Revert "ipv4: tcp: dont cache unconfirmed intput dst"

This reverts commit c074da2. This change has several unwanted side effects: 1) Sockets will cache the DST_NOCACHE route in sk->sk_rx_dst and we'll thus never create a real cached route. 2) All TCP traffic will use DST_NOCACHE and never use the routing cache at all. Signed-off-by: David S. Miller <davem@davemloft.net>
wshizhx · Jun 28, 2012 · c10237e · c10237e
1 parent e440cf2
commit c10237e
Show file tree

Hide file tree

Showing 9 changed files with 15 additions and 20 deletions.
diff --git 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, bool *nocache);
+	int			(*early_demux)(struct sk_buff *skb);
 	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
@@ -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, bool nocache);
+				 u8 tos, struct net_device *devin, bool noref);
 
 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, false);
+	return ip_route_input_common(skb, dst, src, tos, devin, false);
 }
 
 static inline int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
-				       u8 tos, struct net_device *devin, bool nocache)
+				       u8 tos, struct net_device *devin)
 {
-	return ip_route_input_common(skb, dst, src, tos, devin, true, nocache);
+	return ip_route_input_common(skb, dst, src, tos, devin, true);
 }
 
 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
@@ -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, bool *nocache);
+extern int tcp_v4_early_demux(struct sk_buff *skb);
 extern int tcp_v4_rcv(struct sk_buff *skb);
 
 extern struct inet_peer *tcp_v4_get_peer(struct sock *sk);

diff --git 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, false) == 0) {
+	    ip_route_input_noref(skb, tip, sip, 0, dev) == 0) {
 
 		rt = skb_rtable(skb);
 		addr_type = rt->rt_type;

diff --git 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, false);
+					   iph->tos, head->dev);
 		if (err)
 			goto out_rcu_unlock;
 

diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
@@ -326,7 +326,6 @@ 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;
@@ -335,13 +334,13 @@ 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, &nocache);
+				err = ipprot->early_demux(skb);
 			rcu_read_unlock();
 		}
 
 		if (err) {
 			err = ip_route_input_noref(skb, iph->daddr, iph->saddr,
-						   iph->tos, skb->dev, nocache);
+						   iph->tos, skb->dev);
 			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
@@ -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, bool nocache)
+			       u8 tos, struct net_device *dev)
 {
 	struct fib_result res;
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
@@ -2353,8 +2353,6 @@ out:	return err;
 		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;
@@ -2397,7 +2395,7 @@ out:	return err;
 }
 
 int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-			   u8 tos, struct net_device *dev, bool noref, bool nocache)
+			   u8 tos, struct net_device *dev, bool noref)
 {
 	struct rtable	*rth;
 	unsigned int	hash;
@@ -2473,7 +2471,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 		rcu_read_unlock();
 		return -EINVAL;
 	}
-	res = ip_route_input_slow(skb, daddr, saddr, tos, dev, nocache);
+	res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
 	rcu_read_unlock();
 	return res;
 }

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
@@ -1673,7 +1673,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 }
 EXPORT_SYMBOL(tcp_v4_do_rcv);
 
-int tcp_v4_early_demux(struct sk_buff *skb, bool *no_dst_cache)
+int tcp_v4_early_demux(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
 	const struct iphdr *iph;
@@ -1719,8 +1719,6 @@ int tcp_v4_early_demux(struct sk_buff *skb, bool *no_dst_cache)
 				}
 			}
 		}
-	} else {
-		*no_dst_cache = true;
 	}
 
 out_err:

diff --git 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, false))
+					 iph->tos, skb->dev))
 			goto drop;
 	}
 	return dst_input(skb);