[RFC PATCH net-next v1 3/3] net: route: replace route hints with input_dst_cache

[Leone Fernando]

Replace route hints with cached dsts - ip_rcv_finish_core will first try
to use the cache and only then fall back to the demux or perform a full
lookup.

Only add newly found dsts to the cache after all the checks have passed
successfully to avoid adding a dropped packet's dst to the cache.

Multicast dsts are not added to the dst_cache as it will require additional
checks and multicast packets are rarer and a slower path anyway.

A check was added to ip_route_use_dst_cache that prevents forwarding
packets received by devices for which forwarding is disabled.

Signed-off-by: Leone Fernando <leone4fernando@xxxxxxxxx>
---
 include/net/route.h |  6 ++---
 net/ipv4/ip_input.c | 58 ++++++++++++++++++++++++---------------------
 net/ipv4/route.c    | 36 +++++++++++++++++++++-------
 3 files changed, 61 insertions(+), 39 deletions(-)

diff --git a/include/net/route.h b/include/net/route.h
index 980ab474eabd..a5a2f55947d6 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -189,9 +189,9 @@ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 			  struct in_device *in_dev, u32 *itag);
 int ip_route_input_noref(struct sk_buff *skb, __be32 dst, __be32 src,
 			 u8 tos, struct net_device *devin);
-int ip_route_use_hint(struct sk_buff *skb, __be32 dst, __be32 src,
-		      u8 tos, struct net_device *devin,
-		      const struct sk_buff *hint);
+int ip_route_use_dst_cache(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			   u8 tos, struct net_device *dev,
+			   struct dst_entry *dst);
 
 static inline int ip_route_input(struct sk_buff *skb, __be32 dst, __be32 src,
 				 u8 tos, struct net_device *devin)
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 5e9c8156656a..35c8b122d62f 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -305,30 +305,44 @@ static inline bool ip_rcv_options(struct sk_buff *skb, struct net_device *dev)
 	return true;
 }
 
-static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph,
-			    const struct sk_buff *hint)
+static bool ip_can_add_dst_cache(struct sk_buff *skb, __u16 rt_type)
 {
-	return hint && !skb_dst(skb) && ip_hdr(hint)->daddr == iph->daddr &&
-	       ip_hdr(hint)->tos == iph->tos;
+	return skb_valid_dst(skb) &&
+	       rt_type != RTN_BROADCAST &&
+	       rt_type != RTN_MULTICAST &&
+	       !(IPCB(skb)->flags & IPSKB_MULTIPATH);
+}
+
+static bool ip_can_use_dst_cache(const struct net *net, struct sk_buff *skb)
+{
+	return !skb_dst(skb) && !fib4_has_custom_rules(net);
 }
 
 int tcp_v4_early_demux(struct sk_buff *skb);
 int udp_v4_early_demux(struct sk_buff *skb);
 static int ip_rcv_finish_core(struct net *net, struct sock *sk,
-			      struct sk_buff *skb, struct net_device *dev,
-			      const struct sk_buff *hint)
+			      struct sk_buff *skb, struct net_device *dev)
 {
+	struct dst_cache *dst_cache = net_generic(net, dst_cache_net_id);
 	const struct iphdr *iph = ip_hdr(skb);
+	struct dst_entry *dst;
 	int err, drop_reason;
 	struct rtable *rt;
+	bool do_cache;
 
 	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 
-	if (ip_can_use_hint(skb, iph, hint)) {
-		err = ip_route_use_hint(skb, iph->daddr, iph->saddr, iph->tos,
-					dev, hint);
-		if (unlikely(err))
-			goto drop_error;
+	do_cache = ip_can_use_dst_cache(net, skb);
+	if (do_cache) {
+		dst = dst_cache_input_get_noref(dst_cache, skb);
+		if (dst) {
+			err = ip_route_use_dst_cache(skb, iph->daddr,
+						     iph->saddr, iph->tos,
+						     dev, dst);
+			if (unlikely(err))
+				goto drop_error;
+			do_cache = false;
+		}
 	}
 
 	if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
@@ -418,6 +432,9 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
 		}
 	}
 
+	if (do_cache && ip_can_add_dst_cache(skb, rt->rt_type))
+		dst_cache_input_add(dst_cache, skb);
+
 	return NET_RX_SUCCESS;
 
 drop:
@@ -444,7 +461,7 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (!skb)
 		return NET_RX_SUCCESS;
 
