1 files changed, 200 insertions, 118 deletions

diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ccb25d80f679..bf4e4adc2d00 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -360,18 +360,6 @@ static int rt_acct_proc_show(struct seq_file *m, void *v)
 	kfree(dst);
 	return 0;
 }
-
-static int rt_acct_proc_open(struct inode *inode, struct file *file)
-{
-	return single_open(file, rt_acct_proc_show, NULL);
-}
-
-static const struct file_operations rt_acct_proc_fops = {
-	.open		= rt_acct_proc_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
 #endif
 
 static int __net_init ip_rt_do_proc_init(struct net *net)
@@ -389,7 +377,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
 		goto err2;
 
 #ifdef CONFIG_IP_ROUTE_CLASSID
-	pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
+	pde = proc_create_single("rt_acct", 0, net->proc_net,
+			rt_acct_proc_show);
 	if (!pde)
 		goto err3;
 #endif
@@ -709,7 +698,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
 		fnhe->fnhe_gw = gw;
 		fnhe->fnhe_pmtu = pmtu;
 		fnhe->fnhe_mtu_locked = lock;
-		fnhe->fnhe_expires = expires;
+		fnhe->fnhe_expires = max(1UL, expires);
 
 		/* Exception created; mark the cached routes for the nexthop
 		 * stale, so anyone caching it rechecks if this exception
@@ -1297,6 +1286,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst)
 	return mtu - lwtunnel_headroom(dst->lwtstate, mtu);
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 {
 	struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions);
@@ -1310,12 +1329,49 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr)
 
 	for (fnhe = rcu_dereference(hash[hval].chain); fnhe;
 	     fnhe = rcu_dereference(fnhe->fnhe_next)) {
-		if (fnhe->fnhe_daddr == daddr)
+		if (fnhe->fnhe_daddr == daddr) {
+			if (fnhe->fnhe_expires &&
+			    time_after(jiffies, fnhe->fnhe_expires)) {
+				ip_del_fnhe(nh, daddr);
+				break;
+			}
 			return fnhe;
+		}
 	}
 	return NULL;
 }
 
+/* MTU selection:
+ * 1. mtu on route is locked - use it
+ * 2. mtu from nexthop exception
+ * 3. mtu from egress device
+ */
+
+u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
+{
+	struct fib_info *fi = res->fi;
+	struct fib_nh *nh = &fi->fib_nh[res->nh_sel];
+	struct net_device *dev = nh->nh_dev;
+	u32 mtu = 0;
+
+	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
+	    fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
+		mtu = fi->fib_mtu;
+
+	if (likely(!mtu)) {
+		struct fib_nh_exception *fnhe;
+
+		fnhe = find_exception(nh, daddr);
+		if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires))
+			mtu = fnhe->fnhe_pmtu;
+	}
+
+	if (likely(!mtu))
+		mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU);
+
+	return mtu - lwtunnel_headroom(nh->nh_lwtstate, mtu);
+}
+
 static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 			      __be32 daddr, const bool do_cache)
 {
@@ -1339,6 +1395,7 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
 			fnhe->fnhe_gw = 0;
 			fnhe->fnhe_pmtu = 0;
 			fnhe->fnhe_expires = 0;
+			fnhe->fnhe_mtu_locked = false;
 			fnhe_flush_routes(fnhe);
 			orig = NULL;
 		}
@@ -1636,36 +1693,6 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
-static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
-{
-	struct fnhe_hash_bucket *hash;
-	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
-	u32 hval = fnhe_hashfun(daddr);
-
-	spin_lock_bh(&fnhe_lock);
-
-	hash = rcu_dereference_protected(nh->nh_exceptions,
-					 lockdep_is_held(&fnhe_lock));
-	hash += hval;
-
-	fnhe_p = &hash->chain;
-	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
-	while (fnhe) {
-		if (fnhe->fnhe_daddr == daddr) {
-			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
-				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
-			fnhe_flush_routes(fnhe);
-			kfree_rcu(fnhe, rcu);
-			break;
-		}
-		fnhe_p = &fnhe->fnhe_next;
-		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
-						 lockdep_is_held(&fnhe_lock));
-	}
-
-	spin_unlock_bh(&fnhe_lock);
-}
-
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1719,20 +1746,10 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe) {
+		if (fnhe)
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
-			}
-		}
-
-		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
-
-rt_cache:
+		else
+			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -1964,8 +1981,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.saddr = saddr;
 	fl4.flowi4_uid = sock_net_uid(net, NULL);
 
