ipv4: tcp: dont cache unconfirmed intput dst

DDOS synflood attacks hit badly IP route cache.

On typical machines, this cache is allowed to hold up to 8 Millions dst
entries, 256 bytes for each, for a total of 2GB of memory.

rt_garbage_collect() triggers and tries to cleanup things.

Eventually route cache is disabled but machine is under fire and might
OOM and crash.

This patch exploits the new TCP early demux, to set a nocache
boolean in case incoming TCP frame is for a not yet ESTABLISHED or
TIMEWAIT socket.

This 'nocache' boolean is then used in case dst entry is not found in
route cache, to create an unhashed dst entry (DST_NOCACHE)

SYN-cookie-ACK sent use a similar mechanism (ipv4: tcp: dont cache
output dst for syncookies), so after this patch, a machine is able to
absorb a DDOS synflood attack without polluting its IP route cache.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Hans Schillstrom <hans.schillstrom@ericsson.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 14 insertions, 9 deletions

diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 2e560f0c757d..6a9795944369 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -828,7 +828,7 @@ static int arp_process(struct sk_buff *skb)
 	}
 
 	if (arp->ar_op == htons(ARPOP_REQUEST) &&
-	    ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
+	    ip_route_input_noref(skb, tip, sip, 0, dev, false) == 0) {
 
 		rt = skb_rtable(skb);
 		addr_type = rt->rt_type;
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 8d07c973409c..978d55f256ea 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -259,7 +259,7 @@ static void ip_expire(unsigned long arg)
 		skb_dst_drop(head);
 		iph = ip_hdr(head);
 		err = ip_route_input_noref(head, iph->daddr, iph->saddr,
-					   iph->tos, head->dev);
+					   iph->tos, head->dev, false);
 		if (err)
 			goto out_rcu_unlock;
 
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 2a39204de5bc..7be54c8dcbe2 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -326,6 +326,7 @@ static int ip_rcv_finish(struct sk_buff *skb)
 	 */
 	if (skb_dst(skb) == NULL) {
 		int err = -ENOENT;
+		bool nocache = false;
 
 		if (sysctl_ip_early_demux) {
 			const struct net_protocol *ipprot;
@@ -334,13 +335,13 @@ static int ip_rcv_finish(struct sk_buff *skb)
 			rcu_read_lock();
 			ipprot = rcu_dereference(inet_protos[protocol]);
 			if (ipprot && ipprot->early_demux)
-				err = ipprot->early_demux(skb);
+				err = ipprot->early_demux(skb, &nocache);
 			rcu_read_unlock();
 		}
 
 		if (err) {
 			err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-						   iph->tos, skb->dev);
+						   iph->tos, skb->dev, nocache);
 			if (unlikely(err)) {
 				if (err == -EXDEV)
 					NET_INC_STATS_BH(dev_net(skb->dev),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 81533e3a23d1..fdc7900f9d7a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2214,7 +2214,7 @@ static int ip_mkroute_input(struct sk_buff *skb,
  */
 
 static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-			       u8 tos, struct net_device *dev)
+			       u8 tos, struct net_device *dev, bool nocache)
 {
 	struct fib_result res;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -2353,6 +2353,8 @@ local_input:
 		rth->dst.error= -err;
 		rth->rt_flags 	&= ~RTCF_LOCAL;
 	}
+	if (nocache)
+		rth->dst.flags |= DST_NOCACHE;
 	hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
 	rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
 	err = 0;
@@ -2395,7 +2397,7 @@ martian_source_keep_err:
 }
 
 int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-			   u8 tos, struct net_device *dev, bool noref)
+			   u8 tos, struct net_device *dev, bool noref, bool nocache)
 {
 	struct rtable	*rth;
 	unsigned int	hash;
@@ -2471,7 +2473,7 @@ skip_cache:
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
+	res = ip_route_input_slow(skb, daddr, saddr, tos, dev, nocache);
 	rcu_read_unlock();
 	return res;
 }
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 1781dc650b9d..33aabd4fc20f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1673,7 +1673,7 @@ csum_err:
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-int tcp_v4_early_demux(struct sk_buff *skb)
+int tcp_v4_early_demux(struct sk_buff *skb, bool *no_dst_cache)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
@@ -1719,6 +1719,8 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 				}
 			}
 		}
+	} else {
+		*no_dst_cache = true;
 	}
 
 out_err:
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 06814b6216dc..eee636b191b9 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -28,7 +28,7 @@ static inline int xfrm4_rcv_encap_finish(struct sk_buff *skb)
 		const struct iphdr *iph = ip_hdr(skb);
 
 		if (ip_route_input_noref(skb, iph->daddr, iph->saddr,
-					 iph->tos, skb->dev))
+					 iph->tos, skb->dev, false))
 			goto drop;
 	}
 	return dst_input(skb);