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>

3 files changed, 6 insertions, 6 deletions

diff --git a/include/net/protocol.h b/include/net/protocol.h
index 967b926cbfb1..7cfc8f76914d 100644
--- a/include/net/protocol.h
+++ b/include/net/protocol.h
@@ -37,7 +37,7 @@
 
 /* This is used to register protocols. */
 struct net_protocol {
-        int                     (*early_demux)(struct sk_buff *skb);
+        int                     (*early_demux)(struct sk_buff *skb, bool *nocache);
         int                     (*handler)(struct sk_buff *skb);
         void                    (*err_handler)(struct sk_buff *skb, u32 info);
         int                     (*gso_send_check)(struct sk_buff *skb);
diff --git a/include/net/route.h b/include/net/route.h
index 47eb25ac1f7f..6361f9335774 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -201,18 +201,18 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4
 }
 
 extern int ip_route_input_common(struct sk_buff *skb, __be32 dst, __be32 src,
-                                 u8 tos, struct net_device *devin, bool noref);
+                                 u8 tos, struct net_device *devin, bool noref, bool nocache);
 
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
                                  u8 tos, struct net_device *devin)
 {
-        return ip_route_input_common(skb, dst, src, tos, devin, false);
+        return ip_route_input_common(skb, dst, src, tos, devin, false, false);
 }
 
 static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
-                                       u8 tos, struct net_device *devin)
+                                       u8 tos, struct net_device *devin, bool nocache)
 {
-        return ip_route_input_common(skb, dst, src, tos, devin, true);
+        return ip_route_input_common(skb, dst, src, tos, devin, true, nocache);
 }
 
 extern void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 6660ffc4963d..917ed2e55e8c 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -325,7 +325,7 @@ extern void tcp_v4_err(struct sk_buff *skb, u32);
 
 extern void tcp_shutdown (struct sock *sk, int how);
 
-extern int tcp_v4_early_demux(struct sk_buff *skb);
+extern int tcp_v4_early_demux(struct sk_buff *skb, bool *nocache);
 extern int tcp_v4_rcv(struct sk_buff *skb);
 
 extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);