[libvirt] [PATCH 1/2] util/viriptables: add/remove rules that short-circuit masquerading

[Laszlo Ersek]

The functions
- iptablesAddForwardDontMasquerade(),
- iptablesRemoveForwardDontMasquerade
handle exceptions in the masquerading implemented in the POSTROUTING chain
of the "nat" table. Such exceptions should be added as chronologically
latest, logically top-most rules.

The bridge driver will call these functions beginning with the next patch:
some special destination IP addresses always refer to the local
subnetwork, even though they don't match any practical subnetwork's
netmask. Packets from virbrN targeting such IP addresses are never routed
outwards, but the current rules treat them as non-virbrN-destined packets
and masquerade them. This causes problems for some receivers on virbrN.

Signed-off-by: Laszlo Ersek <lersek at redhat.com>
---
 src/util/viriptables.h   |   10 +++++
 src/util/viriptables.c   |   93 ++++++++++++++++++++++++++++++++++++++++++++++
 src/libvirt_private.syms |    2 +
 3 files changed, 105 insertions(+), 0 deletions(-)

diff --git a/src/util/viriptables.h b/src/util/viriptables.h
index b7ce59b..200dbbc 100644
--- a/src/util/viriptables.h
+++ b/src/util/viriptables.h
@@ -117,6 +117,16 @@ int              iptablesRemoveForwardMasquerade (iptablesContext *ctx,
                                                   virSocketAddrRangePtr addr,
                                                   virPortRangePtr port,
                                                   const char *protocol);
+int              iptablesAddForwardDontMasquerade(iptablesContext *ctx,
+                                                  virSocketAddr *netaddr,
+                                                  unsigned int prefix,
+                                                  const char *physdev,
+                                                  const char *destaddr);
+int              iptablesRemoveForwardDontMasquerade(iptablesContext *ctx,
+                                                  virSocketAddr *netaddr,
+                                                  unsigned int prefix,
+                                                  const char *physdev,
+                                                  const char *destaddr);
 int              iptablesAddOutputFixUdpChecksum (iptablesContext *ctx,
                                                   const char *iface,
                                                   int port);
diff --git a/src/util/viriptables.c b/src/util/viriptables.c
index 16fbe9c..c6a9f6b 100644
--- a/src/util/viriptables.c
+++ b/src/util/viriptables.c
@@ -961,6 +961,99 @@ iptablesRemoveForwardMasquerade(iptablesContext *ctx,
 }
 
 
+/* Don't masquerade traffic coming from the network associated with the bridge
+ * if said traffic targets @destaddr.
+ */
+static int
+iptablesForwardDontMasquerade(iptablesContext *ctx,
+                              virSocketAddr *netaddr,
+                              unsigned int prefix,
+                              const char *physdev,
+                              const char *destaddr,
+                              int action)
+{
+    int ret = -1;
+    char *networkstr = NULL;
+    virCommandPtr cmd = NULL;
+
+    if (!(networkstr = iptablesFormatNetwork(netaddr, prefix)))
+        return -1;
+
+    if (!VIR_SOCKET_ADDR_IS_FAMILY(netaddr, AF_INET)) {
+        /* Higher level code *should* guaranteee it's impossible to get here. */
+        virReportError(VIR_ERR_INTERNAL_ERROR,
+                       _("Attempted to NAT '%s'. NAT is only supported for IPv4."),
+                       networkstr);
+        goto cleanup;
+    }
+
+    cmd = iptablesCommandNew(ctx->nat_postrouting, AF_INET, action);
+
+    if (physdev && physdev[0])
+        virCommandAddArgList(cmd, "--out-interface", physdev, NULL);
+
+    virCommandAddArgList(cmd, "--source", networkstr,
+                         "--destination", destaddr, "--jump", "RETURN", NULL);
+    ret = virCommandRun(cmd, NULL);
+cleanup:
+    virCommandFree(cmd);
+    VIR_FREE(networkstr);
+    return ret;
+}
+
+/**
+ * iptablesAddForwardDontMasquerade:
+ * @ctx: pointer to the IP table context
+ * @netaddr: the source network name
+ * @prefix: prefix (# of 1 bits) of netmask to apply to @netaddr
+ * @physdev: the physical output device or NULL
+ * @destaddr: the destination network not to masquerade for
+ *
+ * Add rules to the IP table context to avoid masquerading from
+ * @netaddr/@prefix to @destaddr on @physdev. @destaddr must be in a format
+ * directly consumable by iptables, it must not depend on user input or
+ * configuration.
+ *
+ * Returns 0 in case of success or an error code otherwise.
+ */
+int
+iptablesAddForwardDontMasquerade(iptablesContext *ctx,
+                                 virSocketAddr *netaddr,
+                                 unsigned int prefix,
+                                 const char *physdev,
+                                 const char *destaddr)
+{
+    return iptablesForwardDontMasquerade(ctx, netaddr, prefix, physdev,
+                                         destaddr, ADD);
+}
+
+/**
+ * iptablesRemoveForwardDontMasquerade:
+ * @ctx: pointer to the IP table context
+ * @netaddr: the source network name
+ * @prefix: prefix (# of 1 bits) of netmask to apply to @netaddr
+ * @physdev: the physical output device or NULL
+ * @destaddr: the destination network not to masquerade for
+ *
+ * Remove rules from the IP table context that prevent masquerading from
+ * @netaddr/@prefix to @destaddr on @physdev. @destaddr must be in a format
+ * directly consumable by iptables, it must not depend on user input or
+ * configuration.
+ *
+ * Returns 0 in case of success or an error code otherwise.
+ */
+int
+iptablesRemoveForwardDontMasquerade(iptablesContext *ctx,
+                                    virSocketAddr *netaddr,
+                                    unsigned int prefix,
+                                    const char *physdev,
+                                    const char *destaddr)
+{
+    return iptablesForwardDontMasquerade(ctx, netaddr, prefix, physdev,
+                                         destaddr, REMOVE);
+}
+
+
 static int
 iptablesOutputFixUdpChecksum(iptablesContext *ctx,
                              const char *iface,
diff --git a/src/libvirt_private.syms b/src/libvirt_private.syms
index 9d5f74b..27cc49a 100644
--- a/src/libvirt_private.syms
+++ b/src/libvirt_private.syms
@@ -1364,6 +1364,7 @@ iptablesAddForwardAllowCross;
 iptablesAddForwardAllowIn;
 iptablesAddForwardAllowOut;
 iptablesAddForwardAllowRelatedIn;
+iptablesAddForwardDontMasquerade;
 iptablesAddForwardMasquerade;
 iptablesAddForwardRejectIn;
 iptablesAddForwardRejectOut;
@@ -1376,6 +1377,7 @@ iptablesRemoveForwardAllowCross;
 iptablesRemoveForwardAllowIn;
 iptablesRemoveForwardAllowOut;
 iptablesRemoveForwardAllowRelatedIn;
+iptablesRemoveForwardDontMasquerade;
 iptablesRemoveForwardMasquerade;
 iptablesRemoveForwardRejectIn;
 iptablesRemoveForwardRejectOut;
-- 
1.7.1