-	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys))
+	if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) {
 		flkeys = &_flkeys;
+	} else {
+		fl4.flowi4_proto = 0;
+		fl4.fl4_sport = 0;
+		fl4.fl4_dport = 0;
+	}
 
 	err = fib_lookup(net, &fl4, res, 0);
 	if (err != 0) {
@@ -2216,39 +2238,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		 * the loopback interface and the IP_PKTINFO ipi_ifindex will
 		 * be set to the loopback interface as well.
 		 */
-		fi = NULL;
+		do_cache = false;
 	}
 
 	fnhe = NULL;
 	do_cache &= fi != NULL;
-	if (do_cache) {
+	if (fi) {
 		struct rtable __rcu **prth;
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
+		if (!do_cache)
+			goto add;
 		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-			rth = rcu_dereference(*prth);
-			if (rth && rth->dst.expires &&
-			    time_after(jiffies, rth->dst.expires)) {
-				ip_del_fnhe(nh, fl4->daddr);
-				fnhe = NULL;
-			} else {
-				goto rt_cache;
+		} else {
+			if (unlikely(fl4->flowi4_flags &
+				     FLOWI_FLAG_KNOWN_NH &&
+				     !(nh->nh_gw &&
+				       nh->nh_scope == RT_SCOPE_LINK))) {
+				do_cache = false;
+				goto add;
 			}
+			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
-
-		if (unlikely(fl4->flowi4_flags &
-			     FLOWI_FLAG_KNOWN_NH &&
-			     !(nh->nh_gw &&
-			       nh->nh_scope == RT_SCOPE_LINK))) {
-			do_cache = false;
-			goto add;
-		}
-		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
-
-rt_cache:
 		if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst))
 			return rth;
 	}
@@ -2580,11 +2594,10 @@ struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
 EXPORT_SYMBOL_GPL(ip_route_output_flow);
 
 /* called with rcu_read_lock held */
-static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
-			struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
-			u32 seq)
+static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+			struct rtable *rt, u32 table_id, struct flowi4 *fl4,
+			struct sk_buff *skb, u32 portid, u32 seq)
 {
-	struct rtable *rt = skb_rtable(skb);
 	struct rtmsg *r;
 	struct nlmsghdr *nlh;
 	unsigned long expires = 0;
@@ -2680,7 +2693,7 @@ static int rt_fill_info(struct net *net,  __be32 dst, __be32 src, u32 table_id,
 			}
 		} else
 #endif
-			if (nla_put_u32(skb, RTA_IIF, skb->dev->ifindex))
+			if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif))
 				goto nla_put_failure;
 	}
 
@@ -2695,43 +2708,93 @@ nla_put_failure:
 	return -EMSGSIZE;
 }
 
+static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst,
+						   u8 ip_proto, __be16 sport,
+						   __be16 dport)
+{
+	struct sk_buff *skb;
+	struct iphdr *iph;
+
+	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!skb)
+		return NULL;
+
+	/* Reserve room for dummy headers, this skb can pass
+	 * through good chunk of routing engine.
+	 */
+	skb_reset_mac_header(skb);
+	skb_reset_network_header(skb);
+	skb->protocol = htons(ETH_P_IP);
+	iph = skb_put(skb, sizeof(struct iphdr));
+	iph->protocol = ip_proto;
+	iph->saddr = src;
+	iph->daddr = dst;
+	iph->version = 0x4;
+	iph->frag_off = 0;
+	iph->ihl = 0x5;
+	skb_set_transport_header(skb, skb->len);
+
+	switch (iph->protocol) {
+	case IPPROTO_UDP: {
+		struct udphdr *udph;
+
+		udph = skb_put_zero(skb, sizeof(struct udphdr));
+		udph->source = sport;
+		udph->dest = dport;
+		udph->len = sizeof(struct udphdr);
+		udph->check = 0;
+		break;
+	}
+	case IPPROTO_TCP: {
+		struct tcphdr *tcph;
+
+		tcph = skb_put_zero(skb, sizeof(struct tcphdr));
+		tcph->source	= sport;
+		tcph->dest	= dport;
+		tcph->doff	= sizeof(struct tcphdr) / 4;
+		tcph->rst = 1;
+		tcph->check = ~tcp_v4_check(sizeof(struct tcphdr),
+					    src, dst, 0);
+		break;
+	}
+	case IPPROTO_ICMP: {
+		struct icmphdr *icmph;
+
+		icmph = skb_put_zero(skb, sizeof(struct icmphdr));
+		icmph->type = ICMP_ECHO;
+		icmph->code = 0;
+	}
+	}
+
+	return skb;
+}
+
 static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 			     struct netlink_ext_ack *extack)
 {
 	struct net *net = sock_net(in_skb->sk);
-	struct rtmsg *rtm;
 	struct nlattr *tb[RTA_MAX+1];
+	u32 table_id = RT_TABLE_MAIN;
+	__be16 sport = 0, dport = 0;
 	struct fib_result res = {};
+	u8 ip_proto = IPPROTO_UDP;
 	struct rtable *rt = NULL;
+	struct sk_buff *skb;
+	struct rtmsg *rtm;
 	struct flowi4 fl4;
 	__be32 dst = 0;
 	__be32 src = 0;
+	kuid_t uid;
 	u32 iif;
 	int err;
 	int mark;
-	struct sk_buff *skb;
-	u32 table_id = RT_TABLE_MAIN;
-	kuid_t uid;
 
