ipvs: add sysctl to ignore tunneled packets

This is a way to avoid nasty routing loops when multiple ipvs instances can
forward to eachother.

Signed-off-by: Alex Gartrell <agartrell@fb.com>
Signed-off-by: Simon Horman <horms@verge.net.au>

diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt
index 3ba7095..e6b1c02 100644 (file)
--- a/Documentation/networking/ipvs-sysctl.txt
+++ b/Documentation/networking/ipvs-sysctl.txt
@@ -157,6 +157,16 @@ expire_quiescent_template - BOOLEAN
        persistence template if it is to be used to schedule a new
        connection and the destination server is quiescent.
 
+ignore_tunneled - BOOLEAN
+       0 - disabled (default)
+       not 0 - enabled
+
+       If set, ipvs will set the ipvs_property on all packets which are of
+       unrecognized protocols.  This prevents us from routing tunneled
+       protocols like ipip, which is useful to prevent rescheduling
+       packets that have been tunneled to the ipvs host (i.e. to prevent
+       ipvs routing loops when ipvs is also acting as a real server).
+
 nat_icmp_send - BOOLEAN
         0 - disabled (default)
         not 0 - enabled

diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 47677f0..1096a71 100644 (file)
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -998,6 +998,7 @@ struct netns_ipvs {
        int                     sysctl_backup_only;
        int                     sysctl_conn_reuse_mode;
        int                     sysctl_schedule_icmp;
+       int                     sysctl_ignore_tunneled;
 
        /* ip_vs_lblc */
        int                     sysctl_lblc_expiration;
@@ -1121,6 +1122,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
        return ipvs->sysctl_schedule_icmp;
 }
 
+static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs)
+{
+       return ipvs->sysctl_ignore_tunneled;
+}
+
 #else
 
 static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs)
@@ -1198,6 +1204,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs)
        return 0;
 }
 
+static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs)
+{
+       return 0;
+}
+
 #endif
 
 /* IPVS core functions

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 99be680..453972c 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1760,8 +1760,16 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af)
 
        /* Protocol supported? */
        pd = ip_vs_proto_data_get(net, iph.protocol);
-       if (unlikely(!pd))
+       if (unlikely(!pd)) {
+               /* The only way we'll see this packet again is if it's
+                * encapsulated, so mark it with ipvs_property=1 so we
+                * skip it if we're ignoring tunneled packets
+                */
+               if (sysctl_ignore_tunneled(ipvs))
+                       skb->ipvs_property = 1;
+
                return NF_ACCEPT;
+       }
        pp = pd->pp;
        /*
         * Check if the packet belongs to an existing connection entry

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 31d80e2..7338827 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -1850,6 +1850,12 @@ static struct ctl_table vs_vars[] = {
                .mode           = 0644,
                .proc_handler   = proc_dointvec,
        },
+       {
+               .procname       = "ignore_tunneled",
+               .maxlen         = sizeof(int),
+               .mode           = 0644,
+               .proc_handler   = proc_dointvec,
+       },
 #ifdef CONFIG_IP_VS_DEBUG
        {
                .procname       = "debug_level",
@@ -3902,6 +3908,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net)
        ipvs->sysctl_conn_reuse_mode = 1;
        tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode;
        tbl[idx++].data = &ipvs->sysctl_schedule_icmp;
+       tbl[idx++].data = &ipvs->sysctl_ignore_tunneled;
 
        ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl);
        if (ipvs->sysctl_hdr == NULL) {