ipvs: Fix IPv4 FWMARK virtual services

This fixes the use of fwmarks to denote IPv4 virtual services
which was unfortunately broken as a result of the integration
of IPv6 support into IPVS, which was included in 2.6.28.

The problem arises because fwmarks are stored in the 4th octet
of a union nf_inet_addr .all, however in the case of IPv4 only
the first octet, corresponding to .ip, is assigned and compared.

In other words, using .all = { 0, 0, 0, htonl(svc->fwmark) always
results in a value of 0 (32bits) being stored for IPv4. This means
that one fwmark can be used, as it ends up being mapped to 0, but things
break down when multiple fwmarks are used, as they all end up being mapped
to 0.

As fwmarks are 32bits a reasonable fix seems to be to just store the fwmark
in .ip, and comparing and storing .ip when fwmarks are used.

This patch makes the assumption that in calls to ip_vs_ct_in_get()
and ip_vs_sched_persist() if the proto parameter is IPPROTO_IP then
we are dealing with an fwmark. I believe this is valid as ip_vs_in()
does fairly strict filtering on the protocol and IPPROTO_IP should
not be used in these calls unless explicitly passed when making
these calls for fwmarks in ip_vs_sched_persist().

Tested-by: Fabien Duchêne <fabien.duchene@student.uclouvain.be>
Cc: Joseph Mack NA3T <jmack@wm7d.net>
Cc: Julius Volz <julius.volz@gmail.com>
Signed-off-by: Simon Horman <horms@verge.net.au>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c
index 60aba45023ff7e9d687d356c1aaf4edfebde7e2d..77bfdfeb966e99c0e0212271319fbe4c7eafbe98 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_conn.c
+++ b/net/netfilter/ipvs/ip_vs_conn.c
@@ -260,7 +260,10 @@ struct ip_vs_conn *ip_vs_ct_in_get
        list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) {
                if (cp->af == af &&
                    ip_vs_addr_equal(af, s_addr, &cp->caddr) &&
-                   ip_vs_addr_equal(af, d_addr, &cp->vaddr) &&
+                   /* protocol should only be IPPROTO_IP if
+                    * d_addr is a fwmark */
+                   ip_vs_addr_equal(protocol == IPPROTO_IP ? AF_UNSPEC : af,
+                                    d_addr, &cp->vaddr) &&
                    s_port == cp->cport && d_port == cp->vport &&
                    cp->flags & IP_VS_CONN_F_TEMPLATE &&
                    protocol == cp->protocol) {
@@ -698,7 +701,9 @@ ip_vs_conn_new(int af, int proto, const union nf_inet_addr *caddr, __be16 cport,
        cp->cport          = cport;
        ip_vs_addr_copy(af, &cp->vaddr, vaddr);
        cp->vport          = vport;
-       ip_vs_addr_copy(af, &cp->daddr, daddr);
+       /* proto should only be IPPROTO_IP if d_addr is a fwmark */
+       ip_vs_addr_copy(proto == IPPROTO_IP ? AF_UNSPEC : af,
+                       &cp->daddr, daddr);
        cp->dport          = dport;
        cp->flags          = flags;
        spin_lock_init(&cp->lock);

diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index cb3e031335ebc4af9a95e5a359c10c3805c8754d..8dddb17a947a7be424d28e4f987939a02ff5dc54 100644 (file)
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -278,7 +278,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
                 */
                if (svc->fwmark) {
                        union nf_inet_addr fwmark = {
-                               .all = { 0, 0, 0, htonl(svc->fwmark) }
+                               .ip = htonl(svc->fwmark)
                        };
 
                        ct = ip_vs_ct_in_get(svc->af, IPPROTO_IP, &snet, 0,
@@ -306,7 +306,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc,
                         */
                        if (svc->fwmark) {
                                union nf_inet_addr fwmark = {
-                                       .all = { 0, 0, 0, htonl(svc->fwmark) }
+                                       .ip = htonl(svc->fwmark)
                                };
 
                                ct = ip_vs_conn_new(svc->af, IPPROTO_IP,