	if (ip_rt_gc_timeout > 1)
+		do_div(mult, ip_rt_gc_timeout);
+	goal = (unsigned int)mult;
+	if (goal > rt_hash_mask)
+		goal = rt_hash_mask + 1;
+	for (; goal > 0; goal--) {
+		unsigned long tmo = ip_rt_gc_timeout;
+		unsigned long length;
+
+		i = (i + 1) & rt_hash_mask;
+		rthp = &rt_hash_table[i].chain;
+
+		if (need_resched())
+			cond_resched();
+
+		samples++;
+
+		if (rcu_dereference_raw(*rthp) == NULL)
+			continue;
+		length = 0;
+		spin_lock_bh(rt_hash_lock_addr(i));
+		while ((rth = rcu_dereference_protected(*rthp,
+					lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) {
+			prefetch(rth->dst.rt_next);
+			if (rt_is_expired(rth)) {
+				*rthp = rth->dst.rt_next;
+				rt_free(rth);
+				continue;
+			}
+			if (rth->dst.expires) {
+				/* Entry is expired even if it is in use */
+				if (time_before_eq(jiffies, rth->dst.expires)) {
+nofree:
+					tmo >>= 1;
+					rthp = &rth->dst.rt_next;
+					/*
+					 * We only count entries on
+					 * a chain with equal hash inputs once
+					 * so that entries for different QOS
+					 * levels, and other non-hash input
+					 * attributes don't unfairly skew
+					 * the length computation
+					 */
+					length += has_noalias(rt_hash_table[i].chain, rth);
+					continue;
+				}
+			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout))
+				goto nofree;
+
+			/* Cleanup aged off entries. */
+			*rthp = rth->dst.rt_next;
+			rt_free(rth);
+		}
+		spin_unlock_bh(rt_hash_lock_addr(i));
+		sum += length;
+		sum2 += length*length;
+	}
+	if (samples) {
+		unsigned long avg = sum / samples;
+		unsigned long sd = int_sqrt(sum2 / samples - avg*avg);
+		rt_chain_length_max = max_t(unsigned long,
+					ip_rt_gc_elasticity,
+					(avg + 4*sd) >> FRACT_BITS);
+	}
+	rover = i;
+}
+
+/*
+ * rt_worker_func() is run in process context.
+ * we call rt_check_expire() to scan part of the hash table
+ */
+static void rt_worker_func(struct work_struct *work)
+{
+	rt_check_expire();
+	schedule_delayed_work(&expires_work, ip_rt_gc_interval);
+}
+
 /*
  * Perturbation of rt_genid by a small quantity [1..256]
  * Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
@@ -837,6 +938,7 @@ static void rt_cache_invalidate(struct net *net)
 
 	get_random_bytes(&shuffle, sizeof(shuffle));
 	atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
+	redirect_genid++;
 }
 
 /*
@@ -1265,7 +1367,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
 {
 	struct rtable *rt = (struct rtable *) dst;
 
-	if (rt) {
+	if (rt && !(rt->dst.flags & DST_NOPEER)) {
 		if (rt->peer == NULL)
 			rt_bind_peer(rt, rt->rt_dst, 1);
 
@@ -1276,7 +1378,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
 			iph->id = htons(inet_getid(rt->peer, more));
 			return;
 		}
-	} else
+	} else if (!rt)
 		printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
 		       __builtin_return_address(0));
 
@@ -1304,16 +1406,40 @@ static void rt_del(unsigned hash, struct rtable *rt)
 	spin_unlock_bh(rt_hash_lock_addr(hash));
 }
 
+static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
+{
+	struct rtable *rt = (struct rtable *) dst;
+	__be32 orig_gw = rt->rt_gateway;
+	struct neighbour *n, *old_n;
+
+	dst_confirm(&rt->dst);
+
+	rt->rt_gateway = peer->redirect_learned.a4;
+
+	n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
+	if (IS_ERR(n)) {
+		rt->rt_gateway = orig_gw;
+		return;
+	}
+	old_n = xchg(&rt->dst._neighbour, n);
+	if (old_n)
+		neigh_release(old_n);
+	if (!(n->nud_state & NUD_VALID)) {
+		neigh_event_send(n, NULL);
+	} else {
+		rt->rt_flags |= RTCF_REDIRECTED;
+		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
+	}
+}
+
 /* called in rcu_read_lock() section */
 void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 		    __be32 saddr, struct net_device *dev)
 {
 	int s, i;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	struct rtable *rt;
 	__be32 skeys[2] = { saddr, 0 };
 	int    ikeys[2] = { dev->ifindex, 0 };
-	struct flowi4 fl4;
 	struct inet_peer *peer;
 	struct net *net;
 
@@ -1336,33 +1462,44 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
 			goto reject_redirect;
 	}
 
