1 files changed, 62 insertions, 38 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 0383e66f59bc..43b69af242e1 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -495,7 +495,7 @@ u32 ip_idents_reserve(u32 hash, int segs)
 {
 	u32 *p_tstamp = ip_tstamps + hash % IP_IDENTS_SZ;
 	atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ;
-	u32 old = ACCESS_ONCE(*p_tstamp);
+	u32 old = READ_ONCE(*p_tstamp);
 	u32 now = (u32)jiffies;
 	u32 new, delta = 0;
 
@@ -651,9 +651,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	struct fnhe_hash_bucket *hash;
 	struct fib_nh_exception *fnhe;
 	struct rtable *rt;
+	u32 genid, hval;
 	unsigned int i;
 	int depth;
-	u32 hval = fnhe_hashfun(daddr);
+
+	genid = fnhe_genid(dev_net(nh->nh_dev));
+	hval = fnhe_hashfun(daddr);
 
 	spin_lock_bh(&fnhe_lock);
 
@@ -676,12 +679,13 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 	}
 
 	if (fnhe) {
+		if (fnhe->fnhe_genid != genid)
+			fnhe->fnhe_genid = genid;
 		if (gw)
 			fnhe->fnhe_gw = gw;
-		if (pmtu) {
+		if (pmtu)
 			fnhe->fnhe_pmtu = pmtu;
-			fnhe->fnhe_expires = max(1UL, expires);
-		}
+		fnhe->fnhe_expires = max(1UL, expires);
 		/* Update all cached dsts too */
 		rt = rcu_dereference(fnhe->fnhe_rth_input);
 		if (rt)
@@ -700,7 +704,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 			fnhe->fnhe_next = hash->chain;
 			rcu_assign_pointer(hash->chain, fnhe);
 		}
-		fnhe->fnhe_genid = fnhe_genid(dev_net(nh->nh_dev));
+		fnhe->fnhe_genid = genid;
 		fnhe->fnhe_daddr = daddr;
 		fnhe->fnhe_gw = gw;
 		fnhe->fnhe_pmtu = pmtu;
@@ -1250,7 +1254,7 @@ static void set_class_tag(struct rtable *rt, u32 tag)
 static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
 {
 	unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr);
-	unsigned int advmss = max_t(unsigned int, dst->dev->mtu - header_size,
+	unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size,
 				    ip_rt_min_advmss);
 
 	return min(advmss, IPV4_MAX_PMTU - header_size);
@@ -1267,7 +1271,7 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	if (mtu)
 		return mtu;
 
-	mtu = dst->dev->mtu;
+	mtu = READ_ONCE(dst->dev->mtu);
 
 	if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
 		if (rt->rt_uses_gateway && mtu > 576)
@@ -1398,7 +1402,7 @@ static void ipv4_dst_destroy(struct dst_entry *dst)
 	struct dst_metrics *p = (struct dst_metrics *)DST_METRICS_PTR(dst);
 	struct rtable *rt = (struct rtable *) dst;
 
-	if (p != &dst_default_metrics && atomic_dec_and_test(&p->refcnt))
+	if (p != &dst_default_metrics && refcount_dec_and_test(&p->refcnt))
 		kfree(p);
 
 	if (!list_empty(&rt->rt_uncached)) {
@@ -1456,7 +1460,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr,
 		dst_init_metrics(&rt->dst, fi->fib_metrics->metrics, true);
 		if (fi->fib_metrics != &dst_default_metrics) {
 			rt->dst._metrics |= DST_METRICS_REFCOUNTED;
-			atomic_inc(&fi->fib_metrics->refcnt);
+			refcount_inc(&fi->fib_metrics->refcnt);
 		}
 #ifdef CONFIG_IP_ROUTE_CLASSID
 		rt->dst.tclassid = nh->nh_tclassid;
@@ -1520,43 +1524,56 @@ struct rtable *rt_dst_alloc(struct net_device *dev,
 EXPORT_SYMBOL(rt_dst_alloc);
 
 /* called in rcu_read_lock() section */
-static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-				u8 tos, struct net_device *dev, int our)
+int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			  u8 tos, struct net_device *dev,
+			  struct in_device *in_dev, u32 *itag)
 {
-	struct rtable *rth;
-	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	unsigned int flags = RTCF_MULTICAST;
-	u32 itag = 0;
 	int err;
 
