netdev - [PATCH net-next 1/2] ipv6: introduce and uses route look hints for list input

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <9b3b3a66894a1714266db1d3cb3268efe243509e.1573893340.git.pabeni@redhat.com>
Date:   Sat, 16 Nov 2019 10:14:50 +0100
From:   Paolo Abeni <pabeni@...hat.com>
To:     netdev@...r.kernel.org
Cc:     "David S. Miller" <davem@...emloft.net>,
        Willem de Bruijn <willemdebruijn.kernel@...il.com>,
        Edward Cree <ecree@...arflare.com>
Subject: [PATCH net-next 1/2] ipv6: introduce and uses route look hints for list input

When doing RX batch packet processing, we currently always repeat
the route lookup for each ingress packet. If policy routing is
configured, and IPV6_SUBTREES is disabled at build time, we
know that packets with the same destination address will use
the same dst.

This change tries to avoid per packet route lookup caching
the destination address of the latest successful lookup, and
reusing it for the next packet when the above conditions are
in place. Ingress traffic for most servers should fit.

The measured performance delta under UDP flood vs a recvmmsg
receiver is as follow:

vanilla		patched		delta
Kpps		Kpps		%
1431		1664		+14

In the worst-case scenario - each packet has a different
destination address - the performance delta is within noise
range

Signed-off-by: Paolo Abeni <pabeni@...hat.com>
---
 net/ipv6/ip6_input.c | 30 ++++++++++++++++++++++++++----
 1 file changed, 26 insertions(+), 4 deletions(-)

diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c
index ef7f707d9ae3..b7b947a9ddc9 100644
--- a/net/ipv6/ip6_input.c
+++ b/net/ipv6/ip6_input.c
@@ -44,10 +44,16 @@
 #include <net/inet_ecn.h>
 #include <net/dst_metadata.h>
 
+struct ip6_route_input_hint {
+	unsigned long	refdst;
+	struct in6_addr daddr;
+};
+
 INDIRECT_CALLABLE_DECLARE(void udp_v6_early_demux(struct sk_buff *));
 INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *));
 static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
-				struct sk_buff *skb)
+				struct sk_buff *skb,
+				struct ip6_route_input_hint *hint)
 {
 	void (*edemux)(struct sk_buff *skb);
 
@@ -59,7 +65,13 @@ static void ip6_rcv_finish_core(struct net *net, struct sock *sk,
 			INDIRECT_CALL_2(edemux, tcp_v6_early_demux,
 					udp_v6_early_demux, skb);
 	}
-	if (!skb_valid_dst(skb))
+
+	if (skb_valid_dst(skb))
+		return;
+
+	if (hint && ipv6_addr_equal(&hint->daddr, &ipv6_hdr(skb)->daddr))
+		__skb_dst_copy(skb, hint->refdst);
+	else
 		ip6_route_input(skb);
 }
 
@@ -71,7 +83,7 @@ int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	skb = l3mdev_ip6_rcv(skb);
 	if (!skb)
 		return NET_RX_SUCCESS;
-	ip6_rcv_finish_core(net, sk, skb);
+	ip6_rcv_finish_core(net, sk, skb, NULL);
 
 	return dst_input(skb);
 }
@@ -89,6 +101,7 @@ static void ip6_sublist_rcv_finish(struct list_head *head)
 static void ip6_list_rcv_finish(struct net *net, struct sock *sk,
 				struct list_head *head)
 {
+	struct ip6_route_input_hint _hint, *hint = NULL;
 	struct dst_entry *curr_dst = NULL;
 	struct sk_buff *skb, *next;
 	struct list_head sublist;
@@ -104,9 +117,18 @@ 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);
+		ip6_rcv_finish_core(net, sk, skb, hint);
 		dst = skb_dst(skb);
 		if (curr_dst != dst) {
+#ifndef CONFIG_IPV6_SUBTREES
+			if (!net->ipv6.fib6_has_custom_rules) {
+				_hint.refdst = skb->_skb_refdst;
+				memcpy(&_hint.daddr, &ipv6_hdr(skb)->daddr,
+				       sizeof(_hint.daddr));
+				hint = &_hint;
+			}
+#endif
+
 			/* dispatch old sublist */
 			if (!list_empty(&sublist))
 				ip6_sublist_rcv_finish(&sublist);
-- 
2.21.0