From 82944485937a3afbcda99f48c8375de100934697 Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sat, 29 Apr 2017 20:33:09 +0300 Subject: [PATCH] ipvs: SNAT packet replies only for NATed connections commit 3c5ab3f395d66a9e4e937fcfdf6ebc63894f028b upstream. We do not check if packet from real server is for NAT connection before performing SNAT. This causes problems for setups that use DR/TUN and allow local clients to access the real server directly, for example: - local client in director creates IPVS-DR/TUN connection CIP->VIP and the request packets are routed to RIP. Talks are finished but IPVS connection is not expired yet. - second local client creates non-IPVS connection CIP->RIP with same reply tuple RIP->CIP and when replies are received on LOCAL_IN we wrongly assign them for the first client connection because RIP->CIP matches the reply direction. As result, IPVS SNATs replies for non-IPVS connections. The problem is more visible to local UDP clients but in rare cases it can happen also for TCP or remote clients when the real server sends the reply traffic via the director. So, better to be more precise for the reply traffic. As replies are not expected for DR/TUN connections, better to not touch them. Reported-by: Nick Moriarty Tested-by: Nick Moriarty Signed-off-by: Julian Anastasov Signed-off-by: Simon Horman Signed-off-by: Greg Kroah-Hartman --- net/netfilter/ipvs/ip_vs_core.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-) diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4da560005b0e..dd1649caa2b2 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -845,10 +845,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, { unsigned int verdict = NF_DROP; - if (IP_VS_FWD_METHOD(cp) != 0) { - pr_err("shouldn't reach here, because the box is on the " - "half connection in the tun/dr module.\n"); - } + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) + goto ignore_cp; /* Ensure the checksum is correct */ if (!skb_csum_unnecessary(skb) && ip_vs_checksum_complete(skb, ihl)) { @@ -882,6 +880,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, ip_vs_notrack(skb); else ip_vs_update_conntrack(skb, cp, 0); + +ignore_cp: verdict = NF_ACCEPT; out: @@ -1242,8 +1242,11 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in */ cp = pp->conn_out_get(ipvs, af, skb, &iph); - if (likely(cp)) + if (likely(cp)) { + if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) + goto ignore_cp; return handle_response(af, skb, pd, cp, &iph, hooknum); + } if (sysctl_nat_icmp_send(ipvs) && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || @@ -1285,9 +1288,15 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in } } } + +out: IP_VS_DBG_PKT(12, af, pp, skb, iph.off, "ip_vs_out: packet continues traversal as normal"); return NF_ACCEPT; + +ignore_cp: + __ip_vs_conn_put(cp); + goto out; } /* -- 2.20.1