Merge branch 'net-introduce-and-use-route-hint'

Paolo Abeni says:

====================
net: introduce and use route hint

This series leverages the listification infrastructure to avoid
unnecessary route lookup on ingress packets. In absence of custom rules,
packets with equal daddr will usually land on the same dst.

When processing packet bursts (lists) we can easily reference the previous
dst entry. When we hit the 'same destination' condition we can avoid the
route lookup, coping the already available dst.

Detailed performance numbers are available in the individual commit
messages.

v3 -> v4:
 - move helpers to their own patches (Eric D.)
 - enable hints for SUBTREE builds (David A.)
 - re-enable hints for ipv4 forward (David A.)

v2 -> v3:
 - use fib*_has_custom_rules() helpers (David A.)
 - add ip*_extract_route_hint() helper (Edward C.)
 - use prev skb as hint instead of copying data (Willem )

v1 -> v2:
 - fix build issue with !CONFIG_IP*_MULTIPLE_TABLES
 - fix potential race in ip6_list_rcv_finish()
====================

Acked-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 31 insertions, 2 deletions

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index f66bc2af4e9d..7bae6a91b487 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1461,6 +1461,8 @@ out:
 		}
 #endif
 		goto failure;
+	} else if (fib6_requires_src(rt)) {
+		fib6_routes_require_src_inc(info->nl_net);
 	}
 	return err;
 
@@ -1933,6 +1935,8 @@ int fib6_del(struct fib6_info *rt, struct nl_info *info)
 		struct fib6_info *cur = rcu_dereference_protected(*rtp,
 					lockdep_is_held(&table->tb6_lock));
 		if (rt == cur) {
+			if (fib6_requires_src(cur))
+				fib6_routes_require_src_dec(info->nl_net);
 			fib6_del_route(table, fn, rtp, info);
 			return 0;
 		}
diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index ef7f707d9ae3..7b089d0ac8cd 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -86,11 +86,27 @@ static void ip6_sublist_rcv_finish(struct list_head *head)
 	}
 }
 
+static bool ip6_can_use_hint(const struct sk_buff *skb,
+			     const struct sk_buff *hint)
+{
+	return hint && !skb_dst(skb) &&
+	       ipv6_addr_equal(&ipv6_hdr(hint)->daddr, &ipv6_hdr(skb)->daddr);
+}
+
+static struct sk_buff *ip6_extract_route_hint(const struct net *net,
+					      struct sk_buff *skb)
+{
+	if (fib6_routes_require_src(net) || fib6_has_custom_rules(net))
+		return NULL;
+
+	return skb;
+}
+
 static void ip6_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);
@@ -104,9 +120,15 @@ static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
 		skb = l3mdev_ip6_rcv(skb);
 		if (!skb)
 			continue;
-		ip6_rcv_finish_core(net, sk, skb);
+
+		if (ip6_can_use_hint(skb, hint))
+			skb_dst_copy(skb, hint);
+		else
+			ip6_rcv_finish_core(net, sk, skb);
 		dst = skb_dst(skb);
 		if (curr_dst != dst) {
+			hint = ip6_extract_route_hint(net, skb);
+
 			/* dispatch old sublist */
 			if (!list_empty(&sublist))
 				ip6_sublist_rcv_finish(&sublist);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index edcb52543518..c92b367e058d 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6199,6 +6199,9 @@ static int __net_init ip6_route_net_init(struct net *net)
 	dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst,
 			 ip6_template_metrics, true);
 	INIT_LIST_HEAD(&net->ipv6.ip6_blk_hole_entry->rt6i_uncached);
+#ifdef CONFIG_IPV6_SUBTREES
+	net->ipv6.fib6_routes_require_src = 0;
+#endif
 #endif
 
 	net->ipv6.sysctl.flush_delay = 0;