From acdcecc61285faed359f1a3568c32089cc3a8329 Mon Sep 17 00:00:00 2001 From: Willem de Bruijn Date: Thu, 12 Sep 2019 21:16:39 -0400 Subject: udp: correct reuseport selection with connected sockets UDP reuseport groups can hold a mix unconnected and connected sockets. Ensure that connections only receive all traffic to their 4-tuple. Fast reuseport returns on the first reuseport match on the assumption that all matches are equal. Only if connections are present, return to the previous behavior of scoring all sockets. Record if connections are present and if so (1) treat such connected sockets as an independent match from the group, (2) only return 2-tuple matches from reuseport and (3) do not return on the first 2-tuple reuseport match to allow for a higher scoring match later. New field has_conns is set without locks. No other fields in the bitmap are modified at runtime and the field is only ever set unconditionally, so an RMW cannot miss a change. Fixes: e32ea7e74727 ("soreuseport: fast reuseport UDP socket selection") Link: http://lkml.kernel.org/r/CA+FuTSfRP09aJNYRt04SS6qj22ViiOEWaWmLAwX0psk8-PGNxw@mail.gmail.com Signed-off-by: Willem de Bruijn Acked-by: Paolo Abeni Acked-by: Craig Gallek Signed-off-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv6/datagram.c | 2 ++ net/ipv6/udp.c | 5 +++-- 2 files changed, 5 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 9ab897ded4df..96f939248d2f 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include @@ -254,6 +255,7 @@ ipv4_connected: goto out; } + reuseport_has_conns(sk, true); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 827fe7385078..5995fdc99d3f 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -158,13 +158,14 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - if (sk->sk_reuseport) { + if (sk->sk_reuseport && + sk->sk_state != TCP_ESTABLISHED) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); - if (result) + if (result && !reuseport_has_conns(sk, false)) return result; } result = sk; -- cgit v1.2.3 From 28e486037747c2180470b77c290d4090ad42f259 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 13 Sep 2019 17:45:47 +0800 Subject: ip6_gre: fix a dst leak in ip6erspan_tunnel_xmit In ip6erspan_tunnel_xmit(), if the skb will not be sent out, it has to be freed on the tx_err path. Otherwise when deleting a netns, it would cause dst/dev to leak, and dmesg shows: unregister_netdevice: waiting for lo to become free. Usage count = 1 Fixes: ef7baf5e083c ("ip6_gre: add ip6 erspan collect_md mode") Signed-off-by: Xin Long Acked-by: William Tu Signed-off-by: David S. Miller --- net/ipv6/ip6_gre.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index dd2d0b963260..d5779d6a6065 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -968,7 +968,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET6)) - return -EINVAL; + goto tx_err; key = &tun_info->key; memset(&fl6, 0, sizeof(fl6)); -- cgit v1.2.3