-	memset(&fl4, 0, sizeof(fl4));
-	fl4.daddr = daddr;
 	for (s = 0; s < 2; s++) {
 		for (i = 0; i < 2; i++) {
-			fl4.flowi4_oif = ikeys[i];
-			fl4.saddr = skeys[s];
-			rt = __ip_route_output_key(net, &fl4);
-			if (IS_ERR(rt))
-				continue;
-
-			if (rt->dst.error || rt->dst.dev != dev ||
-			    rt->rt_gateway != old_gw) {
-				ip_rt_put(rt);
-				continue;
-			}
-
-			if (!rt->peer)
-				rt_bind_peer(rt, rt->rt_dst, 1);
+			unsigned int hash;
+			struct rtable __rcu **rthp;
+			struct rtable *rt;
+
+			hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
+
+			rthp = &rt_hash_table[hash].chain;
+
+			while ((rt = rcu_dereference(*rthp)) != NULL) {
+				rthp = &rt->dst.rt_next;
+
+				if (rt->rt_key_dst != daddr ||
+				    rt->rt_key_src != skeys[s] ||
+				    rt->rt_oif != ikeys[i] ||
+				    rt_is_input_route(rt) ||
+				    rt_is_expired(rt) ||
+				    !net_eq(dev_net(rt->dst.dev), net) ||
+				    rt->dst.error ||
+				    rt->dst.dev != dev ||
+				    rt->rt_gateway != old_gw)
+					continue;
 
-			peer = rt->peer;
-			if (peer) {
-				peer->redirect_learned.a4 = new_gw;
-				atomic_inc(&__rt_peer_genid);
+				if (!rt->peer)
+					rt_bind_peer(rt, rt->rt_dst, 1);
+
+				peer = rt->peer;
+				if (peer) {
+					if (peer->redirect_learned.a4 != new_gw ||
+					    peer->redirect_genid != redirect_genid) {
+						peer->redirect_learned.a4 = new_gw;
+						peer->redirect_genid = redirect_genid;
+						atomic_inc(&__rt_peer_genid);
+					}
+					check_peer_redir(&rt->dst, peer);
+				}
 			}
-
-			ip_rt_put(rt);
-			return;
 		}
 	}
 	return;
@@ -1649,40 +1786,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
 	}
 }
 
-static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
-{
-	struct rtable *rt = (struct rtable *) dst;
-	__be32 orig_gw = rt->rt_gateway;
-	struct neighbour *n, *old_n;
-
-	dst_confirm(&rt->dst);
-
-	rt->rt_gateway = peer->redirect_learned.a4;
 
-	n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
-	if (IS_ERR(n))
-		return PTR_ERR(n);
-	old_n = xchg(&rt->dst._neighbour, n);
-	if (old_n)
-		neigh_release(old_n);
-	if (!n || !(n->nud_state & NUD_VALID)) {
-		if (n)
-			neigh_event_send(n, NULL);
-		rt->rt_gateway = orig_gw;
-		return -EAGAIN;
-	} else {
-		rt->rt_flags |= RTCF_REDIRECTED;
-		call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
-	}
-	return 0;
-}
-
-static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+static void ipv4_validate_peer(struct rtable *rt)
 {
-	struct rtable *rt = (struct rtable *) dst;
-
-	if (rt_is_expired(rt))
-		return NULL;
 	if (rt->rt_peer_genid != rt_peer_genid()) {
 		struct inet_peer *peer;
 
@@ -1691,17 +1797,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
 
 		peer = rt->peer;
 		if (peer) {
-			check_peer_pmtu(dst, peer);
+			check_peer_pmtu(&rt->dst, peer);
 
+			if (peer->redirect_genid != redirect_genid)
+				peer->redirect_learned.a4 = 0;
 			if (peer->redirect_learned.a4 &&
-			    peer->redirect_learned.a4 != rt->rt_gateway) {
-				if (check_peer_redir(dst, peer))
-					return NULL;
-			}
+			    peer->redirect_learned.a4 != rt->rt_gateway)
+				check_peer_redir(&rt->dst, peer);
 		}
 
 		rt->rt_peer_genid = rt_peer_genid();
 	}
+}
+
+static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
+{
+	struct rtable *rt = (struct rtable *) dst;
+
+	if (rt_is_expired(rt))
+		return NULL;
+	ipv4_validate_peer(rt);
 	return dst;
 }
 
@@ -1806,12 +1921,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 	return advmss;
 }
 
