net: avoid a full fib lookup when rp_filter is disabled.

Paolo Abeni · davem330 · commit 6e617de84e87 · 2017-09-21T15:15:22.000-07:00
Since commit 1dced6a ("ipv4: Restore accept_local behaviour in fib_validate_source()") a full fib lookup is needed even if the rp_filter is disabled, if accept_local is false - which is the default. What we really need in the above scenario is just checking that the source IP address is not local, and in most case we can do that is a cheaper way looking up the ifaddr hash table. This commit adds a helper for such lookup, and uses it to validate the src address when rp_filter is disabled and no 'local' routes are created by the user space in the relevant namespace. A new ipv4 netns flag is added to account for such routes. We need that to preserve the same behavior we had before this patch. It also drops the checks to bail early from __fib_validate_source, added by the commit 1dced6a ("ipv4: Restore accept_local behaviour in fib_validate_source()") they do not give any measurable performance improvement: if we do the lookup with are on a slower path. This improves UDP performances for unconnected sockets when rp_filter is disabled by 5% and also gives small but measurable performance improvement for TCP flood scenarios. v1 -> v2: - use the ifaddr lookup helper in __ip_dev_find(), as suggested by Eric - fall-back to full lookup if custom local routes are present Signed-off-by: Paolo Abeni <pabeni@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
@@ -179,6 +179,7 @@ __be32 inet_confirm_addr(struct net *net, struct in_device *in_dev, __be32 dst,
 			 __be32 local, int scope);
 struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix,
 				    __be32 mask);
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr);
 static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa)
 {
 	return !((addr^ifa->ifa_address)&ifa->ifa_mask);
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
@@ -49,6 +49,7 @@ struct netns_ipv4 {
 #ifdef CONFIG_IP_MULTIPLE_TABLES
 	struct fib_rules_ops	*rules_ops;
 	bool			fib_has_custom_rules;
+	bool			fib_has_custom_local_routes;
 	struct fib_table __rcu	*fib_main;
 	struct fib_table __rcu	*fib_default;
 #endif
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
@@ -137,22 +137,12 @@ static void inet_hash_remove(struct in_ifaddr *ifa)
  */
 struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 {
-	u32 hash = inet_addr_hash(net, addr);
 	struct net_device *result = NULL;
 	struct in_ifaddr *ifa;
 
 	rcu_read_lock();
-	hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash) {
-		if (ifa->ifa_local == addr) {
-			struct net_device *dev = ifa->ifa_dev->dev;
-
-			if (!net_eq(dev_net(dev), net))
-				continue;
-			result = dev;
-			break;
-		}
-	}
-	if (!result) {
+	ifa = inet_lookup_ifaddr_rcu(net, addr);
+	if (!ifa) {
 		struct flowi4 fl4 = { .daddr = addr };
 		struct fib_result res = { 0 };
 		struct fib_table *local;
@@ -165,6 +155,8 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 		    !fib_table_lookup(local, &fl4, &res, FIB_LOOKUP_NOREF) &&
 		    res.type == RTN_LOCAL)
 			result = FIB_RES_DEV(res);
+	} else {
+		result = ifa->ifa_dev->dev;
 	}
 	if (result && devref)
 		dev_hold(result);
@@ -173,6 +165,20 @@ struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref)
 }
 EXPORT_SYMBOL(__ip_dev_find);
 
+/* called under RCU lock */
+struct in_ifaddr *inet_lookup_ifaddr_rcu(struct net *net, __be32 addr)
+{
+	u32 hash = inet_addr_hash(net, addr);
+	struct in_ifaddr *ifa;
+
+	hlist_for_each_entry_rcu(ifa, &inet_addr_lst[hash], hash)
+		if (ifa->ifa_local == addr &&
+		    net_eq(dev_net(ifa->ifa_dev->dev), net))
+			return ifa;
+
+	return NULL;
+}
+
 static void rtmsg_ifa(int event, struct in_ifaddr *, struct nlmsghdr *, u32);
 
 static BLOCKING_NOTIFIER_HEAD(inetaddr_chain);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
@@ -345,9 +345,6 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	if (res.type != RTN_UNICAST &&
 	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
 		goto e_inval;
-	if (!rpf && !fib_num_tclassid_users(net) &&
-	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev)))
-		goto last_resort;
 	fib_combine_itag(itag, &res);
 	dev_match = false;
 
@@ -402,13 +399,26 @@ int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			struct in_device *idev, u32 *itag)
 {
 	int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
+	struct net *net = dev_net(dev);
 
-	if (!r && !fib_num_tclassid_users(dev_net(dev)) &&
-	    IN_DEV_ACCEPT_LOCAL(idev) &&
+	if (!r && !fib_num_tclassid_users(net) &&
 	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
+		if (IN_DEV_ACCEPT_LOCAL(idev))
+			goto ok;
+		/* if no local routes are added from user space we can check
+		 * for local addresses looking-up the ifaddr table
+		 */
+		if (net->ipv4.fib_has_custom_local_routes)
+			goto full_check;
+		if (inet_lookup_ifaddr_rcu(net, src))
+			return -EINVAL;
+
+ok:
 		*itag = 0;
 		return 0;
 	}
+
+full_check:
 	return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
 }
 
@@ -759,6 +769,8 @@ static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
 	}
 
 	err = fib_table_insert(net, tb, &cfg, extack);
+	if (!err && cfg.fc_type == RTN_LOCAL)
+		net->ipv4.fib_has_custom_local_routes = true;
 errout:
 	return err;
 }

Original file line number	Diff line number	Diff line change
`@@ -179,6 +179,7 @@ __be32 inet_confirm_addr(struct net net, struct in_device in_dev, __be32 dst,`
`179`	`179`	`__be32 local, int scope);`
`180`	`180`	`struct in_ifaddr inet_ifa_byprefix(struct in_device in_dev, __be32 prefix,`
`181`	`181`	`__be32 mask);`
	`182`	`+struct in_ifaddr inet_lookup_ifaddr_rcu(struct net net, __be32 addr);`
`182`	`183`	`static __inline__ bool inet_ifa_match(__be32 addr, struct in_ifaddr *ifa)`
`183`	`184`	`{`
`184`	`185`	`return !((addr^ifa->ifa_address)&ifa->ifa_mask);`