 	/* Primary sanity checks. */
-
 	if (!in_dev)
 		return -EINVAL;
 
 	if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
 	    skb->protocol != htons(ETH_P_IP))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev))
-		goto e_inval;
+		return -EINVAL;
 
 	if (ipv4_is_zeronet(saddr)) {
 		if (!ipv4_is_local_multicast(daddr))
-			goto e_inval;
+			return -EINVAL;
 	} else {
 		err = fib_validate_source(skb, saddr, 0, tos, 0, dev,
-					  in_dev, &itag);
+					  in_dev, itag);
 		if (err < 0)
-			goto e_err;
+			return err;
 	}
+	return 0;
+}
+
+/* called in rcu_read_lock() section */
+static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			     u8 tos, struct net_device *dev, int our)
+{
+	struct in_device *in_dev = __in_dev_get_rcu(dev);
+	unsigned int flags = RTCF_MULTICAST;
+	struct rtable *rth;
+	u32 itag = 0;
+	int err;
+
+	err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag);
+	if (err)
+		return err;
+
 	if (our)
 		flags |= RTCF_LOCAL;
 
 	rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
 			   IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false);
 	if (!rth)
-		goto e_nobufs;
+		return -ENOBUFS;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
 	rth->dst.tclassid = itag;
@@ -1572,13 +1589,6 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 
 	skb_dst_set(skb, &rth->dst);
 	return 0;
-
-e_nobufs:
-	return -ENOBUFS;
-e_inval:
-	return -EINVAL;
-e_err:
-	return err;
 }
 
 
@@ -2236,7 +2246,7 @@ add:
 	if (!rth)
 		return ERR_PTR(-ENOBUFS);
 
-	rth->rt_iif	= orig_oif ? : 0;
+	rth->rt_iif = orig_oif;
 	if (res->table)
 		rth->rt_table_id = res->table->tb_id;
 
@@ -2439,6 +2449,12 @@ struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4,
 		/* L3 master device is the loopback for that domain */
 		dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? :
 			net->loopback_dev;
+
+		/* make sure orig_oif points to fib result device even
+		 * though packet rx/tx happens over loopback or l3mdev
+		 */
+		orig_oif = FIB_RES_OIF(*res);
+
 		fl4->flowi4_oif = dev_out->ifindex;
 		flags |= RTCF_LOCAL;
 		goto make_route;
@@ -2501,7 +2517,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 	struct rtable *ort = (struct rtable *) dst_orig;
 	struct rtable *rt;
 
-	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_NONE, 0);
+	rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0);
 	if (rt) {
 		struct dst_entry *new = &rt->dst;
 
@@ -2750,26 +2766,34 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		err = 0;
 		if (IS_ERR(rt))
 			err = PTR_ERR(rt);
+		else
+			skb_dst_set(skb, &rt->dst);
 	}
 
 	if (err)
 		goto errout_free;
 
-	skb_dst_set(skb, &rt->dst);
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
 
 	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
 		table_id = rt->rt_table_id;
 
-	if (rtm->rtm_flags & RTM_F_FIB_MATCH)
+	if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
+		if (!res.fi) {
+			err = fib_props[res.type].error;
+			if (!err)
+				err = -EHOSTUNREACH;
+			goto errout_free;
+		}
 		err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
 				    nlh->nlmsg_seq, RTM_NEWROUTE, table_id,
 				    rt->rt_type, res.prefix, res.prefixlen,
 				    fl4.flowi4_tos, res.fi, 0);
-	else
+	} else {
 		err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
 				   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
+	}
 	if (err < 0)
 		goto errout_free;
 
@@ -3018,7 +3042,6 @@ struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
 
 int __init ip_rt_init(void)
 {
-	int rc = 0;
 	int cpu;
 
 	ip_idents = kmalloc(IP_IDENTS_SZ * sizeof(*ip_idents), GFP_KERNEL);
@@ -3067,14 +3090,15 @@ int __init ip_rt_init(void)
 	xfrm_init();
 	xfrm4_init();
 #endif
-	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
+	rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL,
+		      RTNL_FLAG_DOIT_UNLOCKED);
 
 #ifdef CONFIG_SYSCTL
 	register_pernet_subsys(&sysctl_route_ops);
 #endif
 	register_pernet_subsys(&rt_genid_ops);
 	register_pernet_subsys(&ipv4_inetpeer_ops);
-	return rc;
+	return 0;
 }
 
 #ifdef CONFIG_SYSCTL