-static unsigned int ipv4_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_mtu(const struct dst_entry *dst)
 {
-	unsigned int mtu = dst->dev->mtu;
+	const struct rtable *rt = (const struct rtable *) dst;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	if (mtu && rt_is_output_route(rt))
+		return mtu;
+
+	mtu = dst->dev->mtu;
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
-		const struct rtable *rt = (const struct rtable *) dst;
 
 		if (rt->rt_gateway != rt->rt_dst && mtu > 576)
 			mtu = 576;
@@ -1844,6 +1964,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
 		dst_init_metrics(&rt->dst, peer->metrics, false);
 
 		check_peer_pmtu(&rt->dst, peer);
+		if (peer->redirect_genid != redirect_genid)
+			peer->redirect_learned.a4 = 0;
 		if (peer->redirect_learned.a4 &&
 		    peer->redirect_learned.a4 != rt->rt_gateway) {
 			rt->rt_gateway = peer->redirect_learned.a4;
@@ -2349,6 +2471,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		    rth->rt_mark == skb->mark &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
+			ipv4_validate_peer(rth);
 			if (noref) {
 				dst_use_noref(&rth->dst, jiffies);
 				skb_dst_set_noref(skb, &rth->dst);
@@ -2407,11 +2530,11 @@ EXPORT_SYMBOL(ip_route_input_common);
 static struct rtable *__mkroute_output(const struct fib_result *res,
 				       const struct flowi4 *fl4,
 				       __be32 orig_daddr, __be32 orig_saddr,
-				       int orig_oif, struct net_device *dev_out,
+				       int orig_oif, __u8 orig_rtos,
+				       struct net_device *dev_out,
 				       unsigned int flags)
 {
 	struct fib_info *fi = res->fi;
-	u32 tos = RT_FL_TOS(fl4);
 	struct in_device *in_dev;
 	u16 type = res->type;
 	struct rtable *rth;
@@ -2462,7 +2585,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 	rth->rt_genid = rt_genid(dev_net(dev_out));
 	rth->rt_flags	= flags;
 	rth->rt_type	= type;
-	rth->rt_key_tos	= tos;
+	rth->rt_key_tos	= orig_rtos;
 	rth->rt_dst	= fl4->daddr;
 	rth->rt_src	= fl4->saddr;
 	rth->rt_route_iif = 0;
@@ -2512,7 +2635,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 {
 	struct net_device *dev_out = NULL;
-	u32 tos	= RT_FL_TOS(fl4);
+	__u8 tos = RT_FL_TOS(fl4);
 	unsigned int flags = 0;
 	struct fib_result res;
 	struct rtable *rth;
@@ -2688,7 +2811,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
 
 make_route:
 	rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
-			       dev_out, flags);
+			       tos, dev_out, flags);
 	if (!IS_ERR(rth)) {
 		unsigned int hash;
 
@@ -2724,6 +2847,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
 			    (IPTOS_RT_MASK | RTO_ONLINK)) &&
 		    net_eq(dev_net(rth->dst.dev), net) &&
 		    !rt_is_expired(rth)) {
+			ipv4_validate_peer(rth);
 			dst_use(&rth->dst, jiffies);
 			RT_CACHE_STAT_INC(out_hit);
 			rcu_read_unlock_bh();
@@ -2747,9 +2871,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo
 	return NULL;
 }
 
-static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst)
+static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
 {
-	return 0;
+	unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
+
+	return mtu ? : dst->dev->mtu;
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -2767,7 +2893,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = {
 	.protocol		=	cpu_to_be16(ETH_P_IP),
 	.destroy		=	ipv4_dst_destroy,
 	.check			=	ipv4_blackhole_dst_check,
-	.default_mtu		=	ipv4_blackhole_default_mtu,
+	.mtu			=	ipv4_blackhole_mtu,
 	.default_advmss		=	ipv4_default_advmss,
 	.update_pmtu		=	ipv4_rt_blackhole_update_pmtu,
 	.cow_metrics		=	ipv4_rt_blackhole_cow_metrics,
@@ -2845,7 +2971,7 @@ static int rt_fill_info(struct net *net,
 	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
-	long expires = 0;
+	unsigned long expires = 0;
 	const struct inet_peer *peer = rt->peer;
 	u32 id = 0, ts = 0, tsage = 0, error;
 
@@ -2902,8 +3028,12 @@ static int rt_fill_info(struct net *net,
 			tsage = get_seconds() - peer->tcp_ts_stamp;
 		}
 		expires = ACCESS_ONCE(peer->pmtu_expires);
-		if (expires)
-			expires -= jiffies;
+		if (expires) {
+			if (time_before(jiffies, expires))
+				expires -= jiffies;
+			else
+				expires = 0;
+		}
 	}
 
 	if (rt_is_input_route(rt)) {
@@ -3145,6 +3275,13 @@ static ctl_table ipv4_route_table[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 	{
+		.procname	= "gc_interval",
+		.data		= &ip_rt_gc_interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
 		.procname	= "redirect_load",
 		.data		= &ip_rt_redirect_load,
 		.maxlen		= sizeof(int),
@@ -3354,6 +3491,11 @@ int __init ip_rt_init(void)
 	devinet_init();
 	ip_fib_init();
 
+	INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func);
+	expires_ljiffies = jiffies;
+	schedule_delayed_work(&expires_work,
+		net_random() % ip_rt_gc_interval + ip_rt_gc_interval);
+
 	if (ip_rt_proc_init())
 		printk(KERN_ERR "Unable to create route proc files\n");
 #ifdef CONFIG_XFRM