ipvs: rerouting to local clients is not needed anymore

[ upstream commit 579eb62ac35845686a7c4286c0a820b4eb1f96aa ]

commit f5a41847acc5 ("ipvs: move ip_route_me_harder for ICMP")
from 2.6.37 introduced ip_route_me_harder() call for responses to
local clients, so that we can provide valid rt_src after SNAT.
It was used by TCP to provide valid daddr for ip_send_reply().
After commit 0a5ebb8000c5 ("ipv4: Pass explicit daddr arg to
ip_send_reply()." from 3.0 this rerouting is not needed anymore
and should be avoided, especially in LOCAL_IN.

Fixes 3.12.33 crash in xfrm reported by Florian Wiessner:
"3.12.33 - BUG xfrm_selector_match+0x25/0x2f6"

Cc: <stable@vger.kernel.org> # 3.10.x
Cc: <stable@vger.kernel.org> # 3.12.x
Cc: <stable@vger.kernel.org> # 3.14.x
Cc: <stable@vger.kernel.org> # 3.18.x
Reported-by: Smart Weblications GmbH - Florian Wiessner <f.wiessner@smart-weblications.de>
Tested-by: Smart Weblications GmbH - Florian Wiessner <f.wiessner@smart-weblications.de>
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Jiri Slaby <jslaby@suse.cz>

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index f7a758fae8e54d0232868967586d56dab71c0807..d1d6b82d225082728e2d10c23f91024f49190059 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -658,16 +658,24 @@ static inline int ip_vs_gather_frags(struct sk_buff *skb, u_int32_t user)
        return err;
 }
 
-static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
+                                unsigned int hooknum)
 {
+       if (!sysctl_snat_reroute(skb))
+               return 0;
+       /* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
+       if (NF_INET_LOCAL_IN == hooknum)
+               return 0;
 #ifdef CONFIG_IP_VS_IPV6
        if (af == AF_INET6) {
-               if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
+               struct dst_entry *dst = skb_dst(skb);
+
+               if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
+                   ip6_route_me_harder(skb) != 0)
                        return 1;
        } else
 #endif
-               if ((sysctl_snat_reroute(skb) ||
-                    skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+               if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
                    ip_route_me_harder(skb, RTN_LOCAL) != 0)
                        return 1;
 
@@ -790,7 +798,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
                                union nf_inet_addr *snet,
                                __u8 protocol, struct ip_vs_conn *cp,
                                struct ip_vs_protocol *pp,
-                               unsigned int offset, unsigned int ihl)
+                               unsigned int offset, unsigned int ihl,
+                               unsigned int hooknum)
 {
        unsigned int verdict = NF_DROP;
 
@@ -820,7 +829,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb,
 #endif
                ip_vs_nat_icmp(skb, pp, cp, 1);
 
-       if (ip_vs_route_me_harder(af, skb))
+       if (ip_vs_route_me_harder(af, skb, hooknum))
                goto out;
 
        /* do the statistics and put it back */
@@ -915,7 +924,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related,
 
        snet.ip = iph->saddr;
        return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-                                   pp, ciph.len, ihl);
+                                   pp, ciph.len, ihl, hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -980,7 +989,8 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related,
        snet.in6 = ciph.saddr.in6;
        writable = ciph.len;
        return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-                                   pp, writable, sizeof(struct ipv6hdr));
+                                   pp, writable, sizeof(struct ipv6hdr),
+                                   hooknum);
 }
 #endif
 
@@ -1039,7 +1049,8 @@ static inline bool is_new_conn(const struct sk_buff *skb,
  */
 static unsigned int
 handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-               struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
+               struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
+               unsigned int hooknum)
 {
        struct ip_vs_protocol *pp = pd->pp;
 
@@ -1077,7 +1088,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
         * if it came from this machine itself.  So re-compute
         * the routing information.
         */
-       if (ip_vs_route_me_harder(af, skb))
+       if (ip_vs_route_me_harder(af, skb, hooknum))
                goto drop;
 
        IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
@@ -1180,7 +1191,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af)
        cp = pp->conn_out_get(af, skb, &iph, 0);
 
        if (likely(cp))
-               return handle_response(af, skb, pd, cp, &iph);
+               return handle_response(af, skb, pd, cp, &iph, hooknum);
        if (sysctl_nat_icmp_send(net) &&
            (pp->protocol == IPPROTO_TCP ||
             pp->protocol == IPPROTO_UDP ||