From 7487449c86c65202b3b725c4524cb48dd65e4e6f Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 28 Sep 2017 15:51:36 +0200 Subject: IPv4: early demux can return an error code Currently no error is emitted, but this infrastructure will used by the next patch to allow source address validation for mcast sockets. Since early demux can do a route lookup and an ipv4 route lookup can return an error code this is consistent with the current ipv4 route infrastructure. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/protocol.h | 4 ++-- include/net/tcp.h | 2 +- include/net/udp.h | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'include') diff --git a/include/net/protocol.h b/include/net/protocol.h index 65ba335b0e7e..4fc75f7ae23b 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -39,8 +39,8 @@ /* This is used to register protocols. */ struct net_protocol { - void (*early_demux)(struct sk_buff *skb); - void (*early_demux_handler)(struct sk_buff *skb); + int (*early_demux)(struct sk_buff *skb); + int (*early_demux_handler)(struct sk_buff *skb); int (*handler)(struct sk_buff *skb); void (*err_handler)(struct sk_buff *skb, u32 info); unsigned int no_policy:1, diff --git a/include/net/tcp.h b/include/net/tcp.h index 3bc910a9bfc6..89974c5286d8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -345,7 +345,7 @@ void tcp_v4_err(struct sk_buff *skb, u32); void tcp_shutdown(struct sock *sk, int how); -void tcp_v4_early_demux(struct sk_buff *skb); +int tcp_v4_early_demux(struct sk_buff *skb); int tcp_v4_rcv(struct sk_buff *skb); int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw); diff --git a/include/net/udp.h b/include/net/udp.h index 12dfbfe2e2d7..6c759c8594e2 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -259,7 +259,7 @@ static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags, return __skb_recv_udp(sk, flags, noblock, &peeked, &off, err); } -void udp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst); int udp_get_port(struct sock *sk, unsigned short snum, int (*saddr_cmp)(const struct sock *, -- cgit v1.2.3 From bc044e8db7962e727a75b591b9851ff2ac5cf846 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 28 Sep 2017 15:51:37 +0200 Subject: udp: perform source validation for mcast early demux The UDP early demux can leverate the rx dst cache even for multicast unconnected sockets. In such scenario the ipv4 source address is validated only on the first packet in the given flow. After that, when we fetch the dst entry from the socket rx cache, we stop enforcing the rp_filter and we even start accepting any kind of martian addresses. Disabling the dst cache for unconnected multicast socket will cause large performace regression, nearly reducing by half the max ingress tput. Instead we factor out a route helper to completely validate an skb source address for multicast packets and we call it from the UDP early demux for mcast packets landing on unconnected sockets, after successful fetching the related cached dst entry. This still gives a measurable, but limited performance regression: rp_filter = 0 rp_filter = 1 edmux disabled: 1182 Kpps 1127 Kpps edmux before: 2238 Kpps 2238 Kpps edmux after: 2037 Kpps 2019 Kpps The above figures are on top of current net tree. Applying the net-next commit 6e617de84e87 ("net: avoid a full fib lookup when rp_filter is disabled.") the delta with rp_filter == 0 will decrease even more. Fixes: 421b3885bf6d ("udp: ipv4: Add udp early demux") Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- include/net/route.h | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/route.h b/include/net/route.h index 57dfc6850d37..d538e6db1afe 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -175,7 +175,9 @@ static inline struct rtable *ip_route_output_gre(struct net *net, struct flowi4 fl4->fl4_gre_key = gre_key; return ip_route_output_key(net, fl4); } - +int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, + u8 tos, struct net_device *dev, + 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_input_rcu(struct sk_buff *skb, __be32 dst, __be32 src, -- cgit v1.2.3