-	ret = ip_rcv_finish_core(net, sk, skb, dev, NULL);
+	ret = ip_rcv_finish_core(net, sk, skb, dev);
 	if (ret != NET_RX_DROP)
 		ret = dst_input(skb);
 	return ret;
@@ -581,21 +598,11 @@ static void ip_sublist_rcv_finish(struct list_head *head)
 	}
 }
 
-static struct sk_buff *ip_extract_route_hint(const struct net *net,
-					     struct sk_buff *skb, int rt_type)
-{
-	if (fib4_has_custom_rules(net) || rt_type == RTN_BROADCAST ||
-	    IPCB(skb)->flags & IPSKB_MULTIPATH)
-		return NULL;
-
-	return skb;
-}
-
 static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 			       struct list_head *head)
 {
-	struct sk_buff *skb, *next, *hint = NULL;
 	struct dst_entry *curr_dst = NULL;
+	struct sk_buff *skb, *next;
 	struct list_head sublist;
 
 	INIT_LIST_HEAD(&sublist);
@@ -610,14 +617,11 @@ static void ip_list_rcv_finish(struct net *net, struct sock *sk,
 		skb = l3mdev_ip_rcv(skb);
 		if (!skb)
 			continue;
-		if (ip_rcv_finish_core(net, sk, skb, dev, hint) == NET_RX_DROP)
+		if (ip_rcv_finish_core(net, sk, skb, dev) == NET_RX_DROP)
 			continue;
 
 		dst = skb_dst(skb);
 		if (curr_dst != dst) {
-			hint = ip_extract_route_hint(net, skb,
-					       ((struct rtable *)dst)->rt_type);
-
 			/* dispatch old sublist */
 			if (!list_empty(&sublist))
 				ip_sublist_rcv_finish(&sublist);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 7c5e68117ee2..3f1977f9b25c 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2157,14 +2157,14 @@ static int ip_mkroute_input(struct sk_buff *skb,
 
 /* Implements all the saddr-related checks as ip_route_input_slow(),
  * assuming daddr is valid and the destination is not a local broadcast one.
- * Uses the provided hint instead of performing a route lookup.
+ * Uses the provided dst from dst_cache instead of performing a route lookup.
  */
-int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
-		      u8 tos, struct net_device *dev,
-		      const struct sk_buff *hint)
+int ip_route_use_dst_cache(struct sk_buff *skb, __be32 daddr, __be32 saddr,
+			   u8 tos, struct net_device *dev,
+			   struct dst_entry *dst)
 {
 	struct in_device *in_dev = __in_dev_get_rcu(dev);
-	struct rtable *rt = skb_rtable(hint);
+	struct rtable *rt = (struct rtable *)dst;
 	struct net *net = dev_net(dev);
 	int err = -EINVAL;
 	u32 tag = 0;
@@ -2178,21 +2178,39 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	if (ipv4_is_loopback(saddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
 		goto martian_source;
 
-	if (rt->rt_type != RTN_LOCAL)
-		goto skip_validate_source;
+	if (ipv4_is_loopback(daddr) && !IN_DEV_NET_ROUTE_LOCALNET(in_dev, net))
+		goto martian_destination;
 
+	if (rt->rt_type != RTN_LOCAL) {
+		if (!IN_DEV_FORWARD(in_dev)) {
+			err = -EHOSTUNREACH;
+			goto out_err;
+		}
+		goto skip_validate_source;
+	}
 	tos &= IPTOS_RT_MASK;
 	err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &tag);
 	if (err < 0)
 		goto martian_source;
 
 skip_validate_source:
-	skb_dst_copy(skb, hint);
+	skb_dst_set_noref(skb, dst);
 	return 0;
 
 martian_source:
 	ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
+out_err:
 	return err;
+
+martian_destination:
+	RT_CACHE_STAT_INC(in_martian_dst);
+#ifdef CONFIG_IP_ROUTE_VERBOSE
+		if (IN_DEV_LOG_MARTIANS(in_dev))
+			net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n",
+					     &daddr, &saddr, dev->name);
+#endif
+	err = -EINVAL;
+	goto out_err;
 }
 
 /* get device for dst_alloc with local routes */
@@ -2213,7 +2231,7 @@ static struct net_device *ip_rt_get_dev(struct net *net,
  *	addresses, because every properly looped back packet
  *	must have correct destination already attached by output routine.
  *	Changes in the enforced policies must be applied also to
- *	ip_route_use_hint().
+ *	ip_route_use_dst_cache().
  *
  *	Such approach solves two big problems:
  *	1. Not simplex devices are handled properly.
-- 
2.34.1