 	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy,
 			  extack);
 	if (err < 0)
-		goto errout;
+		return err;
 
 	rtm = nlmsg_data(nlh);
-
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb) {
-		err = -ENOBUFS;
-		goto errout;
-	}
-
-	/* Reserve room for dummy headers, this skb can pass
-	   through good chunk of routing engine.
-	 */
-	skb_reset_mac_header(skb);
-	skb_reset_network_header(skb);
-
 	src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0;
 	dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0;
 	iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
@@ -2741,14 +2804,22 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	else
 		uid = (iif ? INVALID_UID : current_uid());
 
-	/* Bugfix: need to give ip_route_input enough of an IP header to
-	 * not gag.
-	 */
-	ip_hdr(skb)->protocol = IPPROTO_UDP;
-	ip_hdr(skb)->saddr = src;
-	ip_hdr(skb)->daddr = dst;
+	if (tb[RTA_IP_PROTO]) {
+		err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO],
+						  &ip_proto, extack);
+		if (err)
+			return err;
+	}
+
+	if (tb[RTA_SPORT])
+		sport = nla_get_be16(tb[RTA_SPORT]);
 
-	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
+	if (tb[RTA_DPORT])
+		dport = nla_get_be16(tb[RTA_DPORT]);
+
+	skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport);
+	if (!skb)
+		return -ENOBUFS;
 
 	memset(&fl4, 0, sizeof(fl4));
 	fl4.daddr = dst;
@@ -2757,6 +2828,11 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0;
 	fl4.flowi4_mark = mark;
 	fl4.flowi4_uid = uid;
+	if (sport)
+		fl4.fl4_sport = sport;
+	if (dport)
+		fl4.fl4_dport = dport;
+	fl4.flowi4_proto = ip_proto;
 
 	rcu_read_lock();
 
@@ -2766,10 +2842,10 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 		dev = dev_get_by_index_rcu(net, iif);
 		if (!dev) {
 			err = -ENODEV;
-			goto errout_free;
+			goto errout_rcu;
 		}
 
-		skb->protocol	= htons(ETH_P_IP);
+		fl4.flowi4_iif = iif; /* for rt_fill_info */
 		skb->dev	= dev;
 		skb->mark	= mark;
 		err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos,
@@ -2789,7 +2865,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	}
 
 	if (err)
-		goto errout_free;
+		goto errout_rcu;
 
 	if (rtm->rtm_flags & RTM_F_NOTIFY)
 		rt->rt_flags |= RTCF_NOTIFY;
@@ -2797,34 +2873,40 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
 	if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE)
 		table_id = res.table ? res.table->tb_id : 0;
 
+	/* reset skb for netlink reply msg */
+	skb_trim(skb, 0);
+	skb_reset_network_header(skb);
+	skb_reset_transport_header(skb);
+	skb_reset_mac_header(skb);
+
 	if (rtm->rtm_flags & RTM_F_FIB_MATCH) {
 		if (!res.fi) {
 			err = fib_props[res.type].error;
 			if (!err)
 				err = -EHOSTUNREACH;
-			goto errout_free;
+			goto errout_rcu;
 		}
 		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 {
-		err = rt_fill_info(net, dst, src, table_id, &fl4, skb,
+		err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
 				   NETLINK_CB(in_skb).portid, nlh->nlmsg_seq);
 	}
 	if (err < 0)
-		goto errout_free;
+		goto errout_rcu;
 
 	rcu_read_unlock();
 
 	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
-errout:
-	return err;
 
 errout_free:
+	return err;
+errout_rcu:
 	rcu_read_unlock();
 	kfree_skb(skb);
-	goto errout;
+	goto errout_free;
 }
 
 void ip_rt_multicast_event(struct in_device *in_dev)